{"url":"/sota/zero-shot-action-recognition-on-ucf101","task":{"name":"Zero-Shot Action Recognition","url":"/task/zero-shot-action-recognition","note":null},"dataset":{"name":"UCF101","url":"/dataset/ucf101"},"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":35,"rows_with_code":18,"rows_with_paper_page":32,"rows_dated":32,"rows_using_additional_data":4},"rows":[{"rank_in_archive_order":1,"model":"OTI(ViT-L/14)","metrics":{"Top-1 Accuracy":"92.8"},"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":2,"model":"IMP-MoE-L","metrics":{"Top-1 Accuracy":"91.5"},"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":"MOV (ViT-L/14)","metrics":{"Top-1 Accuracy":"87.1"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/multimodal-open-vocabulary-video","paper_url":"https://arxiv.org/abs/2207.07646v1","paper_title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"VideoCoCa","metrics":{"Top-1 Accuracy":"86.6","Top-5 accuracy":"98.4"},"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":5,"model":"BIKE","metrics":{"Top-1 Accuracy":"86.6"},"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":6,"model":"Text4Vis","metrics":{"Top-1 Accuracy":"85.8"},"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":7,"model":"TC-CLIP","metrics":{"Top-1 Accuracy":"85.4"},"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":8,"model":"EVA-CLIP-E/14+","metrics":{"Top-1 Accuracy":"83.1"},"uses_additional_data":true,"paper_date":"2023-03-27","paper":"/paper/eva-clip-improved-training-techniques-for","paper_url":"https://arxiv.org/abs/2303.15389v1","paper_title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","code":"https://github.com/baaivision/eva","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"MOV (ViT-B/16)","metrics":{"Top-1 Accuracy":"82.6"},"uses_additional_data":false,"paper_date":"2022-07-15","paper":"/paper/multimodal-open-vocabulary-video","paper_url":"https://arxiv.org/abs/2207.07646v1","paper_title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"OST","metrics":{"Top-1 Accuracy":"79.7"},"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":11,"model":"EZ-CLIP","metrics":{"Top-1 Accuracy":"79.1"},"uses_additional_data":true,"paper_date":"2023-12-13","paper":"/paper/ez-clip-efficient-zeroshot-video-action","paper_url":"https://arxiv.org/abs/2312.08010v2","paper_title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","code":"https://github.com/shahzadnit/ez-clip","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"MAXI","metrics":{"Top-1 Accuracy":"78.2"},"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":13,"model":"LoCATe-GAT","metrics":{"Top-1 Accuracy":"76.0"},"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":14,"model":"VicTR (ViT-B/16)","metrics":{"Top-1 Accuracy":"72.4"},"uses_additional_data":false,"paper_date":"2023-04-05","paper":"/paper/victr-video-conditioned-text-representations","paper_url":"https://arxiv.org/abs/2304.02560v2","paper_title":"VicTR: Video-conditioned Text Representations for Activity Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"X-CLIP","metrics":{"Top-1 Accuracy":"72.0"},"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":16,"model":"ResT","metrics":{"Top-1 Accuracy":"58.7"},"uses_additional_data":false,"paper_date":"2022-05-03","paper":"/paper/cross-modal-representation-learning-for-zero","paper_url":"https://arxiv.org/abs/2205.01657v1","paper_title":"Cross-modal Representation Learning for Zero-shot Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"AURL","metrics":{"Top-1 Accuracy":"58"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/alignment-uniformity-aware-representation","paper_url":"https://arxiv.org/abs/2203.15381v1","paper_title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","code":"https://github.com/ShipuLoveMili/CVPR2022-AURL","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":18,"model":"JigsawNet","metrics":{"Top-1 Accuracy":"56.0"},"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":19,"model":"CLASTER","metrics":{"Top-1 Accuracy":"53.9"},"uses_additional_data":false,"paper_date":"2021-01-18","paper":"/paper/claster-clustering-with-reinforcement","paper_url":"https://arxiv.org/abs/2101.07042v3","paper_title":"CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"ER-ZSAR","metrics":{"Top-1 Accuracy":"51.8"},"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":21,"model":"E2E","metrics":{"Top-1 