{"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-recognition","name":"Video Recognition","slug":"video-recognition","description_markdown":"**Video Recognition** is a process of obtaining, processing, and analysing data that it receives from a visual source, specifically 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":307,"papers_with_code":168,"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":10,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/bosphorussign22k","name":"BosphorusSign22k","full_name":"","num_papers_in_archive":8},{"url":"/dataset/midv-2019","name":"MIDV-2019","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mod","name":"MOD++","full_name":"","num_papers_in_archive":3},{"url":"/dataset/3dyoga90","name":"3DYoga90","full_name":"3DYoga90: A Hierarchical Video Dataset for Yoga Pose Understanding","num_papers_in_archive":2},{"url":"/dataset/imbalanced-minikinetics200","name":"Imbalanced-MiniKinetics200","full_name":"Imbalanced-MiniKinetics200","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/crowd11","name":"Crowd 11","full_name":"A Dataset for Fine Grained Crowd Behaviour Analysis","num_papers_in_archive":0},{"url":"/dataset/l-svd","name":"L-SVD","full_name":"Large-Scale Selfie Video Dataset (L-SVD): A Benchmark for Emotion Recognition","num_papers_in_archive":0},{"url":"/dataset/raise-lpbf","name":"RAISE-LPBF","full_name":"","num_papers_in_archive":0}],"subtasks":[],"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":4,"rows_per_page":100,"shown":100,"of":307,"of_with_code":168,"tagged_in_all":307,"counts":{"archive_papers_tagged":307,"with_a_code_link":168,"where_syntology_ran_a_sample":64,"not_listed_spam_title":0,"listed":307,"listed_where_code_ran":64,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":56,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":56,"listed_every_run_a_failure_of_syntologys_instrument":8,"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/drop-an-octave-reducing-spatial-redundancy-in","slug":"drop-an-octave-reducing-spatial-redundancy-in","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","date":"2019-04-10","arxiv_id":"1904.05049","repositories_listed":28,"syntology":{"n":34,"n_ran":24,"n_constructed":0,"n_ran_checked":11,"n_instrument":13,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":9,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 13 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/drop-an-octave-reducing-spatial-redundancy-in#ran","syntology_url":"https://syntology.ai/paper/1904.05049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05049"}},"official":{"repos":["facebookresearch/OctConv"],"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/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/slowfast-networks-for-video-recognition","slug":"slowfast-networks-for-video-recognition","title":"SlowFast Networks for Video Recognition","date":"2018-12-10","arxiv_id":"1812.03982","repositories_listed":15,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/slowfast-networks-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1812.03982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03982"}},"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/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/would-mega-scale-datasets-further-enhance","slug":"would-mega-scale-datasets-further-enhance","title":"Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?","date":"2020-04-10","arxiv_id":"2004.04968","repositories_listed":10,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/would-mega-scale-datasets-further-enhance#ran","syntology_url":"https://syntology.ai/paper/2004.04968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04968"}},"official":{"repos":["kenshohara/3D-ResNets-PyTorch"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/improved-multiscale-vision-transformers-for","slug":"improved-multiscale-vision-transformers-for","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","date":"2021-12-02","arxiv_id":"2112.01526","repositories_listed":9,"syntology":null},{"url":"/paper/multiscale-vision-transformers","slug":"multiscale-vision-transformers","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","repositories_listed":8,"syntology":{"n":26,"n_ran":13,"n_constructed":10,"n_ran_checked":11,"n_instrument":2,"n_unverified":13,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":5,"phrase":"13 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/multiscale-vision-transformers#ran","syntology_url":"https://syntology.ai/paper/2104.11227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.11227"}},"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/x3d-expanding-architectures-for-efficient","slug":"x3d-expanding-architectures-for-efficient","title":"X3D: Expanding Architectures for Efficient Video Recognition","date":"2020-04-09","arxiv_id":"2004.04730","repositories_listed":8,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/x3d-expanding-architectures-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2004.