{"url":"/sota/zero-shot-action-recognition-on-kinetics","task":{"name":"Zero-Shot Action Recognition","url":"/task/zero-shot-action-recognition","note":null},"dataset":{"name":"Kinetics","url":"/dataset/kinetics"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Top-1 Accuracy","Top-5 Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Top-1 Accuracy":"higher","Top-5 Accuracy":"higher"}},"counts":{"rows":20,"rows_with_code":16,"rows_with_paper_page":20,"rows_dated":20,"rows_using_additional_data":3},"rows":[{"rank_in_archive_order":1,"model":"TC-CLIP","metrics":{"Top-1 Accuracy":"78.1","Top-5 Accuracy":"95.7"},"uses_additional_data":false,"paper_date":"2024-04-15","paper":"/paper/leveraging-temporal-contextualization-for","paper_url":"https://arxiv.org/abs/2404.09490v2","paper_title":"Leveraging Temporal Contextualization for Video Action Recognition","code":"https://github.com/naver-ai/tc-clip","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":2,"model":"IMP-MoE-L","metrics":{"Top-1 Accuracy":"76.8"},"uses_additional_data":true,"paper_date":"2023-05-10","paper":"/paper/alternating-gradient-descent-and-mixture-of","paper_url":"https://arxiv.org/abs/2305.06324v2","paper_title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"OST","metrics":{"Top-1 Accuracy":"75.1","Top-5 Accuracy":"94.6"},"uses_additional_data":false,"paper_date":"2023-11-30","paper":"/paper/ost-refining-text-knowledge-with-optimal","paper_url":"https://arxiv.org/abs/2312.00096v2","paper_title":"OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition","code":"https://github.com/tomchen-ctj/OST","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"MAXI","metrics":{"Top-1 Accuracy":"71.6"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/match-expand-and-improve-unsupervised","paper_url":"https://arxiv.org/abs/2303.08914v2","paper_title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","code":"https://github.com/wlin-at/maxi","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":5,"model":"OTI（ViT-L/14）","metrics":{"Top-1 Accuracy":"70.6"},"uses_additional_data":false,"paper_date":"2023-08-14","paper":"/paper/orthogonal-temporal-interpolation-for-zero","paper_url":"https://arxiv.org/abs/2308.06897v1","paper_title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","code":"https://github.com/sweetorangezhuyan/mm2023_oti","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":6,"model":"VideoCoCa","metrics":{"Top-1 Accuracy":"70.1","Top-5 Accuracy":"88.9"},"uses_additional_data":true,"paper_date":"2022-12-09","paper":"/paper/video-text-modeling-with-zero-shot-transfer","paper_url":"https://arxiv.org/abs/2212.04979v3","paper_title":"VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"Text4Vis","metrics":{"Top-1 Accuracy":"68.9","Top-5 Accuracy":"90.3"},"uses_additional_data":false,"paper_date":"2022-07-04","paper":"/paper/transferring-textual-knowledge-for-visual","paper_url":"https://arxiv.org/abs/2207.01297v4","paper_title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","code":"https://github.com/whwu95/Cap4Video","n_code_links":5,"syntology":null},{"rank_in_archive_order":8,"model":"BIKE","metrics":{"Top-1 Accuracy":"68.5","Top-5 Accuracy":"91.1"},"uses_additional_data":false,"paper_date":"2022-12-31","paper":"/paper/bidirectional-cross-modal-knowledge","paper_url":"https://arxiv.org/abs/2301.00182v2","paper_title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","code":"https://github.com/whwu95/Cap4Video","n_code_links":5,"syntology":null},{"rank_in_archive_order":9,"model":"X-CLIP","metrics":{"Top-1 Accuracy":"65.2","Top-5 Accuracy":"86.1"},"uses_additional_data":false,"paper_date":"2022-08-04","paper":"/paper/expanding-language-image-pretrained-models","paper_url":"https://arxiv.org/abs/2208.02816v1","paper_title":"Expanding Language-Image Pretrained Models for General Video Recognition","code":"https://github.com/microsoft/videox","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":10,"model":"LanguageBind","metrics":{"Top-1 Accuracy":"64.1","Top-5 Accuracy":"85.7"},"uses_additional_data":true,"paper_date":"2023-10-03","paper":"/paper/languagebind-extending-video-language","paper_url":"https://arxiv.org/abs/2310.01852v7","paper_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","code":"https://github.com/PKU-YuanGroup/Video-LLaVA","n_code_links":6,"syntology":{"n_ran":9,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"LoCATe-GAT","metrics":{"Top-1 