{"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-understanding","name":"Video Understanding","slug":"video-understanding","description_markdown":"A crucial task of **Video Understanding** is to recognise and localise (in space and time) different actions or events appearing in the video.\r\n\r\n\r\n<span class=\"description-source\">Source: [Action Detection from a Robot-Car Perspective ](https://arxiv.org/abs/1807.11332)</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":1149,"papers_with_code":542,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":56,"subtasks":7,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/charades","name":"Charades","full_name":"","num_papers_in_archive":428},{"url":"/dataset/charades-sta","name":"Charades-STA","full_name":"","num_papers_in_archive":236},{"url":"/dataset/shanghaitech-campus","name":"ShanghaiTech Campus","full_name":"","num_papers_in_archive":207},{"url":"/dataset/seed-bench","name":"SEED-Bench","full_name":"","num_papers_in_archive":137},{"url":"/dataset/ava","name":"AVA","full_name":"Atomic Visual Actions","num_papers_in_archive":113},{"url":"/dataset/soccernet-v2","name":"SoccerNet-v2","full_name":"","num_papers_in_archive":58},{"url":"/dataset/movienet","name":"MovieNet","full_name":"MovieNet","num_papers_in_archive":54},{"url":"/dataset/internvid","name":"InternVid","full_name":"","num_papers_in_archive":46},{"url":"/dataset/epic-kitchens","name":"EPIC-KITCHENS-55","full_name":"","num_papers_in_archive":42},{"url":"/dataset/charades-ego","name":"Charades-Ego","full_name":"","num_papers_in_archive":33},{"url":"/dataset/mtl-aqa","name":"MTL-AQA","full_name":"","num_papers_in_archive":33},{"url":"/dataset/ccd","name":"CCD","full_name":"Car Crash Dataset","num_papers_in_archive":18},{"url":"/dataset/vidsitu","name":"VidSitu","full_name":"","num_papers_in_archive":18},{"url":"/dataset/situated-reasoning-star","name":"STAR Benchmark","full_name":"Situated Reasoning","num_papers_in_archive":17},{"url":"/dataset/hvu","name":"HVU","full_name":"Holistic Video Understanding","num_papers_in_archive":16},{"url":"/dataset/queryd","name":"QuerYD","full_name":"","num_papers_in_archive":15},{"url":"/dataset/ovbench","name":"OVBench","full_name":"","num_papers_in_archive":14},{"url":"/dataset/aesthetic-visual-analysis","name":"Aesthetic Visual Analysis","full_name":"Aesthetic Visual Analysis","num_papers_in_archive":12},{"url":"/dataset/dramaqa","name":"DramaQA","full_name":"","num_papers_in_archive":12},{"url":"/dataset/imagecode","name":"ImageCoDe","full_name":"Image Retrieval from Contextual Descriptions","num_papers_in_archive":11},{"url":"/dataset/moviescope","name":"Moviescope","full_name":"","num_papers_in_archive":6},{"url":"/dataset/v2c","name":"V2C","full_name":"Video-to-Commonsense","num_papers_in_archive":6},{"url":"/dataset/chronomagic","name":"ChronoMagic","full_name":"","num_papers_in_archive":5},{"url":"/dataset/infinibench","name":"InfiniBench","full_name":"InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding","num_papers_in_archive":5},{"url":"/dataset/mlb-youtube-dataset","name":"MLB-YouTube Dataset","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/real-life-violence-situations-dataset","name":"Real Life Violence Situations Dataset","full_name":"","num_papers_in_archive":5},{"url":"/dataset/soccerdb","name":"SoccerDB","full_name":"","num_papers_in_archive":5},{"url":"/dataset/m-3-vos","name":"M$^3$-VOS","full_name":"M$^3$-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation","num_papers_in_archive":4},{"url":"/dataset/query-focused-video-summarization-dataset","name":"Query-Focused Video Summarization Dataset","full_name":"","num_papers_in_archive":4},{"url":"/dataset/converse","name":"CONVERSE","full_name":"","num_papers_in_archive":3},{"url":"/dataset/deepsportradar-v1","name":"DeepSportRadar-v1","full_name":"","num_papers_in_archive":3},{"url":"/dataset/fitness-aqa","name":"Fitness-AQA","full_name":"Fitness Action Quality Assessment [ECCV 2022]","num_papers_in_archive":3},{"url":"/dataset/3massiv","name":"3MASSIV","full_name":"","num_papers_in_archive":2},{"url":"/dataset/chronomagic-pro","name":"ChronoMagic-Pro","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cinescale","name":"Cinescale","full_name":"CineScale: A dataset of cinematic shot scale in movies","num_papers_in_archive":2},{"url":"/dataset/egok360","name":"EGOK360","full_name":"","num_papers_in_archive":2},{"url":"/dataset/stanford-ecm","name":"Stanford-ECM","full_name":"Stanford-ECM","num_papers_in_archive":2},{"url":"/dataset/svbench","name":"SVBench","full_name":"Streaming Video Understanding Benchmark","num_papers_in_archive":2},{"url":"/dataset/vtc","name":"VTC","full_name":"Videos, Titles and Comments","num_papers_in_archive":2},{"url":"/dataset/airletters","name":"AirLetters","full_name":"","num_papers_in_archive":1},{"url":"/dataset/c3d-features-for-phd2gif","name":"C3D features for PHD2GIF","full_name":"","num_papers_in_archive":1},{"url":"/dataset/chronomagic-proh","name":"ChronoMagic-ProH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cinepile","name":"CinePile: A Long Video Question Answering Dataset and Benchmark","full_name":"","num_papers_in_archive":1},{"url":"/dataset/custom-spatio-temporal-action-video-dataset","name":"Custom Spatio-Temporal Action Video Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/i3-video","name":"i3-video","full_name":"is-it-instructional-video","num_papers_in_archive":1},{"url":"/dataset/kinetic-gebc","name":"Kinetics-GEB+","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lsdbench","name":"LSDBench","full_name":"Long-video Sampling Dilemma Benchmark","num_papers_in_archive":1},{"url":"/dataset/musechat-dataset","name":"MuseChat Dataset","full_name":"MuseChat: A Conversational Music Recommendation System for Videos (CVPR 2024 Highlight