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04730"}},"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/weight-standardization","slug":"weight-standardization","title":"Micro-Batch Training with Batch-Channel Normalization and Weight Standardization","date":"2019-03-25","arxiv_id":"1903.10520","repositories_listed":7,"syntology":null},{"url":"/paper/long-term-recurrent-convolutional-networks","slug":"long-term-recurrent-convolutional-networks","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","date":"2014-11-17","arxiv_id":"1411.4389","repositories_listed":7,"syntology":null},{"url":"/paper/bidirectional-cross-modal-knowledge","slug":"bidirectional-cross-modal-knowledge","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","date":"2022-12-31","arxiv_id":"2301.00182","repositories_listed":5,"syntology":null},{"url":"/paper/transferring-textual-knowledge-for-visual","slug":"transferring-textual-knowledge-for-visual","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","date":"2022-07-04","arxiv_id":"2207.01297","repositories_listed":5,"syntology":null},{"url":"/paper/revisiting-3d-resnets-for-video-recognition","slug":"revisiting-3d-resnets-for-video-recognition","title":"Revisiting 3D ResNets for Video Recognition","date":"2021-09-03","arxiv_id":"2109.01696","repositories_listed":5,"syntology":null},{"url":"/paper/hiera-a-hierarchical-vision-transformer","slug":"hiera-a-hierarchical-vision-transformer","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","date":"2023-06-01","arxiv_id":"2306.00989","repositories_listed":4,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hiera-a-hierarchical-vision-transformer#ran","syntology_url":"https://syntology.ai/paper/2306.00989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00989"}},"official":{"repos":["facebookresearch/hiera"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/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/video-focalnets-spatio-temporal-focal","slug":"video-focalnets-spatio-temporal-focal","title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition","date":"2023-07-13","arxiv_id":"2307.06947","repositories_listed":3,"syntology":{"n":32,"n_ran":23,"n_constructed":7,"n_ran_checked":16,"n_instrument":7,"n_unverified":9,"n_honours":1,"n_violates":1,"n_no_contract":14,"n_pointer_only":21,"phrase":"23 ran (of which 7 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/video-focalnets-spatio-temporal-focal#ran","syntology_url":"https://syntology.ai/paper/2307.06947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.06947"}},"official":{"repos":["talalwasim/video-focalnets"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":3,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/movinets-mobile-video-networks-for-efficient","slug":"movinets-mobile-video-networks-for-efficient","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","date":"2021-03-21","arxiv_id":"2103.11511","repositories_listed":3,"syntology":{"n":13,"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/movinets-mobile-video-networks-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2103.11511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.11511"}},"official":{"repos":["tensorflow/models"],"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/mvfnet-multi-view-fusion-network-for","slug":"mvfnet-multi-view-fusion-network-for","title":"MVFNet: Multi-View Fusion Network for Efficient Video Recognition","date":"2020-12-13","arxiv_id":"2012.06977","repositories_listed":3,"syntology":null},{"url":"/paper/pyramidal-convolution-rethinking","slug":"pyramidal-convolution-rethinking","title":"Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition","date":"2020-06-20","arxiv_id":"2006.11538","repositories_listed":3,"syntology":null},{"url":"/paper/omni-sourced-webly-supervised-learning-for","slug":"omni-sourced-webly-supervised-learning-for","title":"Omni-sourced Webly-supervised Learning for Video Recognition","date":"2020-03-29","arxiv_id":"2003.13042","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/omni-sourced-webly-supervised-learning-for#ran","syntology_url":"https://syntology.ai/paper/2003.13042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.13042"}},"official":{"repos":["open-mmlab/mmaction"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/audiovisual-slowfast-networks-for-video","slug":"audiovisual-slowfast-networks-for-video","title":"Audiovisual SlowFast Networks for Video Recognition","date":"2020-01-23","arxiv_id":"2001.08740","repositories_listed":3,"syntology":null},{"url":"/paper/deep-feature-flow-for-video-recognition","slug":"deep-feature-flow-for-video-recognition","title":"Deep Feature Flow for Video