{"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/dense-video-captioning","name":"Dense Video Captioning","slug":"dense-video-captioning","description_markdown":"Most natural videos contain numerous events. For example, in a video of a “man playing a piano”, the video might also contain “another man dancing” or “a crowd clapping”. The task of dense video captioning involves both detecting and describing events in a video.","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":76,"papers_with_code":39,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":9,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/dense-video-captioning-on-activitynet","slug":"dense-video-captioning-on-activitynet","dataset":"ActivityNet Captions","dataset_url":"/dataset/activitynet-captions","rows_in_archive":12,"metrics":["METEOR","BLEU-3","BLEU-4","CIDEr","SODA","DIV-1","DIV-2","RE-4","BLEU4","F1","Precision","Recall"],"first_row_in_archive_order":{"model":"Vid2Seq","paper_title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","paper_url":"/paper/vid2seq-large-scale-pretraining-of-a-visual","paper_date":"2023-02-27","arxiv_id":"2302.14115","code_links":[{"title":"google-research/scenic","url":"https://github.com/google-research/scenic/tree/main/scenic/projects/vid2seq"},{"title":"antoyang/VidChapters","url":"https://github.com/antoyang/VidChapters"},{"title":"KastanDay/video-pretrained-transformer","url":"https://github.com/KastanDay/video-pretrained-transformer"}],"syntology":null}},{"leaderboard":"/sota/dense-video-captioning-on-youcook2","slug":"dense-video-captioning-on-youcook2","dataset":"YouCook2","dataset_url":"/dataset/youcook2","rows_in_archive":7,"metrics":["CIDEr","METEOR","SODA","BLEU4","ROUGE-L","F1","Precision","Recall"],"first_row_in_archive_order":{"model":"HiCM²","paper_title":"HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning","paper_url":"/paper/hicm-2-hierarchical-compact-memory-modeling","paper_date":"2024-12-19","arxiv_id":"2412.14585","code_links":[{"title":"ailab-kyunghee/HiCM2-DVC","url":"https://github.com/ailab-kyunghee/HiCM2-DVC"}],"syntology":null}},{"leaderboard":"/sota/dense-video-captioning-on-vitt","slug":"dense-video-captioning-on-vitt","dataset":"ViTT","dataset_url":"/dataset/vitt","rows_in_archive":4,"metrics":["SODA","CIDEr","METEOR"],"first_row_in_archive_order":{"model":"Vid2Seq (VidChapters-7M PT)","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/dense-video-captioning-on-vidchapters-7m","slug":"dense-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/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/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/vitt","name":"ViTT","full_name":"Video Timeline Tags","num_papers_in_archive":14},{"url":"/dataset/vidchapters-7m","name":"VidChapters-7M","full_name":"","num_papers_in_archive":5},{"url":"/dataset/longvale","name":"LongVALE","full_name":"","num_papers_in_archive":2},{"url":"/dataset/sieve-swap-howto100m-cooking","name":"Sieve & Swap - HowTo100M (Cooking)","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/zero-shot-dense-video-captioning","name":"Zero-shot dense video captioning"}],"parent_tasks":[{"url":"/task/video-captioning","name":"Video Captioning"}],"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":1,"rows_per_page":100,"shown":76,"of":76,"of_with_code":39,"tagged_in_all":76,"counts":{"archive_papers_tagged":76,"with_a_code_link":39,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":76,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":3,"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/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/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/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/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/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/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/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/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/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/longvale-vision-audio-language-event","slug":"longvale-vision-audio-language-event","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","date":"2024-11-29","arxiv_id":"2411.19772","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/longvale-vision-audio-language-event#ran","syntology_url":"https://syntology.ai/paper/2411.19772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19772"}},"official":{"repos":["ttgeng233/LongVALE"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"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/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/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/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/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/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/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/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/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/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/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/visual-transformation-telling","slug":"visual-transformation-telling","title":"Visual Transformation Telling","date":"2023-05-03","arxiv_id":"2305.01928","repositories_listed":1,"syntology":null},{"url":"/paper/learning-grounded-vision-language","slug":"learning-grounded-vision-language","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","date":"2023-03-11","arxiv_id":"2303.06378","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"9 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/learning-grounded-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.06378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06378"}},"official":{"repos":["zjr2000/gvl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/semantic-metadata-extraction-from-dense-video","slug":"semantic-metadata-extraction-from-dense-video","title":"Event and Entity Extraction from Generated Video Captions","date":"2022-11-05","arxiv_id":"2211.02982","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-event-detection-and-captioning-as","slug":"unifying-event-detection-and-captioning-as","title":"Unifying