Paper)","num_papers_in_archive":1},{"url":"/dataset/placepedia","name":"Placepedia","full_name":"Placepedia","num_papers_in_archive":1},{"url":"/dataset/soccernet-echoes-1","name":"SoccerNet-Echoes","full_name":"SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset","num_papers_in_archive":1},{"url":"/dataset/trailers12k","name":"Trailers12k","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vcg-112k","name":"VCG+112K","full_name":"Video Instruction Dataset 112K","num_papers_in_archive":1},{"url":"/dataset/wildqa","name":"WildQA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/win-fail-action-understanding","name":"Win-Fail Action Understanding","full_name":"Win-Fail Action Understanding","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/anomaly-detection-in-surveillance-videos","name":"Anomaly Detection In Surveillance Videos"},{"url":"/task/causal-discovery-in-video-reasoning","name":"Causal Discovery in Video Reasoning"},{"url":"/task/long-video-activity-recognition","name":"Long-video Activity Recognition"},{"url":"/task/streaming-video-understanding","name":"Streaming video understanding"},{"url":"/task/temporal-sentence-grounding","name":"Temporal Sentence Grounding"},{"url":"/task/video-alignment","name":"Video Alignment"},{"url":"/task/video-quality-assessment","name":"Video Quality Assessment"}],"parent_tasks":[{"url":"/task/video","name":"Video"}],"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":12,"rows_per_page":100,"shown":100,"of":1149,"of_with_code":542,"tagged_in_all":1149,"counts":{"archive_papers_tagged":1149,"with_a_code_link":542,"where_syntology_ran_a_sample":218,"not_listed_spam_title":0,"listed":1149,"listed_where_code_ran":218,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":177,"every_run_a_failure_of_syntologys_instrument":41,"listed_with_a_run_with_no_instrument_failure":177,"listed_every_run_a_failure_of_syntologys_instrument":41,"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/is-space-time-attention-all-you-need-for","slug":"is-space-time-attention-all-you-need-for","title":"Is Space-Time Attention All You Need for Video Understanding?","date":"2021-02-09","arxiv_id":"2102.05095","repositories_listed":16,"syntology":{"n":43,"n_ran":35,"n_constructed":17,"n_ran_checked":21,"n_instrument":14,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":14,"phrase":"35 ran (of which 17 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 14 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/is-space-time-attention-all-you-need-for#ran","syntology_url":"https://syntology.ai/paper/2102.05095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05095"}},"official":{"repos":["facebookresearch/TimeSformer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/video-swin-transformer","slug":"video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","repositories_listed":15,"syntology":{"n":32,"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":13,"n_pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/video-swin-transformer#ran","syntology_url":"https://syntology.ai/paper/2106.13230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13230"}},"official":{"repos":["SwinTransformer/Video-Swin-Transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/temporal-shift-module-for-efficient-video","slug":"temporal-shift-module-for-efficient-video","title":"TSM: Temporal Shift Module for Efficient Video Understanding","date":"2018-11-20","arxiv_id":"1811.08383","repositories_listed":13,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/temporal-shift-module-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/1811.08383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.08383"}},"official":{"repos":["MIT-HAN-LAB/temporal-shift-module"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/tokenlearner-what-can-8-learned-tokens-do-for","slug":"tokenlearner-what-can-8-learned-tokens-do-for","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","date":"2021-06-21","arxiv_id":"2106.11297","repositories_listed":11,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 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) · 0 unverified","sample_list":"/paper/tokenlearner-what-can-8-learned-tokens-do-for#ran","syntology_url":"https://syntology.ai/paper/2106.11297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11297"}},"official":{"repos":["google-research/scenic"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/videomae-masked-autoencoders-are-data-1","slug":"videomae-masked-autoencoders-are-data-1","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","date":"2022-03-23","arxiv_id":"2203.12602","repositories_listed":9,"syntology":{"n":13,"n_ran":10,"n_constructed":6,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/videomae-masked-autoencoders-are-data-1#ran","syntology_url":"https://syntology.ai/paper/2203.12602","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12602"}},"official":{"repos":["MCG-NJU/VideoMAE","MCG-NJU/VideoMAE-Action-Detection"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/ava-a-video-dataset-of-spatio-temporally","slug":"ava-a-video-dataset-of-spatio-temporally","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","date":"2017-05-23","arxiv_id":"1705.08421","repositories_listed":9,"syntology":null},{"url":"/paper/soccernet-2022-challenges-results","slug":"soccernet-2022-challenges-results","title":"SoccerNet 2022 Challenges Results","date":"2022-10-05","arxiv_id":"2210.02365","repositories_listed":7,"syntology":null},{"url":"/paper/video-instance-segmentation","slug":"video-instance-segmentation","title":"Video Instance Segmentation","date":"2019-05-12","arxiv_id":"1905.04804","repositories_listed":6,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/video-instance-segmentation#ran","syntology_url":"https://syntology.ai/paper/1905.04804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04804"}},"official":{"repos":["Epiphqny/VisTR"],"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/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/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","repositories_listed":5,"syntology":{"n":24,"n_ran":18,"n_constructed":6,"n_ran_checked":11,"n_instrument":7,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":8,"phrase":"18 