{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/video-captioning","name":"Video Captioning","slug":"video-captioning","description_markdown":"**Video Captioning** is a task of automatic captioning a video by understanding the action and event in the video which can help in the retrieval of the video efficiently through text.\r\n\r\n\r\n<span class=\"description-source\">Source: [NITS-VC System for VATEX Video Captioning Challenge 2020 ](https://arxiv.org/abs/2006.04058)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":473,"papers_with_code":211,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":38,"subtasks":6,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/video-captioning-on-msr-vtt-1","slug":"video-captioning-on-msr-vtt-1","dataset":"MSR-VTT","dataset_url":"/dataset/msr-vtt","rows_in_archive":24,"metrics":["CIDEr","METEOR","ROUGE-L","BLEU-4","GS"],"first_row_in_archive_order":{"model":"mPLUG-2","paper_title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","paper_url":"/paper/mplug-2-a-modularized-multi-modal-foundation","paper_date":"2023-02-01","arxiv_id":"2302.00402","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"x-plug/mplug-owl","url":"https://github.com/x-plug/mplug-owl"},{"title":"alibaba/AliceMind","url":"https://github.com/alibaba/AliceMind"},{"title":"X-PLUG/mPLUG-2","url":"https://github.com/X-PLUG/mPLUG-2"}],"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}},"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/video-captioning-on-msvd-1","slug":"video-captioning-on-msvd-1","dataset":"MSVD","dataset_url":"/dataset/msvd","rows_in_archive":16,"metrics":["CIDEr","BLEU-4","METEOR","ROUGE-L","GS"],"first_row_in_archive_order":{"model":"MaMMUT","paper_title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","paper_url":"/paper/mammut-a-simple-architecture-for-joint","paper_date":"2023-03-29","arxiv_id":"2303.16839","code_links":[{"title":"lucidrains/mammut-pytorch","url":"https://github.com/lucidrains/mammut-pytorch"}],"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mammut-a-simple-architecture-for-joint#ran","syntology_url":"https://syntology.ai/paper/2303.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16839"}},"official":null}}},{"leaderboard":"/sota/video-captioning-on-youcook2","slug":"video-captioning-on-youcook2","dataset":"YouCook2","dataset_url":"/dataset/youcook2","rows_in_archive":14,"metrics":["BLEU-4","BLEU-3","CIDEr","ROUGE-L","METEOR"],"first_row_in_archive_order":{"model":"VAST","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_date":"2023-05-29","arxiv_id":"2305.18500","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/video-captioning-on-vatex-1","slug":"video-captioning-on-vatex-1","dataset":"VATEX","dataset_url":"/dataset/vatex","rows_in_archive":10,"metrics":["BLEU-4","CIDEr","METEOR","ROUGE-L"],"first_row_in_archive_order":{"model":"VALOR","paper_title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","paper_url":"/paper/valor-vision-audio-language-omni-perception","paper_date":"2023-04-17","arxiv_id":"2304.08345","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"}],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-activitynet-captions","slug":"video-captioning-on-activitynet-captions","dataset":"ActivityNet Captions","dataset_url":"/dataset/activitynet-captions","rows_in_archive":5,"metrics":["BLEU4","BLEU-3","CIDEr","ROUGE-L","METEOR"],"first_row_in_archive_order":{"model":"VideoCoCa","paper_title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","paper_url":"/paper/video-text-modeling-with-zero-shot-transfer","paper_date":"2022-12-09","arxiv_id":"2212.04979","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-msrvtt-ctn","slug":"video-captioning-on-msrvtt-ctn","dataset":"MSRVTT-CTN","dataset_url":"/dataset/msrvtt-ctn","rows_in_archive":4,"metrics":["CIDEr","SPICE","ROUGE-L"],"first_row_in_archive_order":{"model":"CEN","paper_title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","paper_url":"/paper/narrativebridge-enhancing-video-captioning","paper_date":"2024-06-10","arxiv_id":"2406.06499","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-msvd-ctn","slug":"video-captioning-on-msvd-ctn","dataset":"MSVD-CTN","dataset_url":"/dataset/msvd-ctn","rows_in_archive":4,"metrics":["CIDEr","ROUGE-L","SPICE"],"first_row_in_archive_order":{"model":"CEN","paper_title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","paper_url":"/paper/narrativebridge-enhancing-video-captioning","paper_date":"2024-06-10","arxiv_id":"2406.06499","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-hindi-msr-vtt","slug":"video-captioning-on-hindi-msr-vtt","dataset":"Hindi MSR-VTT","dataset_url":"/dataset/hindi-msr-vtt","rows_in_archive":2,"metrics":["BLEU4"],"first_row_in_archive_order":{"model":"SBD_Keyframe","paper_title":"An Efficient Keyframes Selection Based Framework for Video Captioning","paper_url":"/paper/an-efficient-keyframes-selection-based","paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-shot2story20k","slug":"video-captioning-on-shot2story20k","dataset":"Shot2Story20K","dataset_url":"/dataset/shot2story20k","rows_in_archive":2,"metrics":["CIDEr","BLEU-4","METEOR","ROUGE"],"first_row_in_archive_order":{"model":"Shotluck-Holmes (3.1B)","paper_title":"Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization","paper_url":"/paper/shotluck-holmes-a-family-of-efficient-small","paper_date":"2024-05-31","arxiv_id":"2405.20648","code_links":[{"title":"Skyline-9/Shotluck-Holmes","url":"https://github.com/Skyline-9/Shotluck-Holmes"}],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-tvc","slug":"video-captioning-on-tvc","dataset":"TVC","dataset_url":"/dataset/tvc","rows_in_archive":2,"metrics":["BLEU-4","CIDEr"],"first_row_in_archive_order":{"model":"VAST","paper_title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","paper_url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","paper_date":"2023-05-29","arxiv_id":"2305.18500","code_links":[{"title":"TXH-mercury/VALOR","url":"https://github.com/TXH-mercury/VALOR"},{"title":"txh-mercury/vast","url":"https://github.com/txh-mercury/vast"}],"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/video-captioning-on-chinaopen-1k-1","slug":"video-captioning-on-chinaopen-1k-1","dataset":"ChinaOpen-1k","dataset_url":"/dataset/chinaopen","rows_in_archive":1,"metrics":["BLEU4","CIDEr","METEOR"],"first_row_in_archive_order":{"model":"GVT","paper_title":"ChinaOpen: A Dataset for Open-world Multimodal Learning","paper_url":"/paper/chinaopen-a-dataset-for-open-world-multimodal-1","paper_date":"2023-05-10","arxiv_id":"2305.05880","code_links":[{"title":"dong03/GenerativeVideo2Text","url":"https://github.com/dong03/GenerativeVideo2Text"}],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-msvd-indonesian","slug":"video-captioning-on-msvd-indonesian","dataset":"MSVD-Indonesian","dataset_url":"/dataset/msvd-indonesian","rows_in_archive":1,"metrics":["BLEU-4","CIDEr","METEOR","ROUGE-L"],"first_row_in_archive_order":{"model":"VNS-GRU (Cross-Lingual)","paper_title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","paper_url":"/paper/msvd-indonesian-a-benchmark-for-multimodal","paper_date":"2023-06-20","arxiv_id":"2306.11341","code_links":[{"title":"willyfh/msvd-indonesian","url":"https://github.com/willyfh/msvd-indonesian"}],"syntology":null}},{"leaderboard":"/sota/video-captioning-on-vidchapters-7m","slug":"video-captioning-on-vidchapters-7m","dataset":"VidChapters-7M","dataset_url":"/dataset/vidchapters-7m","rows_in_archive":1,"metrics":["CIDEr"],"first_row_in_archive_order":{"model":"Vid2Seq","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/msr-vtt","name":"MSR-VTT","full_name":"","num_papers_in_archive":640},{"url":"/dataset/msvd","name":"MSVD","full_name":"Microsoft Research Video Description Corpus","num_papers_in_archive":327},{"url":"/dataset/howto100m","name":"HowTo100M","full_name":"HowTo100M","num_papers_in_archive":286},{"url":"/dataset/webvid","name":"WebVid","full_name":"","num_papers_in_archive":257},{"url":"/dataset/activitynet-captions","name":"ActivityNet Captions","full_name":"","num_papers_in_archive":255},{"url":"/dataset/youcook2","name":"YouCook2","full_name":"","num_papers_in_archive":198},{"url":"/dataset/vatex","name":"VATEX","full_name":"Video And TEXt","num_papers_in_archive":118},{"url":"/dataset/tgif","name":"TGIF","full_name":"Tumblr GIF","num_papers_in_archive":51},{"url":"/dataset/youcook","name":"YouCook","full_name":"","num_papers_in_archive":45},{"url":"/dataset/mtl-aqa","name":"MTL-AQA","full_name":"","num_papers_in_archive":33},{"url":"/dataset/value","name":"VALUE","full_name":"Video-And-Language Understanding Evaluation","num_papers_in_archive":30},{"url":"/dataset/how2qa","name":"How2QA","full_name":"How2QA","num_papers_in_archive":28},{"url":"/dataset/violin","name":"Violin","full_name":"VIdeO-and-Language INference","num_papers_in_archive":18},{"url":"/dataset/tvc","name":"TVC","full_name":"TV show Captions","num_papers_in_archive":16},{"url":"/dataset/mass","name":"MaSS","full_name":"","num_papers_in_archive":15},{"url":"/dataset/vitt","name":"ViTT","full_name":"Video Timeline Tags","num_papers_in_archive":14},{"url":"/dataset/egoexolearn","name":"EgoExoLearn","full_name":"","num_papers_in_archive":12},{"url":"/dataset/2024-ai-city-challenge-mtmc-people-tracking","name":"2024 AI City Challenge","full_name":"","num_papers_in_archive":10},{"url":"/dataset/how2r","name":"How2R","full_name":"How2R","num_papers_in_archive":9},{"url":"/dataset/v2c","name":"V2C","full_name":"Video-to-Commonsense","num_papers_in_archive":6},{"url":"/dataset/skyeye-968k","name":"SkyEye-968k","full_name":"","num_papers_in_archive":5},{"url":"/dataset/vidchapters-7m","name":"VidChapters-7M","full_name":"","num_papers_in_archive":5},{"url":"/dataset/msrvtt-ctn","name":"MSRVTT-CTN","full_name":"MSRVTT Causal-Temporal Narrative","num_papers_in_archive":4},{"url":"/dataset/msvd-ctn","name":"MSVD-CTN","full_name":"MSVD Causal-Temporal Narrative","num_papers_in_archive":4},{"url":"/dataset/youku-mplug","name":"Youku-mPLUG","full_name":"","num_papers_in_archive":4},{"url":"/dataset/m-vad-names","name":"M-VAD Names","full_name":"M-VAD Names Dataset","num_papers_in_archive":3},{"url":"/dataset/shot2story20k","name":"Shot2Story20K","full_name":"","num_papers_in_archive":3},{"url":"/dataset/hindi-msr-vtt","name":"Hindi MSR-VTT","full_name":"Hindi Microsoft reseacrh video to text","num_papers_in_archive":2},{"url":"/dataset/longvale","name":"LongVALE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/mmac-captions","name":"MMAC Captions","full_name":"","num_papers_in_archive":2},{"url":"/dataset/nsva","name":"NSVA","full_name":"NBA dataset for Sports Video Analysis","num_papers_in_archive":2},{"url":"/dataset/chinaopen","name":"ChinaOpen-1k","full_name":"","num_papers_in_archive":1},{"url":"/dataset/kinetic-gebc","name":"Kinetics-GEB+","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lsmdc-context","name":"LSMDC-Context","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/msvd-indonesian","name":"MSVD-Indonesian","full_name":"","num_papers_in_archive":1},{"url":"/dataset/w-oops","name":"W-Oops","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vript","name":"Vript","full_name":"🎬 Vript: A Video Is Worth Thousands of Words","num_papers_in_archive":0}],"subtasks":[{"url":"/task/audio-visual-video-captioning","name":"Audio-Visual Video Captioning"},{"url":"/task/boundary-captioning","name":"Boundary Captioning"},{"url":"/task/dense-video-captioning","name":"Dense Video Captioning"},{"url":"/task/live-video-captioning","name":"Live Video Captioning"},{"url":"/task/video-boundary-captioning","name":"Video Boundary Captioning"},{"url":"/task/visual-text-correction","name":"Visual Text Correction"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":473,"of_with_code":211,"tagged_in_all":473,"counts":{"archive_papers_tagged":473,"with_a_code_link":211,"where_syntology_ran_a_sample":64,"not_listed_spam_title":0,"listed":473,"listed_where_code_ran":64,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":55,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":55,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/eco-efficient-convolutional-network-for","slug":"eco-efficient-convolutional-network-for","title":"ECO: Efficient Convolutional Network for Online Video