Accuracy":"58.7"},"uses_additional_data":false,"paper_date":"2024-11-27","paper":"/paper/locate-gat-modeling-multi-scale-local-context","paper_url":"https://ieeexplore.ieee.org/document/10769605","paper_title":"LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition","code":"https://github.com/sandipan211/LoCATe-GAT","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"JigsawNet","metrics":{"Top-1 Accuracy":"45.9","Top-5 Accuracy":"78.8"},"uses_additional_data":false,"paper_date":"2022-03-28","paper":"/paper/rethinking-zero-shot-action-recognition","paper_url":"https://link.springer.com/chapter/10.1007/978-3-031-19772-7_7","paper_title":"Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions","code":"https://github.com/KevinQian97/JigsawNet","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"ER-ZSAR (ST+Obj)","metrics":{"Top-1 Accuracy":"42.1","Top-5 Accuracy":"73.1"},"uses_additional_data":false,"paper_date":"2021-08-05","paper":"/paper/elaborative-rehearsal-for-zero-shot-action","paper_url":"https://arxiv.org/abs/2108.02833v2","paper_title":"Elaborative Rehearsal for Zero-shot Action Recognition","code":"https://github.com/DeLightCMU/ElaborativeRehearsal","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"ER-ZSAR (ST)","metrics":{"Top-1 Accuracy":"37.1","Top-5 Accuracy":"69.3"},"uses_additional_data":false,"paper_date":"2021-08-05","paper":"/paper/elaborative-rehearsal-for-zero-shot-action","paper_url":"https://arxiv.org/abs/2108.02833v2","paper_title":"Elaborative Rehearsal for Zero-shot Action Recognition","code":"https://github.com/DeLightCMU/ElaborativeRehearsal","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"DEVISE","metrics":{"Top-1 Accuracy":"23.8","Top-5 Accuracy":"51.0"},"uses_additional_data":false,"paper_date":"2013-12-01","paper":"/paper/devise-a-deep-visual-semantic-embedding-model","paper_url":"http://papers.nips.cc/paper/5204-devise-a-deep-visual-semantic-embedding-model","paper_title":"DeViSE: A Deep Visual-Semantic Embedding Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"DEM","metrics":{"Top-1 Accuracy":"23.6","Top-5 Accuracy":"49.5"},"uses_additional_data":false,"paper_date":"2016-11-15","paper":"/paper/learning-a-deep-embedding-model-for-zero-shot","paper_url":"https://arxiv.org/abs/1611.05088v4","paper_title":"Learning a Deep Embedding Model for Zero-Shot Learning","code":"https://github.com/lzrobots/DeepEmbeddingModel_ZSL","n_code_links":4,"syntology":null},{"rank_in_archive_order":17,"model":"ALE","metrics":{"Top-1 Accuracy":"23.4","Top-5 Accuracy":"50.3"},"uses_additional_data":false,"paper_date":"2015-03-30","paper":"/paper/label-embedding-for-image-classification","paper_url":"http://arxiv.org/abs/1503.08677v2","paper_title":"Label-Embedding for Image Classification","code":"https://github.com/mvp18/Popular-ZSL-Algorithms","n_code_links":2,"syntology":null},{"rank_in_archive_order":18,"model":"ESZSL","metrics":{"Top-1 Accuracy":"22.9","Top-5 Accuracy":"48.3"},"uses_additional_data":false,"paper_date":"2015-07-06","paper":"/paper/an-embarrassingly-simple-approach-to-zero","paper_url":"https://dl.acm.org/doi/10.5555/3045118.3045347","paper_title":"An embarrassingly simple approach to zero-shot learning","code":"https://github.com/chichilicious/embarrsingly-simple-zero-shot-learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"GCN","metrics":{"Top-1 Accuracy":"22.3","Top-5 Accuracy":"49.7"},"uses_additional_data":false,"paper_date":"2020-08-28","paper":"/paper/all-about-knowledge-graphs-for-actions","paper_url":"https://arxiv.org/abs/2008.12432v1","paper_title":"All About Knowledge Graphs for Actions","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"SJE(Word Embedding)","metrics":{"Top-1 Accuracy":"22.3","Top-5 Accuracy":"48.2"},"uses_additional_data":false,"paper_date":"2014-09-30","paper":"/paper/evaluation-of-output-embeddings-for-fine","paper_url":"http://arxiv.org/abs/1409.8403v2","paper_title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","code":"https://github.com/mvp18/Popular-ZSL-Algorithms","n_code_links":2,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":8,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":7,"samples_over_distinct_papers":{"n_ran":24,"n_unverified":21,"n_samples":45,"n_pointer_only_licence":14,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":27,"n_unverified":33,"n_samples":60,"n_pointer_only_licence":14,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}