Recognition","date":"2016-11-23","arxiv_id":"1611.07715","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-feature-flow-for-video-recognition#ran","syntology_url":"https://syntology.ai/paper/1611.07715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.07715"}},"official":{"repos":["msracver/Deep-Feature-Flow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/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/zeroi2v-zero-cost-adaptation-of-pre-trained","slug":"zeroi2v-zero-cost-adaptation-of-pre-trained","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","date":"2023-10-02","arxiv_id":"2310.01324","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/zeroi2v-zero-cost-adaptation-of-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2310.01324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01324"}},"official":{"repos":["mcg-nju/zeroi2v","leexinhao/ZeroI2V"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/what-can-simple-arithmetic-operations-do-for","slug":"what-can-simple-arithmetic-operations-do-for","title":"What Can Simple Arithmetic Operations Do for Temporal Modeling?","date":"2023-07-18","arxiv_id":"2307.08908","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/what-can-simple-arithmetic-operations-do-for#ran","syntology_url":"https://syntology.ai/paper/2307.08908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.08908"}},"official":{"repos":["whwu95/ATM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/frame-flexible-network","slug":"frame-flexible-network","title":"Frame Flexible Network","date":"2023-03-26","arxiv_id":"2303.14817","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/frame-flexible-network#ran","syntology_url":"https://syntology.ai/paper/2303.14817","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14817"}},"official":{"repos":["bespontaneous/ffn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/frozen-clip-models-are-efficient-video","slug":"frozen-clip-models-are-efficient-video","title":"Frozen CLIP Models are Efficient Video Learners","date":"2022-08-06","arxiv_id":"2208.03550","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":3,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"5 ran (of which 3 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) · 5 unverified","sample_list":"/paper/frozen-clip-models-are-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2208.03550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03550"}},"official":{"repos":["opengvlab/efficient-video-recognition"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/expanding-language-image-pretrained-models","slug":"expanding-language-image-pretrained-models","title":"Expanding Language-Image Pretrained Models for General Video Recognition","date":"2022-08-04","arxiv_id":"2208.02816","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/expanding-language-image-pretrained-models#ran","syntology_url":"https://syntology.ai/paper/2208.02816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02816"}},"official":{"repos":["microsoft/videox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptformer-adapting-vision-transformers-for","slug":"adaptformer-adapting-vision-transformers-for","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","date":"2022-05-26","arxiv_id":"2205.13535","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":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/adaptformer-adapting-vision-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2205.13535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.13535"}},"official":{"repos":["ShoufaChen/AdaptFormer"],"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/gate-shift-fuse-for-video-action-recognition","slug":"gate-shift-fuse-for-video-action-recognition","title":"Gate-Shift-Fuse for Video Action Recognition","date":"2022-03-16","arxiv_id":"2203.08897","repositories_listed":2,"syntology":null},{"url":"/paper/adafocus-v2-end-to-end-training-of-spatial","slug":"adafocus-v2-end-to-end-training-of-spatial","title":"AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition","date":"2021-12-28","arxiv_id":"2112.14238","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/adaptive-focus-for-efficient-video","slug":"adaptive-focus-for-efficient-video","title":"Adaptive Focus for Efficient Video Recognition","date":"2021-05-07","arxiv_id":"2105.03245","repositories_listed":2,"syntology":{"n":23,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":23,"phrase":"13 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; 6 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/adaptive-focus-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2105.03245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03245"}},"official":{"repos":["blackfeather-wang/AdaFocus"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-equivariant-representations","slug":"learning-equivariant-representations","title":"Learning Equivariant Representations","date":"2020-12-04","arxiv_id":"2012.02771","repositories_listed":2,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-3","slug":"self-supervised-video-representation-learning-3","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","date":"2020-08-06","arxiv_id":"2008.02531","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-supervised-video-representation-learning-3#ran","syntology_url":"https://syntology.ai/paper/2008.02531","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.02531"}},"official":{"repos":["BestJuly/Inter-intra-video-contrastive-learning"],"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/tam-temporal-adaptive-module-for-video","slug":"tam-temporal-adaptive-module-for-video","title":"TAM: Temporal Adaptive Module for Video Recognition","date":"2020-05-14","arxiv_id":"2005.06803","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"5 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; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/tam-temporal-adaptive-module-for-video#ran","syntology_url":"https://syntology.ai/paper/2005.06803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.06803"}},"official":{"repos":["liu-zhy/TANet","liu-zhy/temporal-adaptive-module"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/improved-residual-networks-for-image-and","slug":"improved-residual-networks-for-image-and","title":"Improved Residual Networks for Image and Video Recognition","date":"2020-04-10","arxiv_id":"2004.04989","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improved-residual-networks-for-image-and#ran","syntology_url":"https://syntology.ai/paper/2004.04989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04989"}},"official":{"repos":["iduta/iresnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sequence-level-semantics-aggregation-for","slug":"sequence-level-semantics-aggregation-for","title":"Sequence Level Semantics Aggregation for Video Object Detection","date":"2019-07-15","arxiv_id":"1907.06390","repositories_listed":2,"syntology":null},{"url":"/paper/a2-nets-double-attention-networks-1","slug":"a2-nets-double-attention-networks-1","title":"A^2-Nets: Double Attention Networks","date":"2018-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/flow-guided-feature-aggregation-for-video","slug":"flow-guided-feature-aggregation-for-video","title":"Flow-Guided Feature Aggregation for Video Object Detection","date":"2017-03-29","arxiv_id":"1703.10025","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flow-guided-feature-aggregation-for-video#ran","syntology_url":"https://syntology.ai/paper/1703.10025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.10025"}},"official":{"repos":["msracver/Flow-Guided-Feature-Aggregation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dvfl-net-a-lightweight-distilled-video-focal","slug":"dvfl-net-a-lightweight-distilled-video-focal","title":"DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition","date":"2025-07-16","arxiv_id":"2507.12426","repositories_listed":1,"syntology":null},{"url":"/paper/vcrbench-exploring-long-form-causal-reasoning","slug":"vcrbench-exploring-long-form-causal-reasoning","title":"VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models","date":"2025-05-13","arxiv_id":"2505.08455","repositories_listed":1,"syntology":null},{"url":"/paper/basket-a-large-scale-video-dataset-for-fine","slug":"basket-a-large-scale-video-dataset-for-fine","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","date":"2025-03-26","arxiv_id":"2503.20781","repositories_listed":1,"syntology":null},{"url":"/paper/pave-patching-and-adapting-video-large","slug":"pave-patching-and-adapting-video-large","title":"PAVE: Patching and Adapting Video Large Language Models","date":"2025-03-25","arxiv_id":"2503.19794","repositories_listed":1,"syntology":null},{"url":"/paper/videopure-diffusion-based-adversarial","slug":"videopure-diffusion-based-adversarial","title":"VideoPure: Diffusion-based Adversarial Purification for Video Recognition","date":"2025-01-25","arxiv_id":"2501.14999","repositories_listed":1,"syntology":null},{"url":"/paper/uni-adafocus-spatial-temporal-dynamic","slug":"uni-adafocus-spatial-temporal-dynamic","title":"Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition","date":"2024-12-15","arxiv_id":"2412.11228","repositories_listed":1,"syntology":null},{"url":"/paper/mote-reconciling-generalization-with","slug":"mote-reconciling-generalization-with","title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","date":"2024-10-14","arxiv_id":"2410.10589","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":1,"n_ran_checked":3,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"8 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; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/mote-reconciling-generalization-with#ran","syntology_url":"https://syntology.ai/paper/2410.10589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10589"}},"official":{"repos":["zmhh-h/mote"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-up-your-kernels-large-kernel-design","slug":"scaling-up-your-kernels-large-kernel-design","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","date":"2024-10-10","arxiv_id":"2410.08049","repositories_listed":1,"syntology":null},{"url":"/paper/genrec-unifying-video-generation-and","slug":"genrec-unifying-video-generation-and","title":"GenRec: Unifying Video Generation and Recognition with Diffusion