Understanding","date":"2018-04-24","arxiv_id":"1804.09066","repositories_listed":6,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/eco-efficient-convolutional-network-for#ran","syntology_url":"https://syntology.ai/paper/1804.09066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.09066"}},"official":{"repos":["mzolfaghari/ECO-efficient-video-understanding"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/top-down-visual-saliency-guided-by-captions","slug":"top-down-visual-saliency-guided-by-captions","title":"Top-down Visual Saliency Guided by Captions","date":"2016-12-21","arxiv_id":"1612.07360","repositories_listed":6,"syntology":null},{"url":"/paper/delving-deeper-into-convolutional-networks","slug":"delving-deeper-into-convolutional-networks","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","date":"2015-11-19","arxiv_id":"1511.06432","repositories_listed":6,"syntology":null},{"url":"/paper/frozen-in-time-a-joint-video-and-image","slug":"frozen-in-time-a-joint-video-and-image","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","date":"2021-04-01","arxiv_id":"2104.00650","repositories_listed":5,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/frozen-in-time-a-joint-video-and-image#ran","syntology_url":"https://syntology.ai/paper/2104.00650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00650"}},"official":{"repos":["m-bain/frozen-in-time"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/what-and-how-well-you-performed-a-multitask","slug":"what-and-how-well-you-performed-a-multitask","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","date":"2019-04-08","arxiv_id":"1904.04346","repositories_listed":5,"syntology":null},{"url":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","repositories_listed":4,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":8,"n_instrument":9,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}},"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/cap4video-what-can-auxiliary-captions-do-for","slug":"cap4video-what-can-auxiliary-captions-do-for","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","date":"2022-12-31","arxiv_id":"2301.00184","repositories_listed":4,"syntology":{"n":25,"n_ran":20,"n_constructed":0,"n_ran_checked":9,"n_instrument":11,"n_unverified":5,"n_honours":5,"n_violates":1,"n_no_contract":3,"n_pointer_only":11,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 5 honoured, 1 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cap4video-what-can-auxiliary-captions-do-for#ran","syntology_url":"https://syntology.ai/paper/2301.00184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00184"}},"official":{"repos":["whwu95/Cap4Video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/expectation-maximization-contrastive-learning","slug":"expectation-maximization-contrastive-learning","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","date":"2022-11-21","arxiv_id":"2211.11427","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/expectation-maximization-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2211.11427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.11427"}},"official":{"repos":["jpthu17/emcl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/multi-modal-dense-video-captioning","slug":"multi-modal-dense-video-captioning","title":"Multi-modal Dense Video Captioning","date":"2020-03-17","arxiv_id":"2003.07758","repositories_listed":4,"syntology":null},{"url":"/paper/vatex-a-large-scale-high-quality-multilingual","slug":"vatex-a-large-scale-high-quality-multilingual","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","date":"2019-04-06","arxiv_id":"1904.03493","repositories_listed":4,"syntology":null},{"url":"/paper/videollama-2-advancing-spatial-temporal","slug":"videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","arxiv_id":"2406.07476","repositories_listed":3,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/videollama-2-advancing-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2406.07476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07476"}},"official":{"repos":["damo-nlp-sg/videollama2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/vid2seq-large-scale-pretraining-of-a-visual","slug":"vid2seq-large-scale-pretraining-of-a-visual","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","date":"2023-02-27","arxiv_id":"2302.14115","repositories_listed":3,"syntology":null},{"url":"/paper/hero-hierarchical-encoder-for-video-language","slug":"hero-hierarchical-encoder-for-video-language","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","date":"2020-05-01","arxiv_id":"2005.00200","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hero-hierarchical-encoder-for-video-language#ran","syntology_url":"https://syntology.ai/paper/2005.00200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00200"}},"official":{"repos":["linjieli222/HERO"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/videobert-a-joint-model-for-video-and","slug":"videobert-a-joint-model-for-video-and","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","date":"2019-04-03","arxiv_id":"1904.01766","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videobert-a-joint-model-for-video-and#ran","syntology_url":"https://syntology.ai/paper/1904.01766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01766"}},"official":null}},{"url":"/paper/reconstruction-network-for-video-captioning","slug":"reconstruction-network-for-video-captioning","title":"Reconstruction Network for Video Captioning","date":"2018-03-30","arxiv_id":"1803.11438","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reconstruction-network-for-video-captioning#ran","syntology_url":"https://syntology.ai/paper/1803.11438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11438"}},"official":null}},{"url":"/paper/cogvideox-text-to-video-diffusion-models-with","slug":"cogvideox-text-to-video-diffusion-models-with","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","date":"2024-08-12","arxiv_id":"2408.06072","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cogvideox-text-to-video-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2408.06072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06072"}},"official":{"repos":["thudm/cogvideo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-recap-recursive-captioning-of-hour-long","slug":"video-recap-recursive-captioning-of-hour-long","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","date":"2024-02-20","arxiv_id":"2402.13250","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-recap-recursive-captioning-of-hour-long#ran","syntology_url":"https://syntology.ai/paper/2402.13250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13250"}},"official":{"repos":["md-mohaiminul/VideoRecap"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rtq-rethinking-video-language-understanding","slug":"rtq-rethinking-video-language-understanding","title":"RTQ: