{"url":"/task/few-shot-action-recognition","name":"Few Shot Action Recognition","slug":"few-shot-action-recognition","description_markdown":"Few-shot (FS) action recognition is a challenging com-\r\nputer vision problem, where the task is to classify an unlabelled query video into one of the action categories in the support set having limited samples per action class.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":76,"papers_with_code":31,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/few-shot-action-recognition-on-kinetics-100","slug":"few-shot-action-recognition-on-kinetics-100","dataset":"Kinetics-100","dataset_url":"/dataset/kinetics-100","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Name Tuning","paper_title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","paper_url":"/paper/few-shot-classification-of-interactive","paper_date":"2024-06-03","arxiv_id":"2406.01662","code_links":[{"title":"zanedurante/vlm_benchmark","url":"https://github.com/zanedurante/vlm_benchmark"}],"syntology":null}},{"leaderboard":"/sota/few-shot-action-recognition-on-hmdb51","slug":"few-shot-action-recognition-on-hmdb51","dataset":"HMDB51","dataset_url":"/dataset/hmdb51","rows_in_archive":7,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"STRM","paper_title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","paper_url":"/paper/spatio-temporal-relation-modeling-for-few","paper_date":"2021-12-09","arxiv_id":"2112.05132","code_links":[{"title":"Anirudh257/strm","url":"https://github.com/Anirudh257/strm"}],"syntology":null}},{"leaderboard":"/sota/few-shot-action-recognition-on-ucf101","slug":"few-shot-action-recognition-on-ucf101","dataset":"UCF101","dataset_url":"/dataset/ucf101","rows_in_archive":7,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"STRM","paper_title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","paper_url":"/paper/spatio-temporal-relation-modeling-for-few","paper_date":"2021-12-09","arxiv_id":"2112.05132","code_links":[{"title":"Anirudh257/strm","url":"https://github.com/Anirudh257/strm"}],"syntology":null}},{"leaderboard":"/sota/few-shot-action-recognition-on-something","slug":"few-shot-action-recognition-on-something","dataset":"Something-Something-100","dataset_url":"/dataset/something-something-100","rows_in_archive":5,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"HyRSM","paper_title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","paper_url":"/paper/hybrid-relation-guided-set-matching-for-few","paper_date":"2022-04-28","arxiv_id":"2204.13423","code_links":[{"title":"alibaba-mmai-research/HyRSM","url":"https://github.com/alibaba-mmai-research/HyRSM"}],"syntology":null}},{"leaderboard":"/sota/few-shot-action-recognition-on-moma-lrg","slug":"few-shot-action-recognition-on-moma-lrg","dataset":"MOMA-LRG","dataset_url":"/dataset/moma-lrg","rows_in_archive":4,"metrics":["Activity Classification Accuracy (5-shot 5-way)","Subactivity Classification Accuracy (5-shot 5-way)"],"first_row_in_archive_order":{"model":"Name Tuning","paper_title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","paper_url":"/paper/few-shot-classification-of-interactive","paper_date":"2024-06-03","arxiv_id":"2406.01662","code_links":[{"title":"zanedurante/vlm_benchmark","url":"https://github.com/zanedurante/vlm_benchmark"}],"syntology":null}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/hmdb51","name":"HMDB51","full_name":"","num_papers_in_archive":839},{"url":"/dataset/kinetics-100","name":"Kinetics-100","full_name":"","num_papers_in_archive":8},{"url":"/dataset/something-something-100","name":"Something-Something-100","full_name":"","num_papers_in_archive":4},{"url":"/dataset/moma-lrg","name":"MOMA-LRG","full_name":"Multi-Object Multi-Actor activity parsing with Language-Refined Graphs","num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[{"url":"/task/action-recognition-in-videos","name":"Action Recognition"}],"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":31,"tagged_in_all":76,"items":[{"url":"/paper/temporal-relational-crosstransformers-for-few","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","date":"2021-01-15","arxiv_id":"2101.06184","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/temporal-relational-crosstransformers-for-few","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","date":"2021-01-15","arxiv_id":"2101.06184","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/action-genome-actions-as-composition-of","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","date":"2019-12-15","arxiv_id":"1912.06992","repositories_listed":2,"syntology":null},{"url":"/paper/action-genome-actions-as-composition-of","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","date":"2019-12-15","arxiv_id":"1912.06992","repositories_listed":2,"syntology":null},{"url":"/paper/task-adapter-task-specific-adaptation-with","title":"Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition","date":"2025-05-09","arxiv_id":"2505.06002","repositories_listed":1,"syntology":null},{"url":"/paper