Models","date":"2024-08-27","arxiv_id":"2408.15241","repositories_listed":1,"syntology":null},{"url":"/paper/omniclip-adapting-clip-for-video-recognition","slug":"omniclip-adapting-clip-for-video-recognition","title":"OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning","date":"2024-08-12","arxiv_id":"2408.06158","repositories_listed":1,"syntology":null},{"url":"/paper/videomamba-spatio-temporal-selective-state","slug":"videomamba-spatio-temporal-selective-state","title":"VideoMamba: Spatio-Temporal Selective State Space Model","date":"2024-07-11","arxiv_id":"2407.08476","repositories_listed":1,"syntology":null},{"url":"/paper/posmlp-video-spatial-and-temporal-relative","slug":"posmlp-video-spatial-and-temporal-relative","title":"PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition","date":"2024-07-03","arxiv_id":"2407.02934","repositories_listed":1,"syntology":null},{"url":"/paper/demamba-ai-generated-video-detection-on","slug":"demamba-ai-generated-video-detection-on","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","date":"2024-05-30","arxiv_id":"2405.19707","repositories_listed":1,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":6,"n_instrument":7,"n_unverified":6,"n_honours":3,"n_violates":1,"n_no_contract":2,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/demamba-ai-generated-video-detection-on#ran","syntology_url":"https://syntology.ai/paper/2405.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19707"}},"official":{"repos":["chenhaoxing/DeMamba"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/vg4d-vision-language-model-goes-4d-video","slug":"vg4d-vision-language-model-goes-4d-video","title":"VG4D: Vision-Language Model Goes 4D Video Recognition","date":"2024-04-17","arxiv_id":"2404.11605","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-tuning-towards-parameter-and","slug":"dynamic-tuning-towards-parameter-and","title":"Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation","date":"2024-03-18","arxiv_id":"2403.11808","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dynamic-tuning-towards-parameter-and#ran","syntology_url":"https://syntology.ai/paper/2403.11808","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11808"}},"official":{"repos":["nus-hpc-ai-lab/dynamic-tuning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/don-t-judge-by-the-look-a-motion-coherent","slug":"don-t-judge-by-the-look-a-motion-coherent","title":"Don't Judge by the Look: Towards Motion Coherent Video Representation","date":"2024-03-14","arxiv_id":"2403.09506","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-augmentation-and-distillation","slug":"hierarchical-augmentation-and-distillation","title":"Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognition","date":"2024-01-11","arxiv_id":"2401.06287","repositories_listed":1,"syntology":null},{"url":"/paper/haltingvt-adaptive-token-halting-transformer","slug":"haltingvt-adaptive-token-halting-transformer","title":"HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition","date":"2024-01-10","arxiv_id":"2401.04975","repositories_listed":1,"syntology":null},{"url":"/paper/video-recognition-in-portrait-mode","slug":"video-recognition-in-portrait-mode","title":"Video Recognition in Portrait Mode","date":"2023-12-21","arxiv_id":"2312.13746","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-the-power-of-cnn-and-transformer","slug":"unleashing-the-power-of-cnn-and-transformer","title":"Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition","date":"2023-12-18","arxiv_id":"2312.11128","repositories_listed":1,"syntology":null},{"url":"/paper/logostylefool-vitiating-video-recognition","slug":"logostylefool-vitiating-video-recognition","title":"LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer","date":"2023-12-15","arxiv_id":"2312.09935","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-short-term-transformers-for-action","slug":"adapting-short-term-transformers-for-action","title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","date":"2023-12-04","arxiv_id":"2312.01897","repositories_listed":1,"syntology":null},{"url":"/paper/devias-learning-disentangled-video","slug":"devias-learning-disentangled-video","title":"DEVIAS: Learning Disentangled Video Representations of Action and Scene","date":"2023-11-30","arxiv_id":"2312.00826","repositories_listed":1,"syntology":null},{"url":"/paper/ost-refining-text-knowledge-with-optimal","slug":"ost-refining-text-knowledge-with-optimal","title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","date":"2023-11-30","arxiv_id":"2312.00096","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/ost-refining-text-knowledge-with-optimal#ran","syntology_url":"https://syntology.ai/paper/2312.