Rethinking Video-language Understanding Based on Image-text Model","date":"2023-12-01","arxiv_id":"2312.00347","repositories_listed":2,"syntology":null},{"url":"/paper/soccernet-2023-challenges-results","slug":"soccernet-2023-challenges-results","title":"SoccerNet 2023 Challenges Results","date":"2023-09-12","arxiv_id":"2309.06006","repositories_listed":2,"syntology":null},{"url":"/paper/learning-multi-modal-representations-by","slug":"learning-multi-modal-representations-by","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","date":"2023-07-27","arxiv_id":"2307.15220","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-multi-modal-representations-by#ran","syntology_url":"https://syntology.ai/paper/2307.15220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.15220"}},"official":{"repos":["camma-public/peskavlp","camma-public/surgvlp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/causalvlr-a-toolbox-and-benchmark-for-visual","slug":"causalvlr-a-toolbox-and-benchmark-for-visual","title":"CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning","date":"2023-06-30","arxiv_id":"2306.17462","repositories_listed":2,"syntology":null},{"url":"/paper/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 4 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}},"official":null}},{"url":"/paper/vast-a-vision-audio-subtitle-text-omni-1","slug":"vast-a-vision-audio-subtitle-text-omni-1","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","date":"2023-05-29","arxiv_id":"2305.18500","repositories_listed":2,"syntology":{"n":42,"n_ran":35,"n_constructed":4,"n_ran_checked":25,"n_instrument":10,"n_unverified":7,"n_honours":4,"n_violates":1,"n_no_contract":20,"n_pointer_only":8,"phrase":"35 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 1 violated, 20 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vast-a-vision-audio-subtitle-text-omni-1#ran","syntology_url":"https://syntology.ai/paper/2305.18500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18500"}},"official":{"repos":["txh-mercury/vast"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/soccernet-caption-dense-video-captioning-for","slug":"soccernet-caption-dense-video-captioning-for","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","date":"2023-04-10","arxiv_id":"2304.04565","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/soccernet-caption-dense-video-captioning-for#ran","syntology_url":"https://syntology.ai/paper/2304.04565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04565"}},"official":null}},{"url":"/paper/zeronlg-aligning-and-autoencoding-domains-for","slug":"zeronlg-aligning-and-autoencoding-domains-for","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","date":"2023-03-11","arxiv_id":"2303.06458","repositories_listed":2,"syntology":null},{"url":"/paper/mugen-a-playground-for-video-audio-text","slug":"mugen-a-playground-for-video-audio-text","title":"MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration","date":"2022-04-17","arxiv_id":"2204.08058","repositories_listed":2,"syntology":null},{"url":"/paper/x-modaler-a-versatile-and-high-performance","slug":"x-modaler-a-versatile-and-high-performance","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","date":"2021-08-18","arxiv_id":"2108.08217","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-dense-video-captioning-with","slug":"end-to-end-dense-video-captioning-with","title":"End-to-End Dense Video Captioning with Parallel Decoding","date":"2021-08-17","arxiv_id":"2108.07781","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-dense-video-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2108.07781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.07781"}},"official":{"repos":["ttengwang/pdvc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/enriching-video-captions-with-contextual-text","slug":"enriching-video-captions-with-contextual-text","title":"Enriching Video Captions With Contextual Text","date":"2020-07-29","arxiv_id":"2007.14682","repositories_listed":2,"syntology":null},{"url":"/paper/a-better-use-of-audio-visual-cues-dense-video","slug":"a-better-use-of-audio-visual-cues-dense-video","title":"A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer","date":"2020-05-17","arxiv_id":"2005.08271","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-better-use-of-audio-visual-cues-dense-video#ran","syntology_url":"https://syntology.ai/paper/2005.08271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08271"}},"official":{"repos":["v-iashin/BMT"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video2commonsense-generating-commonsense","slug":"video2commonsense-generating-commonsense","title":"Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning","date":"2020-03-11","arxiv_id":"2003.05162","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video2commonsense-generating-commonsense#ran","syntology_url":"https://syntology.ai/paper/2003.05162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05162"}},"official":{"repos":["jacobswan1/Video2Commonsense"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/univilm-a-unified-video-and-language-pre#ran","syntology_url":"https://syntology.ai/paper/2002.06353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06353"}},"official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/a-semantics-assisted-video-captioning-model","slug":"a-semantics-assisted-video-captioning-model","title":"A Semantics-Assisted Video Captioning Model Trained with Scheduled Sampling","date":"2019-08-31","arxiv_id":"1909.00121","repositories_listed":2,"syntology":null},{"url":"/paper/omninet-a-unified-architecture-for-multi","slug":"omninet-a-unified-architecture-for-multi","title":"OmniNet: A unified architecture for multi-modal multi-task learning","date":"2019-07-17","arxiv_id":"1907.07804","repositories_listed":2,"syntology":null},{"url":"/paper/190600283","slug":"190600283","title":"Learning to Generate