Event Detection and Captioning as Sequence Generation via Pre-Training","date":"2022-07-18","arxiv_id":"2207.08625","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":4,"n_ran_checked":5,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/unifying-event-detection-and-captioning-as#ran","syntology_url":"https://syntology.ai/paper/2207.08625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08625"}},"official":{"repos":["qiqang/uedvc"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/dense-video-captioning-using-unsupervised","slug":"dense-video-captioning-using-unsupervised","title":"Dense Video Captioning Using Unsupervised Semantic Information","date":"2021-12-15","arxiv_id":"2112.08455","repositories_listed":1,"syntology":null},{"url":"/paper/global-object-proposals-for-improving-multi","slug":"global-object-proposals-for-improving-multi","title":"Global Object Proposals for Improving Multi-Sentence Video Descriptions","date":"2021-07-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/tsp-temporally-sensitive-pretraining-of-video","slug":"tsp-temporally-sensitive-pretraining-of-video","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","date":"2020-11-23","arxiv_id":"2011.11479","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-pretraining-for-dense-video","slug":"multimodal-pretraining-for-dense-video","title":"Multimodal Pretraining for Dense Video Captioning","date":"2020-11-10","arxiv_id":"2011.11760","repositories_listed":1,"syntology":null},{"url":"/paper/soda-story-oriented-dense-video-captioning","slug":"soda-story-oriented-dense-video-captioning","title":"SODA: Story Oriented Dense Video Captioning Evaluation Framework","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dense-captioning-events-in-videos-sysu","slug":"dense-captioning-events-in-videos-sysu","title":"Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020","date":"2020-06-21","arxiv_id":"2006.11693","repositories_listed":1,"syntology":null},{"url":"/paper/streamlined-dense-video-captioning","slug":"streamlined-dense-video-captioning","title":"Streamlined Dense Video Captioning","date":"2019-04-08","arxiv_id":"1904.03870","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-dense-video-captioning-with-masked","slug":"end-to-end-dense-video-captioning-with-masked","title":"End-to-End Dense Video Captioning with Masked Transformer","date":"2018-04-03","arxiv_id":"1804.00819","repositories_listed":1,"syntology":null},{"url":"/paper/bidirectional-attentive-fusion-with-context","slug":"bidirectional-attentive-fusion-with-context","title":"Bidirectional Attentive Fusion with Context Gating for Dense Video Captioning","date":"2018-03-31","arxiv_id":"1804.00100","repositories_listed":1,"syntology":null},{"url":"/paper/joint-event-detection-and-description-in","slug":"joint-event-detection-and-description-in","title":"Joint Event Detection and Description in Continuous Video Streams","date":"2018-02-28","arxiv_id":"1802.10250","repositories_listed":1,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/joint-event-detection-and-description-in#ran","syntology_url":"https://syntology.ai/paper/1802.10250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10250"}},"official":{"repos":["VisionLearningGroup/JEDDi-Net"],"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/towards-automatic-learning-of-procedures-from","slug":"towards-automatic-learning-of-procedures-from","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","date":"2017-03-28","arxiv_id":"1703.09788","repositories_listed":1,"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/towards-automatic-learning-of-procedures-from#ran","syntology_url":"https://syntology.ai/paper/1703.09788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.09788"}},"official":null}},{"url":null,"slug":"dense-video-captioning-using-graph-based","title":"Dense Video Captioning using Graph-based Sentence Summarization","date":"2025-06-25","arxiv_id":"2506.20583","repositories_listed":0,"syntology":null},{"url":null,"slug":"show-tell-and-summarize-dense-video","title":"Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization","date":"2025-06-25","arxiv_id":"2506.20567","repositories_listed":0,"syntology":null},{"url":null,"slug":"timesoccer-an-end-to-end-multimodal-large","title":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","date":"2025-04-24","arxiv_id":"2504.17365","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-and-learn-leveraging-expert-knowledge","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","date":"2025-03-14","arxiv_id":"2503.11392","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-equalized-dense-video-captioning","title":"Event-Equalized Dense Video Captioning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-temporal-event-cues-for-dense-video","title":"Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning","date":"2024-12-16","arxiv_id":"2412.11467","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-llms-for-temporal-reasoning-in-long","title":"Video LLMs for Temporal Reasoning in Long Videos","date":"2024-12-04","arxiv_id":"2412.02930","repositories_listed":0,"syntology":null},{"url":null,"slug":"seq2time-sequential-knowledge-transfer-for","title":"Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding","date":"2024-11-25","arxiv_id":"2411.16932","repositories_listed":0,"syntology":null},{"url":null,"slug":"whats-in-a-video-factorized-autoregressive","title":"Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning","date":"2024-11-22","arxiv_id":"2411.14688","repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-for-soccernet-2023-dense","title":"Technical Report for Soccernet 2023 -- Dense Video Captioning","date":"2024-10-31","arxiv_id":"2411.00882","repositories_listed":0,"syntology":null},{"url":"/paper/the-8th-ai-city-challenge","slug":"the-8th-ai-city-challenge","title":"The 8th AI City