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00096"}},"official":{"repos":["tomchen-ctj/OST"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automated-sperm-assessment-framework-and","slug":"automated-sperm-assessment-framework-and","title":"Automated Sperm Assessment Framework and Neural Network Specialized for Sperm Video Recognition","date":"2023-11-10","arxiv_id":"2311.05927","repositories_listed":1,"syntology":null},{"url":"/paper/object-centric-video-representation-for-long","slug":"object-centric-video-representation-for-long","title":"Object-centric Video Representation for Long-term Action Anticipation","date":"2023-10-31","arxiv_id":"2311.00180","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/object-centric-video-representation-for-long#ran","syntology_url":"https://syntology.ai/paper/2311.00180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00180"}},"official":{"repos":["brown-palm/ObjectPrompt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-relevance-of-temporal-features-for","slug":"on-the-relevance-of-temporal-features-for","title":"On the Relevance of Temporal Features for Medical Ultrasound Video Recognition","date":"2023-10-16","arxiv_id":"2310.10453","repositories_listed":1,"syntology":null},{"url":"/paper/building-an-open-vocabulary-video-clip-model","slug":"building-an-open-vocabulary-video-clip-model","title":"Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data","date":"2023-10-08","arxiv_id":"2310.05010","repositories_listed":1,"syntology":null},{"url":"/paper/disentangling-spatial-and-temporal-learning","slug":"disentangling-spatial-and-temporal-learning","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","date":"2023-09-14","arxiv_id":"2309.07911","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":6,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":10,"phrase":"9 ran (of which 6 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) · 1 unverified","sample_list":"/paper/disentangling-spatial-and-temporal-learning#ran","syntology_url":"https://syntology.ai/paper/2309.07911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07911"}},"official":{"repos":["alibaba-mmai-research/dist"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/eventful-transformers-leveraging-temporal","slug":"eventful-transformers-leveraging-temporal","title":"Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers","date":"2023-08-25","arxiv_id":"2308.13494","repositories_listed":1,"syntology":{"n":25,"n_ran":7,"n_constructed":1,"n_ran_checked":3,"n_instrument":4,"n_unverified":18,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 18 unverified","sample_list":"/paper/eventful-transformers-leveraging-temporal#ran","syntology_url":"https://syntology.ai/paper/2308.13494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13494"}},"official":{"repos":["WISION-Lab/eventful-transformer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":18,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-from-semantic-alignment-between","slug":"learning-from-semantic-alignment-between","title":"Learning from Semantic Alignment between Unpaired Multiviews for Egocentric Video Recognition","date":"2023-08-22","arxiv_id":"2308.11489","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-from-semantic-alignment-between#ran","syntology_url":"https://syntology.ai/paper/2308.11489","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11489"}},"official":{"repos":["wqtwjt1996/sum-l"],"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/audio-visual-class-incremental-learning","slug":"audio-visual-class-incremental-learning","title":"Audio-Visual Class-Incremental Learning","date":"2023-08-21","arxiv_id":"2308.11073","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/audio-visual-class-incremental-learning#ran","syntology_url":"https://syntology.ai/paper/2308.11073","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11073"}},"official":{"repos":["weiguopian/av-cil_iccv2023"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/helping-hands-an-object-aware-ego-centric","slug":"helping-hands-an-object-aware-ego-centric","title":"Helping Hands: An Object-Aware Ego-Centric Video Recognition Model","date":"2023-08-15","arxiv_id":"2308.07918","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"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) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/helping-hands-an-object-aware-ego-centric#ran","syntology_url":"https://syntology.ai/paper/2308.07918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07918"}},"official":{"repos":["chuhanxx/helping_hand_for_egocentric_videos"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/orthogonal-temporal-interpolation-for-zero","slug":"orthogonal-temporal-interpolation-for-zero","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","date":"2023-08-14","arxiv_id":"2308.06897","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/orthogonal-temporal-interpolation-for-zero#ran","syntology_url":"https://syntology.ai/paper/2308.06897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.06897"}},"official":{"repos":["sweetorangezhuyan/mm2023_oti"],"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":["official"]}}},{"url":"/paper/prune-spatio-temporal-tokens-by-semantic","slug":"prune-spatio-temporal-tokens-by-semantic","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","date":"2023-08-08","arxiv_id":"2308.04549","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"14 