Grounded Visual Captions without Localization Supervision","date":"2019-06-01","arxiv_id":"1906.00283","repositories_listed":2,"syntology":null},{"url":"/paper/video-captioning-with-recurrent-networks","slug":"video-captioning-with-recurrent-networks","title":"Video captioning with recurrent networks based on frame- and video-level features and visual content classification","date":"2015-12-09","arxiv_id":"1512.02949","repositories_listed":2,"syntology":null},{"url":"/paper/ugc-videocaptioner-an-omni-ugc-video-detail","slug":"ugc-videocaptioner-an-omni-ugc-video-detail","title":"UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks","date":"2025-07-15","arxiv_id":"2507.11336","repositories_listed":1,"syntology":null},{"url":"/paper/video-salmonn-2-captioning-enhanced-audio","slug":"video-salmonn-2-captioning-enhanced-audio","title":"video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models","date":"2025-06-18","arxiv_id":"2506.15220","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-salmonn-2-captioning-enhanced-audio#ran","syntology_url":"https://syntology.ai/paper/2506.15220","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15220"}},"official":{"repos":["bytedance/video-salmonn-2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flash-latent-aware-semi-autoregressive","slug":"flash-latent-aware-semi-autoregressive","title":"FLASH: Latent-Aware Semi-Autoregressive Speculative Decoding for Multimodal Tasks","date":"2025-05-19","arxiv_id":"2505.12728","repositories_listed":1,"syntology":null},{"url":"/paper/focusedad-character-centric-movie-audio","slug":"focusedad-character-centric-movie-audio","title":"FocusedAD: Character-centric Movie Audio Description","date":"2025-04-16","arxiv_id":"2504.12157","repositories_listed":1,"syntology":null},{"url":"/paper/caption-anything-in-video-fine-grained-object","slug":"caption-anything-in-video-fine-grained-object","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","date":"2025-04-07","arxiv_id":"2504.05541","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/caption-anything-in-video-fine-grained-object#ran","syntology_url":"https://syntology.ai/paper/2504.05541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05541"}},"official":{"repos":["yunlong10/CAT-V"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pretrained-image-text-models-are-secretly","slug":"pretrained-image-text-models-are-secretly","title":"Pretrained Image-Text Models are Secretly Video Captioners","date":"2025-02-19","arxiv_id":"2502.13363","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pretrained-image-text-models-are-secretly#ran","syntology_url":"https://syntology.ai/paper/2502.13363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13363"}},"official":{"repos":["chunhuizng/mllm-video-captioner"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vidcapbench-a-comprehensive-benchmark-of","slug":"vidcapbench-a-comprehensive-benchmark-of","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","date":"2025-02-18","arxiv_id":"2502.12782","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-working-memory-query-guided-segment","slug":"temporal-working-memory-query-guided-segment","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","date":"2025-02-09","arxiv_id":"2502.06020","repositories_listed":1,"syntology":null},{"url":"/paper/vidchain-chain-of-tasks-with-metric-based","slug":"vidchain-chain-of-tasks-with-metric-based","title":"VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning","date":"2025-01-12","arxiv_id":"2501.06761","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-banzhaf-interaction-for-general","slug":"hierarchical-banzhaf-interaction-for-general","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","date":"2024-12-30","arxiv_id":"2412.20964","repositories_listed":1,"syntology":null},{"url":"/paper/hicm-2-hierarchical-compact-memory-modeling","slug":"hicm-2-hierarchical-compact-memory-modeling","title":"HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning","date":"2024-12-19","arxiv_id":"2412.14585","repositories_listed":1,"syntology":null},{"url":"/paper/g-veval-a-versatile-metric-for-evaluating","slug":"g-veval-a-versatile-metric-for-evaluating","title":"G-VEval: A Versatile Metric for Evaluating Image and Video Captions Using GPT-4o","date":"2024-12-18","arxiv_id":"2412.13647","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/g-veval-a-versatile-metric-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2412.13647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13647"}},"official":{"repos":["ztangaj/gveval"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-location-caption-alignment-via","slug":"implicit-location-caption-alignment-via","title":"Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning","date":"2024-12-17","arxiv_id":"2412.12791","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/implicit-location-caption-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2412.12791","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12791"}},"official":{"repos":["ShipingGe/ILCACM"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/vg-tvp-multimodal-procedural-planning-via","slug":"vg-tvp-multimodal-procedural-planning-via","title":"VG-TVP: Multimodal Procedural Planning via Visually Grounded Text-Video Prompting","date":"2024-12-16","arxiv_id":"2412.11621","repositories_listed":1,"syntology":null},{"url":"/paper/videollm-knows-when-to-speak-enhancing-time","slug":"videollm-knows-when-to-speak-enhancing-time","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","date":"2024-11-27","arxiv_id":"2411.17991","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videollm-knows-when-to-speak-enhancing-time#ran","syntology_url":"https://syntology.ai/paper/2411.17991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17991"}},"official":{"repos":["yellow-binary-tree/mmduet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pseudo-labeling-with-keyword-refining-for-few","slug":"pseudo-labeling-with-keyword-refining-for-few","title":"Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning","date":"2024-11-06","arxiv_id":"2411.04059","repositories_listed":1,"syntology":null},{"url":"/paper/lvd-2m-a-long-take-video-dataset-with","slug":"lvd-2m-a-long-take-video-dataset-with","