Challenge","date":"2024-04-15","arxiv_id":"2404.09432","repositories_listed":0,"syntology":null},{"url":null,"slug":"dibs-enhancing-dense-video-captioning-with","title":"DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement","date":"2024-04-03","arxiv_id":"2404.02755","repositories_listed":0,"syntology":null},{"url":null,"slug":"avicuna-audio-visual-llm-with-interleaver-and","title":"Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding","date":"2024-03-24","arxiv_id":"2403.16276","repositories_listed":0,"syntology":null},{"url":null,"slug":"exo2egodvc-dense-video-captioning-of","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","date":"2023-11-28","arxiv_id":"2311.16444","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-video-captioning-a-survey-of-techniques","title":"Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols","date":"2023-11-05","arxiv_id":"2311.02538","repositories_listed":0,"syntology":null},{"url":null,"slug":"ucf-crime-annotation-a-benchmark-for","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","date":"2023-09-25","arxiv_id":"2309.13925","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-dense-video-captioning-by-jointly","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment","date":"2023-07-05","arxiv_id":"2307.02682","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-review-of-deep-learning-for-video","title":"A Review of Deep Learning for Video Captioning","date":"2023-04-22","arxiv_id":"2304.11431","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-templated-caption-for-video","title":"Exploiting Auxiliary Caption for Video Grounding","date":"2023-01-15","arxiv_id":"2301.05997","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-closer-look-at-temporal-ordering-in-the","title":"A Closer Look at Temporal Ordering in the Segmentation of Instructional Videos","date":"2022-09-30","arxiv_id":"2209.15501","repositories_listed":0,"syntology":null},{"url":null,"slug":"recipe-generation-from-unsegmented-cooking","title":"Recipe Generation from Unsegmented Cooking Videos","date":"2022-09-21","arxiv_id":"2209.10134","repositories_listed":0,"syntology":null},{"url":null,"slug":"savchoi-detecting-suspicious-activities-using","title":"SAVCHOI: Detecting Suspicious Activities using Dense Video Captioning with Human Object Interactions","date":"2022-07-24","arxiv_id":"2207.11838","repositories_listed":0,"syntology":null},{"url":null,"slug":"pic-4th-challenge-semantic-assisted-multi","title":"PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning","date":"2022-07-06","arxiv_id":"2207.02583","repositories_listed":0,"syntology":null},{"url":"/paper/end-to-end-dense-video-captioning-as-sequence-1","slug":"end-to-end-dense-video-captioning-as-sequence-1","title":"End-to-end Dense Video Captioning as Sequence Generation","date":"2022-04-18","arxiv_id":"2204.08121","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-aware-pretraining-for-dense-video","title":"Semantic-Aware Pretraining for Dense Video Captioning","date":"2022-04-13","arxiv_id":"2204.07449","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-dense-video-captioning-as-sequence","title":"End-to-end Dense Video Captioning as Sequence Generation","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dvcflow-modeling-information-flow-towards","title":"DVCFlow: Modeling Information Flow Towards Human-like Video Captioning","date":"2021-11-19","arxiv_id":"2111.10146","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-ground-and-refine-top-down-dense-video","title":"Sketch, Ground, and Refine: Top-Down Dense Video Captioning","date":"2021-06-19","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-dense-video-captioning-via","title":"Weakly Supervised Dense Video Captioning via Jointly Usage of Knowledge Distillation and Cross-modal Matching","date":"2021-05-18","arxiv_id":"2105.08252","repositories_listed":0,"syntology":null},{"url":"/paper/iperceive-applying-common-sense-reasoning-to-1","slug":"iperceive-applying-common-sense-reasoning-to-1","title":"iPerceive: Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering","date":"2020-11-16","arxiv_id":"2011.07735","repositories_listed":0,"syntology":null},{"url":null,"slug":"sact-self-aware-multi-space-feature","title":"SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning","date":"2020-06-25","arxiv_id":"2006.14262","repositories_listed":0,"syntology":null},{"url":"/paper/team-ruc-aim3-technical-report-at-activitynet","slug":"team-ruc-aim3-technical-report-at-activitynet","title":"Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning","date":"2020-06-14","arxiv_id":"2006.07896","repositories_listed":0,"syntology":null},{"url":null,"slug":"activitynet-2019-task-3-exploring-contexts","title":"Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos","date":"2019-07-11","arxiv_id":"1907.05092","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-is-all-you-need-for-videos-self","title":"Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers","date":"2019-06-06","arxiv_id":"1906.02792","repositories_listed":0,"syntology":null},{"url":null,"slug":"ruccmu-system-report-for-dense-captioning","title":"RUC+CMU: System Report for Dense Captioning Events in Videos","date":"2018-06-22","arxiv_id":"1806.08854","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-localizing-and-describing-events-for","title":"Jointly Localizing and Describing Events for Dense Video Captioning","date":"2018-04-23","arxiv_id":"1804.08274","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-dense-video-captioning","title":"Weakly Supervised Dense Video Captioning","date":"2017-04-05","arxiv_id":"1704.01502","repositories_listed":0,"syntology":null}],"syntology_records":18,"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":2,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/dense-video-captioning-on-youcook2","since_archive":"/sota/dense-video-captioning-on-youcook2#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/dense-video-captioning-on-vitt","since_archive":"/sota/dense-video-captioning-on-vitt#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":16,"papers_where_code_ran_first_page":"/task/dense-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":"ran","page":1,"of":1,"url":"/task/dense-video-captioning/papers/ran/1","json":"/task/dense-video-captioning/papers/ran/1.json","rows":16}],"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":"85ce9e192a3795abfd0396d634f7f17491208c4e05516990e76eb8e6c9ea300d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}