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}},"official":null}},{"url":"/paper/clip4clip-an-empirical-study-of-clip-for-end","slug":"clip4clip-an-empirical-study-of-clip-for-end","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","date":"2021-04-18","arxiv_id":"2104.08860","repositories_listed":5,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/clip4clip-an-empirical-study-of-clip-for-end#ran","syntology_url":"https://syntology.ai/paper/2104.08860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08860"}},"official":{"repos":["ArrowLuo/CLIP4Clip"],"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/representation-flow-for-action-recognition","slug":"representation-flow-for-action-recognition","title":"Representation Flow for Action Recognition","date":"2018-10-02","arxiv_id":"1810.01455","repositories_listed":5,"syntology":null},{"url":"/paper/learnable-pooling-with-context-gating-for","slug":"learnable-pooling-with-context-gating-for","title":"Learnable pooling with Context Gating for video classification","date":"2017-06-21","arxiv_id":"1706.06905","repositories_listed":5,"syntology":null},{"url":"/paper/chat-univi-unified-visual-representation","slug":"chat-univi-unified-visual-representation","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","date":"2023-11-14","arxiv_id":"2311.08046","repositories_listed":4,"syntology":null},{"url":"/paper/video-llama-an-instruction-tuned-audio-visual","slug":"video-llama-an-instruction-tuned-audio-visual","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","date":"2023-06-05","arxiv_id":"2306.02858","repositories_listed":4,"syntology":{"n":25,"n_ran":18,"n_constructed":7,"n_ran_checked":8,"n_instrument":10,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":9,"phrase":"18 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/video-llama-an-instruction-tuned-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2306.02858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02858"}},"official":{"repos":["damo-nlp-sg/video-llama"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deepsportradar-v1-computer-vision-dataset-for","slug":"deepsportradar-v1-computer-vision-dataset-for","title":"DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations","date":"2022-08-17","arxiv_id":"2208.08190","repositories_listed":4,"syntology":null},{"url":"/paper/cvnets-high-performance-library-for-computer","slug":"cvnets-high-performance-library-for-computer","title":"CVNets: High Performance Library for Computer Vision","date":"2022-06-04","arxiv_id":"2206.02002","repositories_listed":4,"syntology":null},{"url":"/paper/tsm-temporal-shift-module-for-efficient-and","slug":"tsm-temporal-shift-module-for-efficient-and","title":"TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Device","date":"2021-09-27","arxiv_id":"2109.13227","repositories_listed":4,"syntology":null},{"url":"/paper/soccernet-v2-a-dataset-and-benchmarks-for","slug":"soccernet-v2-a-dataset-and-benchmarks-for","title":"SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos","date":"2020-11-26","arxiv_id":"2011.13367","repositories_listed":4,"syntology":null},{"url":"/paper/temporal-interlacing-network","slug":"temporal-interlacing-network","title":"Temporal Interlacing Network","date":"2020-01-17","arxiv_id":"2001.06499","repositories_listed":4,"syntology":{"n":25,"n_ran":17,"n_constructed":9,"n_ran_checked":14,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":1,"phrase":"17 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/temporal-interlacing-network#ran","syntology_url":"https://syntology.ai/paper/2001.06499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06499"}},"official":{"repos":["deepcs233/TIN"],"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/long-term-feature-banks-for-detailed-video","slug":"long-term-feature-banks-for-detailed-video","title":"Long-Term Feature Banks for Detailed Video Understanding","date":"2018-12-12","arxiv_id":"1812.05038","repositories_listed":4,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/long-term-feature-banks-for-detailed-video#ran","syntology_url":"https://syntology.ai/paper/1812.05038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.05038"}},"official":{"repos":["facebookresearch/video-long-term-feature-banks"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/virtualhome-simulating-household-activities","slug":"virtualhome-simulating-household-activities","title":"VirtualHome: Simulating Household Activities via Programs","date":"2018-06-19","arxiv_id":"1806.07011","repositories_listed":4,"syntology":null},{"url":"/paper/ts-lstm-and-temporal-inception-exploiting","slug":"ts-lstm-and-temporal-inception-exploiting","title":"TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition","date":"2017-03-30","arxiv_id":"1703.10667","repositories_listed":4,"syntology":null},{"url":"/paper/cogvlm2-visual-language-models-for-image-and","slug":"cogvlm2-visual-language-models-for-image-and","title":"CogVLM2: Visual Language Models for Image and Video Understanding","date":"2024-08-29","arxiv_id":"2408.16500","repositories_listed":3,"syntology":{"n":17,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cogvlm2-visual-language-models-for-image-and#ran","syntology_url":"https://syntology.ai/paper/2408.16500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16500"}},"official":{"repos":["thudm/cogvlm2","thudm/glm-4"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mlvu-a-comprehensive-benchmark-for-multi-task","slug":"mlvu-a-comprehensive-benchmark-for-multi-task","title":"MLVU: Benchmarking Multi-task Long Video Understanding","date":"2024-06-06","arxiv_id":"2406.04264","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mlvu-a-comprehensive-benchmark-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2406.04264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04264"}},"official":{"repos":["junjie99/mlvu","FlagOpen/FlagEmbedding"],"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","unlocated"]}}},{"url":"/paper/no-time-to-waste-squeeze-time-into-channel","slug":"no-time-to-waste-squeeze-time-into-channel","title":"No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding","date":"2024-05-14","arxiv_id":"2405.08344","repositories_listed":3,"syntology":null},{"url":"/paper/mvbench-a-comprehensive-multi-modal-video","slug":"mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mvbench-a-comprehensive-multi-modal-video#ran","syntology_url":"https://syntology.ai/paper/2311.