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","date":"2024-10-14","arxiv_id":"2410.10816","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lvd-2m-a-long-take-video-dataset-with#ran","syntology_url":"https://syntology.ai/paper/2410.10816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10816"}},"official":{"repos":["silentview/lvd-2m"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grounded-videollm-sharpening-fine-grained","slug":"grounded-videollm-sharpening-fine-grained","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","date":"2024-10-04","arxiv_id":"2410.03290","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-videollm-sharpening-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2410.03290","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03290"}},"official":{"repos":["whb139426/grounded-video-llm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/ifcap-image-like-retrieval-and-frequency","slug":"ifcap-image-like-retrieval-and-frequency","title":"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning","date":"2024-09-26","arxiv_id":"2409.18046","repositories_listed":1,"syntology":null},{"url":"/paper/soccernet-2024-challenges-results","slug":"soccernet-2024-challenges-results","title":"SoccerNet 2024 Challenges Results","date":"2024-09-16","arxiv_id":"2409.10587","repositories_listed":1,"syntology":null},{"url":"/paper/longvila-scaling-long-context-visual-language","slug":"longvila-scaling-long-context-visual-language","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","date":"2024-08-19","arxiv_id":"2408.10188","repositories_listed":1,"syntology":null},{"url":"/paper/skyscript-100m-1000000000-pairs-of-scripts","slug":"skyscript-100m-1000000000-pairs-of-scripts","title":"SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama","date":"2024-08-18","arxiv_id":"2408.09333","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03006","slug":"2408-03006","title":"Dual-path Collaborative Generation Network for Emotional Video Captioning","date":"2024-08-06","arxiv_id":"2408.03006","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02272","slug":"2408-02272","title":"COM Kitchens: An Unedited Overhead-view Video Dataset as a Vision-Language Benchmark","date":"2024-08-05","arxiv_id":"2408.02272","repositories_listed":1,"syntology":null},{"url":"/paper/2407-21757","slug":"2407-21757","title":"Learning Video Context as Interleaved Multimodal Sequences","date":"2024-07-31","arxiv_id":"2407.21757","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2407-21757#ran","syntology_url":"https://syntology.ai/paper/2407.21757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21757"}},"official":{"repos":["showlab/movieseq"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/effectively-leveraging-clip-for-generating","slug":"effectively-leveraging-clip-for-generating","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","date":"2024-07-30","arxiv_id":"2407.20642","repositories_listed":1,"syntology":null},{"url":"/paper/tarsier-recipes-for-training-and-evaluating-1","slug":"tarsier-recipes-for-training-and-evaluating-1","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","date":"2024-06-30","arxiv_id":"2407.00634","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tarsier-recipes-for-training-and-evaluating-1#ran","syntology_url":"https://syntology.ai/paper/2407.00634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00634"}},"official":{"repos":["bytedance/tarsier"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/live-video-captioning","slug":"live-video-captioning","title":"Live Video Captioning","date":"2024-06-20","arxiv_id":"2406.14206","repositories_listed":1,"syntology":null},{"url":"/paper/alanavlm-a-multimodal-embodied-ai-foundation","slug":"alanavlm-a-multimodal-embodied-ai-foundation","title":"AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding","date":"2024-06-19","arxiv_id":"2406.13807","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alanavlm-a-multimodal-embodied-ai-foundation#ran","syntology_url":"https://syntology.ai/paper/2406.13807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13807"}},"official":{"repos":["alanaai/evud"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-of-video-datasets-for-grounded-event","slug":"a-survey-of-video-datasets-for-grounded-event","title":"A Survey of Video Datasets for Grounded Event Understanding","date":"2024-06-14","arxiv_id":"2406.09646","repositories_listed":1,"syntology":null},{"url":"/paper/videogpt-integrating-image-and-video-encoders","slug":"videogpt-integrating-image-and-video-encoders","title":"VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding","date":"2024-06-13","arxiv_id":"2406.09418","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videogpt-integrating-image-and-video-encoders#ran","syntology_url":"https://syntology.ai/paper/2406.09418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09418"}},"official":{"repos":["mbzuai-oryx/videogpt-plus"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vript-a-video-is-worth-thousands-of-words","slug":"vript-a-video-is-worth-thousands-of-words","title":"Vript: A Video Is Worth Thousands of Words","date":"2024-06-10","arxiv_id":"2406.06040","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vript-a-video-is-worth-thousands-of-words#ran","syntology_url":"https://syntology.ai/paper/2406.06040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06040"}},"official":{"repos":["mutonix/vript"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/sharegpt4video-improving-video-understanding","slug":"sharegpt4video-improving-video-understanding","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","date":"2024-06-06","arxiv_id":"2406.04325","repositories_listed":1,"syntology":null},{"url":"/paper/shotluck-holmes-a-family-of-efficient-small","slug":"shotluck-holmes-a-family-of-efficient-small","title":"Shotluck Holmes: A Family of Efficient Small-Scale Large Language Vision Models For Video Captioning and