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prune-spatio-temporal-tokens-by-semantic#ran","syntology_url":"https://syntology.ai/paper/2308.04549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04549"}},"official":{"repos":["mark12ding/sta"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-temporal-modeling-with-learnable","slug":"implicit-temporal-modeling-with-learnable","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","date":"2023-04-20","arxiv_id":"2304.10465","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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) · 2 unverified","sample_list":"/paper/implicit-temporal-modeling-with-learnable#ran","syntology_url":"https://syntology.ai/paper/2304.10465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.10465"}},"official":{"repos":["francis-rings/ila"],"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/use-your-head-improving-long-tail-video","slug":"use-your-head-improving-long-tail-video","title":"Use Your Head: Improving Long-Tail Video Recognition","date":"2023-04-03","arxiv_id":"2304.01143","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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/use-your-head-improving-long-tail-video#ran","syntology_url":"https://syntology.ai/paper/2304.01143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01143"}},"official":{"repos":["tobyperrett/lmr-release"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-effectiveness-of-mae-pre-pretraining-for","slug":"the-effectiveness-of-mae-pre-pretraining-for","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","date":"2023-03-23","arxiv_id":"2303.13496","repositories_listed":1,"syntology":null},{"url":"/paper/making-vision-transformers-efficient-from-a","slug":"making-vision-transformers-efficient-from-a","title":"Making Vision Transformers Efficient from A Token Sparsification View","date":"2023-03-15","arxiv_id":"2303.08685","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/making-vision-transformers-efficient-from-a#ran","syntology_url":"https://syntology.ai/paper/2303.08685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08685"}},"official":{"repos":["changsn/STViT-R"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/match-expand-and-improve-unsupervised","slug":"match-expand-and-improve-unsupervised","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","date":"2023-03-15","arxiv_id":"2303.08914","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/match-expand-and-improve-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2303.08914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08914"}},"official":{"repos":["wlin-at/maxi"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/maximizing-spatio-temporal-entropy-of-deep-3d","slug":"maximizing-spatio-temporal-entropy-of-deep-3d","title":"Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition","date":"2023-03-05","arxiv_id":"2303.02693","repositories_listed":1,"syntology":null},{"url":"/paper/transforming-clip-to-an-open-vocabulary-video","slug":"transforming-clip-to-an-open-vocabulary-video","title":"Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization","date":"2023-02-01","arxiv_id":"2302.00624","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/transforming-clip-to-an-open-vocabulary-video#ran","syntology_url":"https://syntology.ai/paper/2302.00624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00624"}},"official":{"repos":["wengzejia1/open-vclip"],"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/revisiting-temporal-modeling-for-clip-based","slug":"revisiting-temporal-modeling-for-clip-based","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","date":"2023-01-26","arxiv_id":"2301.11116","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-robustness-assessment-via","slug":"efficient-robustness-assessment-via","title":"Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos","date":"2023-01-03","arxiv_id":"2301.00896","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-movie-scene-detection-using-state","slug":"efficient-movie-scene-detection-using-state","title":"Efficient Movie Scene Detection using State-Space Transformers","date":"2022-12-29","arxiv_id":"2212.14427","repositories_listed":1,"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/efficient-movie-scene-detection-using-state#ran","syntology_url":"https://syntology.ai/paper/2212.14427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14427"}},"official":{"repos":["md-mohaiminul/trans4mer"],"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/vlg-general-video-recognition-with-web","slug":"vlg-general-video-recognition-with-web","title":"VLG: General Video Recognition with Web Textual Knowledge","date":"2022-12-03","arxiv_id":"2212.01638","repositories_listed":1,"syntology":null},{"url":"/paper/svformer-semi-supervised-video-transformer","slug":"svformer-semi-supervised-video-transformer","title":"SVFormer: Semi-supervised Video Transformer for Action Recognition","date":"2022-11-23","arxiv_id":"2211.13222","repositories_listed":1,"syntology":null},{"url":"/paper/look-more-but-care-less-in-video-recognition","slug":"look-more-but-care-less-in-video-recognition","title":"Look More but Care Less in