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17005"}},"official":{"repos":["opengvlab/ask-anything"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/panoptic-video-scene-graph-generation-1","slug":"panoptic-video-scene-graph-generation-1","title":"Panoptic Video Scene Graph Generation","date":"2023-11-28","arxiv_id":"2311.17058","repositories_listed":3,"syntology":{"n":11,"n_ran":11,"n_constructed":2,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/panoptic-video-scene-graph-generation-1#ran","syntology_url":"https://syntology.ai/paper/2311.17058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17058"}},"official":{"repos":["jingkang50/openpvsg","lilydaytoy/openpvsg","lilydaytoy/pvsgannotation"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/uniformerv2-spatiotemporal-learning-by-arming-1","slug":"uniformerv2-spatiotemporal-learning-by-arming-1","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","date":"2022-11-17","arxiv_id":"2211.09552","repositories_listed":3,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/uniformerv2-spatiotemporal-learning-by-arming-1#ran","syntology_url":"https://syntology.ai/paper/2211.09552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09552"}},"official":{"repos":["OpenGVLab/UniFormerV2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-action-segmentation-an-analysis-of","slug":"temporal-action-segmentation-an-analysis-of","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","date":"2022-10-19","arxiv_id":"2210.10352","repositories_listed":3,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/temporal-action-segmentation-an-analysis-of#ran","syntology_url":"https://syntology.ai/paper/2210.10352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10352"}},"official":{"repos":["atlas-eccv22/awesome-temporal-action-segmentation","nus-cvml/awesome-temporal-action-segmentation"],"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/progressive-attention-on-multi-level-dense","slug":"progressive-attention-on-multi-level-dense","title":"Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection","date":"2021-12-09","arxiv_id":"2112.04771","repositories_listed":3,"syntology":null},{"url":"/paper/token-shift-transformer-for-video","slug":"token-shift-transformer-for-video","title":"Token Shift Transformer for Video Classification","date":"2021-08-05","arxiv_id":"2108.02432","repositories_listed":3,"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/token-shift-transformer-for-video#ran","syntology_url":"https://syntology.ai/paper/2108.02432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.02432"}},"official":{"repos":["VideoNetworks/TokShift-Transformer"],"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/actor-context-actor-relation-network-for","slug":"actor-context-actor-relation-network-for","title":"Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization","date":"2020-06-14","arxiv_id":"2006.07976","repositories_listed":3,"syntology":{"n":27,"n_ran":17,"n_constructed":0,"n_ran_checked":16,"n_instrument":1,"n_unverified":10,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":4,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/actor-context-actor-relation-network-for#ran","syntology_url":"https://syntology.ai/paper/2006.07976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07976"}},"official":{"repos":["Siyu-C/ACAR-Net"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":9,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/long-term-temporal-context-for-per-camera","slug":"long-term-temporal-context-for-per-camera","title":"Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection","date":"2019-12-07","arxiv_id":"1912.03538","repositories_listed":3,"syntology":null},{"url":"/paper/a-multigrid-method-for-efficiently-training","slug":"a-multigrid-method-for-efficiently-training","title":"A Multigrid Method for Efficiently Training Video Models","date":"2019-12-02","arxiv_id":"1912.00998","repositories_listed":3,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-multigrid-method-for-efficiently-training#ran","syntology_url":"https://syntology.ai/paper/1912.00998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00998"}},"official":{"repos":["facebookresearch/SlowFast"],"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/actalign-zero-shot-fine-grained-video","slug":"actalign-zero-shot-fine-grained-video","title":"ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignment","date":"2025-06-28","arxiv_id":"2506.22967","repositories_listed":2,"syntology":null},{"url":"/paper/video-compression-commander-plug-and-play","slug":"video-compression-commander-plug-and-play","title":"Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models","date":"2025-05-20","arxiv_id":"2505.14454","repositories_listed":2,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/video-compression-commander-plug-and-play#ran","syntology_url":"https://syntology.ai/paper/2505.14454","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14454"}},"official":{"repos":["xuyang-liu16/vidcom2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/videoeval-pro-robust-and-realistic-long-video","slug":"videoeval-pro-robust-and-realistic-long-video","title":"VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation","date":"2025-05-20","arxiv_id":"2505.14640","repositories_listed":2,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videoeval-pro-robust-and-realistic-long-video#ran","syntology_url":"https://syntology.ai/paper/2505.14640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14640"}},"official":null}},{"url":"/paper/timechat-online-80-visual-tokens-are","slug":"timechat-online-80-visual-tokens-are","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","date":"2025-04-24","arxiv_id":"2504.17343","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/timechat-online-80-visual-tokens-are#ran","syntology_url":"https://syntology.ai/paper/2504.