Summarization","date":"2024-05-31","arxiv_id":"2405.20648","repositories_listed":1,"syntology":null},{"url":"/paper/vtg-llm-integrating-timestamp-knowledge-into","slug":"vtg-llm-integrating-timestamp-knowledge-into","title":"VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding","date":"2024-05-22","arxiv_id":"2405.13382","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":5,"n_instrument":10,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vtg-llm-integrating-timestamp-knowledge-into#ran","syntology_url":"https://syntology.ai/paper/2405.13382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13382"}},"official":{"repos":["gyxxyg/vtg-llm"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/narrative-action-evaluation-with-prompt","slug":"narrative-action-evaluation-with-prompt","title":"Narrative Action Evaluation with Prompt-Guided Multimodal Interaction","date":"2024-04-22","arxiv_id":"2404.14471","repositories_listed":1,"syntology":null},{"url":"/paper/movie101v2-improved-movie-narration-benchmark","slug":"movie101v2-improved-movie-narration-benchmark","title":"Movie101v2: Improved Movie Narration Benchmark","date":"2024-04-20","arxiv_id":"2404.13370","repositories_listed":1,"syntology":null},{"url":"/paper/trafficvlm-a-controllable-visual-language","slug":"trafficvlm-a-controllable-visual-language","title":"TrafficVLM: A Controllable Visual Language Model for Traffic Video Captioning","date":"2024-04-14","arxiv_id":"2404.09275","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trafficvlm-a-controllable-visual-language#ran","syntology_url":"https://syntology.ai/paper/2404.09275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09275"}},"official":{"repos":["quangminhdinh/trafficvlm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-traffic-safety-with-parallel-dense","slug":"enhancing-traffic-safety-with-parallel-dense","title":"Enhancing Traffic Safety with Parallel Dense Video Captioning for End-to-End Event Analysis","date":"2024-04-12","arxiv_id":"2404.08229","repositories_listed":1,"syntology":null},{"url":"/paper/do-you-remember-dense-video-captioning-with","slug":"do-you-remember-dense-video-captioning-with","title":"Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval","date":"2024-04-11","arxiv_id":"2404.07610","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/do-you-remember-dense-video-captioning-with#ran","syntology_url":"https://syntology.ai/paper/2404.07610","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07610"}},"official":{"repos":["ailab-kyunghee/cm2_dvc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ma-lmm-memory-augmented-large-multimodal","slug":"ma-lmm-memory-augmented-large-multimodal","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","date":"2024-04-08","arxiv_id":"2404.05726","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ma-lmm-memory-augmented-large-multimodal#ran","syntology_url":"https://syntology.ai/paper/2404.05726","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05726"}},"official":{"repos":["boheumd/MA-LMM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/streaming-dense-video-captioning","slug":"streaming-dense-video-captioning","title":"Streaming Dense Video Captioning","date":"2024-04-01","arxiv_id":"2404.01297","repositories_listed":1,"syntology":null},{"url":"/paper/omnivid-a-generative-framework-for-universal","slug":"omnivid-a-generative-framework-for-universal","title":"OmniVid: A Generative Framework for Universal Video Understanding","date":"2024-03-26","arxiv_id":"2403.17935","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/omnivid-a-generative-framework-for-universal#ran","syntology_url":"https://syntology.ai/paper/2403.17935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17935"}},"official":{"repos":["wangjk666/omnivid"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/git-towards-generalist-vision-transformer","slug":"git-towards-generalist-vision-transformer","title":"GiT: Towards Generalist Vision Transformer through Universal Language Interface","date":"2024-03-14","arxiv_id":"2403.09394","repositories_listed":1,"syntology":null},{"url":"/paper/panda-70m-captioning-70m-videos-with-multiple","slug":"panda-70m-captioning-70m-videos-with-multiple","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","date":"2024-02-29","arxiv_id":"2402.19479","repositories_listed":1,"syntology":null},{"url":"/paper/lvchat-facilitating-long-video-comprehension","slug":"lvchat-facilitating-long-video-comprehension","title":"LVCHAT: Facilitating Long Video Comprehension","date":"2024-02-19","arxiv_id":"2402.12079","repositories_listed":1,"syntology":null},{"url":"/paper/connect-collapse-corrupt-learning-cross-modal","slug":"connect-collapse-corrupt-learning-cross-modal","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","date":"2024-01-16","arxiv_id":"2401.08567","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/connect-collapse-corrupt-learning-cross-modal#ran","syntology_url":"https://syntology.ai/paper/2401.08567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08567"}},"official":{"repos":["yuhui-zh15/c3"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-recipe-for-scaling-up-text-to-video","slug":"a-recipe-for-scaling-up-text-to-video","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","date":"2023-12-25","arxiv_id":"2312.15770","repositories_listed":1,"syntology":null},{"url":"/paper/shot2story20k-a-new-benchmark-for","slug":"shot2story20k-a-new-benchmark-for","title":"Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos","date":"2023-12-16","arxiv_id":"2312.10300","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/shot2story20k-a-new-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2312.