Video Recognition","date":"2022-11-18","arxiv_id":"2211.09992","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 3 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) · 3 unverified","sample_list":"/paper/look-more-but-care-less-in-video-recognition#ran","syntology_url":"https://syntology.ai/paper/2211.09992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09992"}},"official":{"repos":["bespontaneous/afnet-pytorch"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-superimposed-crossover-module-for","slug":"temporal-superimposed-crossover-module-for","title":"Temporal superimposed crossover module for effective continuous sign language","date":"2022-11-07","arxiv_id":"2211.03387","repositories_listed":1,"syntology":null},{"url":"/paper/cluster-and-aggregate-face-recognition-with","slug":"cluster-and-aggregate-face-recognition-with","title":"Cluster and Aggregate: Face Recognition with Large Probe Set","date":"2022-10-19","arxiv_id":"2210.10864","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":6,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cluster-and-aggregate-face-recognition-with#ran","syntology_url":"https://syntology.ai/paper/2210.10864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.10864"}},"official":{"repos":["mk-minchul/caface"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-unified-view-on-visual-parameter","slug":"towards-a-unified-view-on-visual-parameter","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","date":"2022-10-03","arxiv_id":"2210.00788","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"13 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-a-unified-view-on-visual-parameter#ran","syntology_url":"https://syntology.ai/paper/2210.00788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.00788"}},"official":{"repos":["bruceyo/V-PETL"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adafocusv3-on-unified-spatial-temporal","slug":"adafocusv3-on-unified-spatial-temporal","title":"AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition","date":"2022-09-27","arxiv_id":"2209.13465","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-resolution-in-the-context-of","slug":"rethinking-resolution-in-the-context-of","title":"Rethinking Resolution in the Context of Efficient Video Recognition","date":"2022-09-26","arxiv_id":"2209.12797","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rethinking-resolution-in-the-context-of#ran","syntology_url":"https://syntology.ai/paper/2209.12797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12797"}},"official":{"repos":["cvmi-lab/reskd"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-online-video-detection-with","slug":"real-time-online-video-detection-with","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","date":"2022-09-19","arxiv_id":"2209.09236","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/real-time-online-video-detection-with#ran","syntology_url":"https://syntology.ai/paper/2209.09236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.09236"}},"official":{"repos":["zhaoyue-zephyrus/testra"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visually-explaining-3d-cnn-predictions-for","slug":"visually-explaining-3d-cnn-predictions-for","title":"Adaptive occlusion sensitivity analysis for visually explaining video recognition networks","date":"2022-07-26","arxiv_id":"2207.12859","repositories_listed":1,"syntology":null},{"url":"/paper/mar-masked-autoencoders-for-efficient-action","slug":"mar-masked-autoencoders-for-efficient-action","title":"MAR: Masked Autoencoders for Efficient Action Recognition","date":"2022-07-24","arxiv_id":"2207.11660","repositories_listed":1,"syntology":null},{"url":"/paper/object-state-change-classification-in","slug":"object-state-change-classification-in","title":"Object State Change Classification in Egocentric Videos using the Divided Space-Time Attention Mechanism","date":"2022-07-24","arxiv_id":"2207.11814","repositories_listed":1,"syntology":null},{"url":"/paper/vidconv-a-modernized-2d-convnet-for-efficient","slug":"vidconv-a-modernized-2d-convnet-for-efficient","title":"VidConv: A modernized 2D ConvNet for Efficient Video Recognition","date":"2022-07-08","arxiv_id":"2207.03782","repositories_listed":1,"syntology":null}],"syntology_records":48,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":64,"papers_where_code_ran_first_page":"/task/video-recognition/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":4,"url":"/task/video-recognition/papers/2","json":"/task/video-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/video-recognition/papers/3","json":"/task/video-recognition/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/video-recognition/papers/4","json":"/task/video-recognition/papers/4.json","rows":7},{"order":"ran","page":1,"of":1,"url":"/task/video-recognition/papers/ran/1","json":"/task/video-recognition/papers/ran/1.json","rows":64}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"c5846327b7be70500b49ef93f151ccfafde60bb5cbc7211981661580431f081a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}