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.17343"}},"official":{"repos":["yaolinli/TimeChat-Online"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"url":"/paper/spatial-r1-enhancing-mllms-in-video-spatial","slug":"spatial-r1-enhancing-mllms-in-video-spatial","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","date":"2025-04-02","arxiv_id":"2504.01805","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatial-r1-enhancing-mllms-in-video-spatial#ran","syntology_url":"https://syntology.ai/paper/2504.01805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01805"}},"official":{"repos":["ouyangkun10/spacer","ouyangkun10/spatial-r1"],"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/llava-onevision-easy-visual-task-transfer","slug":"llava-onevision-easy-visual-task-transfer","title":"LLaVA-OneVision: Easy Visual Task Transfer","date":"2024-08-06","arxiv_id":"2408.03326","repositories_listed":2,"syntology":null},{"url":"/paper/segment-anything-for-videos-a-systematic","slug":"segment-anything-for-videos-a-systematic","title":"Segment Anything for Videos: A Systematic Survey","date":"2024-07-31","arxiv_id":"2408.08315","repositories_listed":2,"syntology":null},{"url":"/paper/omagent-a-multi-modal-agent-framework-for","slug":"omagent-a-multi-modal-agent-framework-for","title":"OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer","date":"2024-06-24","arxiv_id":"2406.16620","repositories_listed":2,"syntology":null},{"url":"/paper/pvuw-2024-challenge-on-complex-video","slug":"pvuw-2024-challenge-on-complex-video","title":"PVUW 2024 Challenge on Complex Video Understanding: Methods and Results","date":"2024-06-24","arxiv_id":"2406.17005","repositories_listed":2,"syntology":null},{"url":"/paper/leveraging-temporal-contextualization-for","slug":"leveraging-temporal-contextualization-for","title":"Leveraging Temporal Contextualization for Video Action Recognition","date":"2024-04-15","arxiv_id":"2404.09490","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leveraging-temporal-contextualization-for#ran","syntology_url":"https://syntology.ai/paper/2404.09490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.09490"}},"official":{"repos":["naver-ai/tc-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}},"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"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/internvideo2-scaling-video-foundation-models","slug":"internvideo2-scaling-video-foundation-models","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","date":"2024-03-22","arxiv_id":"2403.15377","repositories_listed":2,"syntology":null},{"url":"/paper/towards-neuro-symbolic-video-understanding","slug":"towards-neuro-symbolic-video-understanding","title":"Towards Neuro-Symbolic Video Understanding","date":"2024-03-16","arxiv_id":"2403.11021","repositories_listed":2,"syntology":null},{"url":"/paper/videoagent-long-form-video-understanding-with","slug":"videoagent-long-form-video-understanding-with","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","date":"2024-03-15","arxiv_id":"2403.10517","repositories_listed":2,"syntology":null},{"url":"/paper/videomamba-state-space-model-for-efficient","slug":"videomamba-state-space-model-for-efficient","title":"VideoMamba: State Space Model for Efficient Video Understanding","date":"2024-03-11","arxiv_id":"2403.06977","repositories_listed":2,"syntology":{"n":15,"n_ran":9,"n_constructed":5,"n_ran_checked":6,"n_instrument":3,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/videomamba-state-space-model-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2403.06977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06977"}},"official":{"repos":["opengvlab/videomamba"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","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/spatio-temporal-prompting-network-for-robust-1","slug":"spatio-temporal-prompting-network-for-robust-1","title":"Spatio-temporal Prompting Network for Robust Video Feature Extraction","date":"2024-02-04","arxiv_id":"2402.02574","repositories_listed":2,"syntology":null},{"url":"/paper/smile-multimodal-dataset-for-understanding","slug":"smile-multimodal-dataset-for-understanding","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","date":"2023-12-15","arxiv_id":"2312.09818","repositories_listed":2,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":9,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/smile-multimodal-dataset-for-understanding#ran","syntology_url":"https://syntology.ai/paper/2312.09818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09818"}},"official":{"repos":["postech-ami/smile-dataset","smile-data/smile"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"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/ego-exo4d-understanding-skilled-human","slug":"ego-exo4d-understanding-skilled-human","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","date":"2023-11-30","arxiv_id":"2311.18259","repositories_listed":2,"syntology":{"n":17,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"11 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; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/ego-exo4d-understanding-skilled-human#ran","syntology_url":"https://syntology.ai/paper/2311.18259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18259"}},"official":{"repos":["facebookresearch/Ego4d"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/side4video-spatial-temporal-side-network-for","slug":"side4video-spatial-temporal-side-network-for","title":"Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning","date":"2023-11-27","arxiv_id":"2311.15769","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/sas-video-qa-self-adaptive-sampling-for","slug":"sas-video-qa-self-adaptive-sampling-for","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","date":"2023-07-09","arxiv_id":"2307.04192","repositories_listed":2,"syntology":null},{"url":"/paper/icsvr-investigating-compositional-and","slug":"icsvr-investigating-compositional-and","title":"ICSVR: Investigating Compositional and Syntactic Understanding in Video Retrieval Models","date":"2023-06-28","arxiv_id":"2306.16533","repositories_listed":2,"syntology":null},{"url":"/paper/fha-kitchens-a-novel-dataset-for-fine-grained","slug":"fha-kitchens-a-novel-dataset-for-fine-grained","title":"Multi-Granularity Hand Action Detection","date":"2023-06-19","arxiv_id":"2306.10858","repositories_listed":2,"syntology":null},{"url":"/paper/video-chatgpt-towards-detailed-video","slug":"video-chatgpt-towards-detailed-video","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","date":"2023-06-08","arxiv_id":"2306.05424","repositories_listed":2,"syntology":null},{"url":"/paper/dsec-mos-segment-any-moving-object-with","slug":"dsec-mos-segment-any-moving-object-with","title":"Event-Free Moving Object Segmentation from Moving Ego Vehicle","date":"2023-04-28","arxiv_id":"2305.00126","repositories_listed":2,"syntology":null},{"url":"/paper/transition-is-a-process-pair-to-video-change","slug":"transition-is-a-process-pair-to-video-change","title":"Transition Is a Process: Pair-to-Video Change Detection Networks for Very High Resolution Remote Sensing Images","date":"2022-12-07","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/internvideo-general-video-foundation-models","slug":"internvideo-general-video-foundation-models","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","date":"2022-12-06","arxiv_id":"2212.03191","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":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) · 0 unverified","sample_list":"/paper/internvideo-general-video-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2212.03191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03191"}},"official":{"repos":["opengvlab/internvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-video-representation-learning-via","slug":"efficient-video-representation-learning-via","title":"EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens","date":"2022-11-19","arxiv_id":"2211.10636","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"3 ran (of which 3 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) · 3 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-video-representation-learning-via#ran","syntology_url":"https://syntology.ai/paper/2211.10636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10636"}},"official":{"repos":["sunilhoho/everest","sunilhoho/VideoMS"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/internvideo-ego4d-a-pack-of-champion","slug":"internvideo-ego4d-a-pack-of-champion","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","date":"2022-11-17","arxiv_id":"2211.09529","repositories_listed":2,"syntology":null},{"url":"/paper/uniformerv2-spatiotemporal-learning-by-arming","slug":"uniformerv2-spatiotemporal-learning-by-arming","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","date":"2022-09-22","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/spotting-temporally-precise-fine-grained","slug":"spotting-temporally-precise-fine-grained","title":"Spotting Temporally Precise, Fine-Grained Events in Video","date":"2022-07-20","arxiv_id":"2207.10213","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 ran (of which 1 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","sample_list":"/paper/spotting-temporally-precise-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2207.10213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10213"}},"official":{"repos":["soccernet/sn-spotting","jhong93/spot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/federated-self-supervised-learning-for-video","slug":"federated-self-supervised-learning-for-video","title":"Federated Self-supervised Learning for Video Understanding","date":"2022-07-05","arxiv_id":"2207.01975","repositories_listed":2,"syntology":null},{"url":"/paper/basictad-an-astounding-rgb-only-baseline-for","slug":"basictad-an-astounding-rgb-only-baseline-for","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","date":"2022-05-05","arxiv_id":"2205.02717","repositories_listed":2,"syntology":null},{"url":"/paper/fitclip-refining-large-scale-pretrained-image","slug":"fitclip-refining-large-scale-pretrained-image","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","date":"2022-03-24","arxiv_id":"2203.13371","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/fitclip-refining-large-scale-pretrained-image#ran","syntology_url":"https://syntology.ai/paper/2203.13371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13371"}},"official":{"repos":["bryant1410/fitclip","bryant1410/tclip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-dataset-for-medical-instructional-video","slug":"a-dataset-for-medical-instructional-video","title":"A Dataset for Medical Instructional Video Classification and Question Answering","date":"2022-01-30","arxiv_id":"2201.12888","repositories_listed":2,"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/a-dataset-for-medical-instructional-video#ran","syntology_url":"https://syntology.ai/paper/2201.12888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12888"}},"official":{"repos":["deepaknlp/medvidqacl"],"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/video-joint-modelling-based-on-hierarchical","slug":"video-joint-modelling-based-on-hierarchical","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","date":"2021-12-27","arxiv_id":"2112.13478","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-referring-video-object","slug":"end-to-end-referring-video-object","title":"End-to-End