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10300"}},"official":{"repos":["bytedance/Shot2Story"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/video-summarization-towards-entity-aware","slug":"video-summarization-towards-entity-aware","title":"Video Summarization: Towards Entity-Aware Captions","date":"2023-12-01","arxiv_id":"2312.02188","repositories_listed":1,"syntology":null},{"url":"/paper/vtimellm-empower-llm-to-grasp-video-moments","slug":"vtimellm-empower-llm-to-grasp-video-moments","title":"VTimeLLM: Empower LLM to Grasp Video Moments","date":"2023-11-30","arxiv_id":"2311.18445","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vtimellm-empower-llm-to-grasp-video-moments#ran","syntology_url":"https://syntology.ai/paper/2311.18445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18445"}},"official":{"repos":["huangb23/vtimellm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-zero-shot-abilities-of-vision","slug":"analyzing-zero-shot-abilities-of-vision","title":"Analyzing Zero-Shot Abilities of Vision-Language Models on Video Understanding Tasks","date":"2023-10-07","arxiv_id":"2310.04914","repositories_listed":1,"syntology":null},{"url":"/paper/howtocaption-prompting-llms-to-transform","slug":"howtocaption-prompting-llms-to-transform","title":"HowToCaption: Prompting LLMs to Transform Video Annotations at Scale","date":"2023-10-07","arxiv_id":"2310.04900","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/howtocaption-prompting-llms-to-transform#ran","syntology_url":"https://syntology.ai/paper/2310.04900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04900"}},"official":{"repos":["ninatu/howtocaption"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vidchapters-7m-video-chapters-at-scale","slug":"vidchapters-7m-video-chapters-at-scale","title":"VidChapters-7M: Video Chapters at Scale","date":"2023-09-25","arxiv_id":"2309.13952","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vidchapters-7m-video-chapters-at-scale#ran","syntology_url":"https://syntology.ai/paper/2309.13952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.13952"}},"official":null}},{"url":"/paper/accurate-and-fast-compressed-video-captioning","slug":"accurate-and-fast-compressed-video-captioning","title":"Accurate and Fast Compressed Video Captioning","date":"2023-09-22","arxiv_id":"2309.12867","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":8,"n_ran_checked":9,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/accurate-and-fast-compressed-video-captioning#ran","syntology_url":"https://syntology.ai/paper/2309.12867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12867"}},"official":{"repos":["acherstyx/CoCap"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multicapclip-auto-encoding-prompts-for-zero","slug":"multicapclip-auto-encoding-prompts-for-zero","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","date":"2023-08-25","arxiv_id":"2308.13218","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multicapclip-auto-encoding-prompts-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.13218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13218"}},"official":{"repos":["yangbang18/multicapclip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vl-pet-vision-and-language-parameter","slug":"vl-pet-vision-and-language-parameter","title":"VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control","date":"2023-08-18","arxiv_id":"2308.09804","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vl-pet-vision-and-language-parameter#ran","syntology_url":"https://syntology.ai/paper/2308.09804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09804"}},"official":{"repos":["henryhzy/vl-pet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prompt-switch-efficient-clip-adaptation-for","slug":"prompt-switch-efficient-clip-adaptation-for","title":"Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval","date":"2023-08-15","arxiv_id":"2308.07648","repositories_listed":1,"syntology":{"n":16,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":12,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":16,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/prompt-switch-efficient-clip-adaptation-for#ran","syntology_url":"https://syntology.ai/paper/2308.07648","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07648"}},"official":{"repos":["bladewaltz1/promptswitch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/omnidatacomposer-a-unified-data-structure-for","slug":"omnidatacomposer-a-unified-data-structure-for","title":"OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation","date":"2023-08-08","arxiv_id":"2308.04126","repositories_listed":1,"syntology":null},{"url":"/paper/msvd-indonesian-a-benchmark-for-multimodal","slug":"msvd-indonesian-a-benchmark-for-multimodal","title":"MSVD-Indonesian: A Benchmark for Multimodal Video-Text Tasks in Indonesian","date":"2023-06-20","arxiv_id":"2306.11341","repositories_listed":1,"syntology":null},{"url":"/paper/llmva-gebc-large-language-model-with-video","slug":"llmva-gebc-large-language-model-with-video","title":"LLMVA-GEBC: Large Language Model with Video Adapter for Generic Event Boundary Captioning","date":"2023-06-17","arxiv_id":"2306.10354","repositories_listed":1,"syntology":null},{"url":"/paper/cosa-concatenated-sample-pretrained-vision","slug":"cosa-concatenated-sample-pretrained-vision","title":"COSA: Concatenated Sample Pretrained Vision-Language Foundation Model","date":"2023-06-15","arxiv_id":"2306.09085","repositories_listed":1,"syntology":null},{"url":"/paper/youku-mplug-a-10-million-large-scale-chinese","slug":"youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","date":"2023-06-07","arxiv_id":"2306.04362","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/youku-mplug-a-10-million-large-scale-chinese#ran","syntology_url":"https://syntology.ai/paper/2306.04362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04362"}},"official":{"repos":["x-plug/youku-mplug"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/movie101-a-new-movie-understanding-benchmark","slug":"movie101-a-new-movie-understanding-benchmark","title":"Movie101: A New Movie Understanding Benchmark","date":"2023-05-20","arxiv_id":"2305.12140","repositories_listed":1,"syntology":null}],"syntology_records":47,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":64,"papers_where_code_ran_first_page":"/task/video-captioning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/video-captioning/papers/2","json":"/task/video-captioning/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/video-captioning/papers/3","json":"/task/video-captioning/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/video-captioning/papers/4","json":"/task/video-captioning/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/video-captioning/papers/5","json":"/task/video-captioning/papers/5.json","rows":73},{"order":"ran","page":1,"of":1,"url":"/task/video-captioning/papers/ran/1","json":"/task/video-captioning/papers/ran/1.json","rows":64}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"e44aa2d2605f58d30c5d5e4eb8307dd113999593dd77efa4d4d927031ddbc0d5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}