Accuracy":"48"},"uses_additional_data":false,"paper_date":"2020-03-03","paper":"/paper/rethinking-zero-shot-video-classification-end","paper_url":"https://arxiv.org/abs/2003.01455v4","paper_title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","code":"https://github.com/bbrattoli/ZeroShotVideoClassification","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":12,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"SPOT","metrics":{"Top-1 Accuracy":"40.9"},"uses_additional_data":false,"paper_date":"2023-04-06","paper":"/paper/synthetic-sample-selection-for-generalized","paper_url":"https://arxiv.org/abs/2304.02846v1","paper_title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"TS-GCN","metrics":{"Top-1 Accuracy":"34.2"},"uses_additional_data":false,"paper_date":"2019-07-17","paper":"/paper/i-know-the-relationships-zero-shot-action","paper_url":"https://ojs.aaai.org//index.php/AAAI/article/view/4843","paper_title":"I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs","code":"https://github.com/junyuGao/Zero-Shot-Action-Recognition-with-Two-Stream-GCN","n_code_links":1,"syntology":null},{"rank_in_archive_order":24,"model":"O2A","metrics":{"Top-1 Accuracy":"30.3"},"uses_additional_data":false,"paper_date":"2015-10-23","paper":"/paper/objects2action-classifying-and-localizing","paper_url":"http://arxiv.org/abs/1510.06939v1","paper_title":"Objects2action: Classifying and localizing actions without any video example","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"ASR","metrics":{"Top-1 Accuracy":"24.4"},"uses_additional_data":false,"paper_date":"2017-06-28","paper":"/paper/alternative-semantic-representations-for-zero","paper_url":"http://arxiv.org/abs/1706.09317v1","paper_title":"Alternative Semantic Representations for Zero-Shot Human Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"UR","metrics":{"Top-1 Accuracy":"17.5"},"uses_additional_data":false,"paper_date":"2018-03-22","paper":"/paper/towards-universal-representation-for-unseen","paper_url":"http://arxiv.org/abs/1803.08460v1","paper_title":"Towards Universal Representation for Unseen Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"IAP","metrics":{"Top-1 Accuracy":"16.7"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"DAP","metrics":{"Top-1 Accuracy":"15.9"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"MTE","metrics":{"Top-1 Accuracy":"15.8"},"uses_additional_data":false,"paper_date":"2016-11-26","paper":"/paper/multi-task-zero-shot-action-recognition-with","paper_url":"http://arxiv.org/abs/1611.08663v1","paper_title":"Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"ZSECOC","metrics":{"Top-1 Accuracy":"15.1"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/zero-shot-action-recognition-with-error","paper_url":"http://openaccess.thecvf.com/content_cvpr_2017/html/Qin_Zero-Shot_Action_Recognition_CVPR_2017_paper.html","paper_title":"Zero-Shot Action Recognition With Error-Correcting Output Codes","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"ESZSL","metrics":{"Top-1 Accuracy":"15.0"},"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":32,"model":"HAA","metrics":{"Top-1 Accuracy":"14.9"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"SJE(Attribute)","metrics":{"Top-1 Accuracy":"12.0"},"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},{"rank_in_archive_order":34,"model":"SVE","metrics":{"Top-1 Accuracy":"10.9"},"uses_additional_data":false,"paper_date":"2015-02-05","paper":"/paper/semantic-embedding-space-for-zero-shot-action","paper_url":"http://arxiv.org/abs/1502.01540v1","paper_title":"Semantic Embedding Space for Zero-Shot Action Recognition","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"SJE(Word Embedding)","metrics":{"Top-1 Accuracy":"9.9"},"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 6,264 of the 9,581 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":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+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":10,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":10,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":26,"n_unverified":39,"n_samples":65,"n_pointer_only_licence":19,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":26,"n_unverified":39,"n_samples":65,"n_pointer_only_licence":19,"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"}}}