Referring Video Object Segmentation with Multimodal Transformers","date":"2021-11-29","arxiv_id":"2111.14821","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"9 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/end-to-end-referring-video-object#ran","syntology_url":"https://syntology.ai/paper/2111.14821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14821"}},"official":{"repos":["mttr2021/MTTR"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tada-temporally-adaptive-convolutions-for-1","slug":"tada-temporally-adaptive-convolutions-for-1","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","date":"2021-10-12","arxiv_id":"2110.06178","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/tada-temporally-adaptive-convolutions-for-1#ran","syntology_url":"https://syntology.ai/paper/2110.06178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06178"}},"official":{"repos":["alibaba-mmai-research/pytorch-video-understanding"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/learning-temporally-causal-latent-processes","slug":"learning-temporally-causal-latent-processes","title":"Learning Temporally Causal Latent Processes from General Temporal Data","date":"2021-10-11","arxiv_id":"2110.05428","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-temporally-causal-latent-processes#ran","syntology_url":"https://syntology.ai/paper/2110.05428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.05428"}},"official":{"repos":["weirayao/leap"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","listed"]}}},{"url":"/paper/learning-temporally-latent-causal-processes","slug":"learning-temporally-latent-causal-processes","title":"Learning Temporally Latent Causal Processes from General Temporal Data","date":"2021-09-29","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/spatial-temporal-transformer-for-dynamic","slug":"spatial-temporal-transformer-for-dynamic","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","date":"2021-07-26","arxiv_id":"2107.12309","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":4,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":6,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/spatial-temporal-transformer-for-dynamic#ran","syntology_url":"https://syntology.ai/paper/2107.12309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12309"}},"official":{"repos":["yrcong/sttran"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/disentangle-your-dense-object-detector","slug":"disentangle-your-dense-object-detector","title":"Disentangle Your Dense Object Detector","date":"2021-07-07","arxiv_id":"2107.02963","repositories_listed":2,"syntology":null},{"url":"/paper/feature-combination-meets-attention-baidu","slug":"feature-combination-meets-attention-baidu","title":"Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection","date":"2021-06-28","arxiv_id":"2106.14447","repositories_listed":2,"syntology":null},{"url":"/paper/towards-long-form-video-understanding-1","slug":"towards-long-form-video-understanding-1","title":"Towards Long-Form Video Understanding","date":"2021-06-21","arxiv_id":"2106.11310","repositories_listed":2,"syntology":{"n":19,"n_ran":18,"n_constructed":0,"n_ran_checked":15,"n_instrument":3,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":13,"n_pointer_only":2,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-long-form-video-understanding-1#ran","syntology_url":"https://syntology.ai/paper/2106.11310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.11310"}},"official":{"repos":["chaoyuaw/lvu"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/next-qa-next-phase-of-question-answering-to","slug":"next-qa-next-phase-of-question-answering-to","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","date":"2021-05-18","arxiv_id":"2105.08276","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 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) · 0 unverified","sample_list":"/paper/next-qa-next-phase-of-question-answering-to#ran","syntology_url":"https://syntology.ai/paper/2105.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08276"}},"official":{"repos":["doc-doc/NExT-QA"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/relaxed-transformer-decoders-for-direct","slug":"relaxed-transformer-decoders-for-direct","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","date":"2021-02-03","arxiv_id":"2102.01894","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/relaxed-transformer-decoders-for-direct#ran","syntology_url":"https://syntology.ai/paper/2102.01894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.01894"}},"official":{"repos":["MCG-NJU/RTD-Action"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/occluded-video-instance-segmentation","slug":"occluded-video-instance-segmentation","title":"Occluded Video Instance Segmentation: A Benchmark","date":"2021-02-02","arxiv_id":"2102.01558","repositories_listed":2,"syntology":null},{"url":"/paper/trackformer-multi-object-tracking-with","slug":"trackformer-multi-object-tracking-with","title":"TrackFormer: Multi-Object Tracking with Transformers","date":"2021-01-07","arxiv_id":"2101.02702","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-video-instance-segmentation-with","slug":"end-to-end-video-instance-segmentation-with","title":"End-to-End Video Instance Segmentation with Transformers","date":"2020-11-30","arxiv_id":"2011.14503","repositories_listed":2,"syntology":null},{"url":"/paper/queryd-a-video-dataset-with-high-quality","slug":"queryd-a-video-dataset-with-high-quality","title":"QuerYD: A video dataset with high-quality text and audio narrations","date":"2020-11-22","arxiv_id":"2011.11071","repositories_listed":2,"syntology":null},{"url":"/paper/features-understanding-in-3d-cnns-for-actions","slug":"features-understanding-in-3d-cnns-for-actions","title":"Features Understanding in 3D CNNs for Actions Recognition in Video","date":"2020-10-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/pan-towards-fast-action-recognition-via","slug":"pan-towards-fast-action-recognition-via","title":"PAN: Towards Fast Action Recognition via Learning Persistence of Appearance","date":"2020-08-08","arxiv_id":"2008.03462","repositories_listed":2,"syntology":null},{"url":"/paper/uncertainty-based-traffic-accident","slug":"uncertainty-based-traffic-accident","title":"Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning","date":"2020-08-01","arxiv_id":"2008.00334","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uncertainty-based-traffic-accident#ran","syntology_url":"https://syntology.ai/paper/2008.00334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.00334"}},"official":{"repos":["Cogito2012/CarCrashDataset","Cogito2012/UString"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/motionsqueeze-neural-motion-feature-learning","slug":"motionsqueeze-neural-motion-feature-learning","title":"MotionSqueeze: Neural Motion Feature Learning for Video Understanding","date":"2020-07-20","arxiv_id":"2007.09933","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/motionsqueeze-neural-motion-feature-learning#ran","syntology_url":"https://syntology.ai/paper/2007.09933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09933"}},"official":null}},{"url":"/paper/temporal-aggregate-representations-for-long","slug":"temporal-aggregate-representations-for-long","title":"Temporal Aggregate Representations for Long-Range Video Understanding","date":"2020-06-01","arxiv_id":"2006.00830","repositories_listed":2,"syntology":null},{"url":"/paper/a-comprehensive-study-on-visual-explanations","slug":"a-comprehensive-study-on-visual-explanations","title":"Towards Visually Explaining Video Understanding Networks with Perturbation","date":"2020-05-01","arxiv_id":"2005.00375","repositories_listed":2,"syntology":null},{"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/multi-moments-in-time-learning-and","slug":"multi-moments-in-time-learning-and","title":"Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding","date":"2019-11-01","arxiv_id":"1911.00232","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-moments-in-time-learning-and#ran","syntology_url":"https://syntology.ai/paper/1911.00232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00232"}},"official":null}},{"url":"/paper/tiny-video-networks","slug":"tiny-video-networks","title":"Tiny Video Networks","date":"2019-10-15","arxiv_id":"1910.06961","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/tiny-video-networks#ran","syntology_url":"https://syntology.ai/paper/1910.06961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06961"}},"official":{"repos":["google-research/google-research"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/cater-a-diagnostic-dataset-for-compositional","slug":"cater-a-diagnostic-dataset-for-compositional","title":"CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning","date":"2019-10-10","arxiv_id":"1910.04744","repositories_listed":2,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cater-a-diagnostic-dataset-for-compositional#ran","syntology_url":"https://syntology.ai/paper/1910.04744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04744"}},"official":null}},{"url":"/paper/assemblenet-searching-for-multi-stream-neural","slug":"assemblenet-searching-for-multi-stream-neural","title":"AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures","date":"2019-05-30","arxiv_id":"1905.13209","repositories_listed":2,"syntology":null},{"url":"/paper/constrained-size-tensorflow-models-for","slug":"constrained-size-tensorflow-models-for","title":"Constrained-size Tensorflow Models for YouTube-8M Video Understanding Challenge","date":"2018-08-21","arxiv_id":"1808.06739","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}],"syntology_records":50,"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":218,"papers_where_code_ran_first_page":"/task/video-understanding/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":12,"url":"/task/video-understanding/papers/2","json":"/task/video-understanding/papers/2.json","rows":100},{"order":"archive","page":3,"of":12,"url":"/task/video-understanding/papers/3","json":"/task/video-understanding/papers/3.json","rows":100},{"order":"archive","page":4,"of":12,"url":"/task/video-understanding/papers/4","json":"/task/video-understanding/papers/4.json","rows":100},{"order":"archive","page":5,"of":12,"url":"/task/video-understanding/papers/5","json":"/task/video-understanding/papers/5.json","rows":100},{"order":"archive","page":6,"of":12,"url":"/task/video-understanding/papers/6","json":"/task/video-understanding/papers/6.json","rows":100},{"order":"archive","page":7,"of":12,"url":"/task/video-understanding/papers/7","json":"/task/video-understanding/papers/7.json","rows":100},{"order":"archive","page":8,"of":12,"url":"/task/video-understanding/papers/8","json":"/task/video-understanding/papers/8.json","rows":100},{"order":"archive","page":9,"of":12,"url":"/task/video-understanding/papers/9","json":"/task/video-understanding/papers/9.json","rows":100},{"order":"archive","page":10,"of":12,"url":"/task/video-understanding/papers/10","json":"/task/video-understanding/papers/10.json","rows":100},{"order":"archive","page":11,"of":12,"url":"/task/video-understanding/papers/11","json":"/task/video-understanding/papers/11.json","rows":100},{"order":"archive","page":12,"of":12,"url":"/task/video-understanding/papers/12","json":"/task/video-understanding/papers/12.json","rows":49},{"order":"ran","page":1,"of":3,"url":"/task/video-understanding/papers/ran/1","json":"/task/video-understanding/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":3,"url":"/task/video-understanding/papers/ran/2","json":"/task/video-understanding/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":3,"url":"/task/video-understanding/papers/ran/3","json":"/task/video-understanding/papers/ran/3.json","rows":18}],"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":"80a33308a9c3c9962e18974f03be720d094dfa343b09d1f825b8719086d08dca","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}