{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":168,"tagged_in_all":307,"items":[{"url":"/paper/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":14,"n_unverified":20,"n_pointer_only":8}},{"url":"/paper/video-swin-transformer","title":"Video Swin Transformer","date":"2021-06-24","arxiv_id":"2106.13230","repositories_listed":15,"syntology":{"n":32,"n_ran":7,"n_unverified":25,"n_pointer_only":0}},{"url":"/paper/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":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/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":6,"n_unverified":10,"n_pointer_only":4}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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":2,"n_unverified":20,"n_pointer_only":0}},{"url":"/paper/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","title":"Multiscale Vision Transformers","date":"2021-04-22","arxiv_id":"2104.11227","repositories_listed":8,"syntology":{"n":26,"n_ran":13,"n_unverified":13,"n_pointer_only":5}},{"url":"/paper/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":2,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/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","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","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":17,"n_unverified":15,"n_pointer_only":21}},{"url":"/paper/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":8,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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","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","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":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/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","title":"Deep Feature Flow for Video Recognition","date":"2016-11-23","arxiv_id":"1611.07715","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/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","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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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_unverified":3,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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_unverified":5,"n_pointer_only":10}},{"url":"/paper/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_unverified":0,"n_pointer_only":3}}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}