/task-adapter-task-specific-adaptation-with","title":"Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition","date":"2025-05-09","arxiv_id":"2505.06002","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-alignment-free-video-matching-for-1","title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","date":"2025-04-08","arxiv_id":"2504.05956","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/temporal-alignment-free-video-matching-for-1","title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","date":"2025-04-08","arxiv_id":"2504.05956","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/tamt-temporal-aware-model-tuning-for-cross","title":"TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition","date":"2024-11-28","arxiv_id":"2411.19041","repositories_listed":1,"syntology":null},{"url":"/paper/tamt-temporal-aware-model-tuning-for-cross","title":"TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition","date":"2024-11-28","arxiv_id":"2411.19041","repositories_listed":1,"syntology":null},{"url":"/paper/soap-enhancing-spatio-temporal-relation-and","title":"SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition","date":"2024-07-23","arxiv_id":"2407.16344","repositories_listed":1,"syntology":null},{"url":"/paper/soap-enhancing-spatio-temporal-relation-and","title":"SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognition","date":"2024-07-23","arxiv_id":"2407.16344","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-classification-of-interactive","title":"Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)","date":"2024-06-03","arxiv_id":"2406.01662","repositories_listed":1,"syntology":null},{"url":"/paper/d-2-st-adapter-disentangled-and-deformable","title":"D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition","date":"2023-12-03","arxiv_id":"2312.01431","repositories_listed":1,"syntology":null},{"url":"/paper/d-2-st-adapter-disentangled-and-deformable","title":"D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition","date":"2023-12-03","arxiv_id":"2312.01431","repositories_listed":1,"syntology":null},{"url":"/paper/cdfsl-v-cross-domain-few-shot-learning-for","title":"CDFSL-V: Cross-Domain Few-Shot Learning for Videos","date":"2023-09-07","arxiv_id":"2309.03989","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/cdfsl-v-cross-domain-few-shot-learning-for","title":"CDFSL-V: Cross-Domain Few-Shot Learning for Videos","date":"2023-09-07","arxiv_id":"2309.03989","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/boosting-few-shot-action-recognition-with","title":"Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching","date":"2023-08-18","arxiv_id":"2308.09346","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-few-shot-action-recognition-with","title":"Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching","date":"2023-08-18","arxiv_id":"2308.09346","repositories_listed":1,"syntology":null},{"url":"/paper/task-specific-alignment-and-multiple-level","title":"Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition","date":"2023-07-05","arxiv_id":"2307.01985","repositories_listed":1,"syntology":null},{"url":"/paper/task-specific-alignment-and-multiple-level","title":"Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition","date":"2023-07-05","arxiv_id":"2307.01985","repositories_listed":1,"syntology":null},{"url":"/paper/molo-motion-augmented-long-short-contrastive","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","date":"2023-04-03","arxiv_id":"2304.00946","repositories_listed":1,"syntology":null},{"url":"/paper/molo-motion-augmented-long-short-contrastive","title":"MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition","date":"2023-04-03","arxiv_id":"2304.00946","repositories_listed":1,"syntology":null},{"url":"/paper/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_unverified":1,"n_pointer_only":4}},{"url":"/paper/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_unverified":1,"n_pointer_only":4}},{"url":"/paper/clip-guided-prototype-modulating-for-few-shot","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","date":"2023-03-06","arxiv_id":"2303.02982","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/clip-guided-prototype-modulating-for-few-shot","title":"CLIP-guided Prototype Modulating for Few-shot Action Recognition","date":"2023-03-06","arxiv_id":"2303.02982","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/hyrsm-hybrid-relation-guided-temporal-set","title":"HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition","date":"2023-01-09","arxiv_id":"2301.03330","repositories_listed":1,"syntology":null},{"url":"/paper/hyrsm-hybrid-relation-guided-temporal-set","title":"HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition","date":"2023-01-09","arxiv_id":"2301.03330","repositories_listed":1,"syntology":null},{"url":"/paper/tempclr-temporal-alignment-representation","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","date":"2022-12-28","arxiv_id":"2212.13738","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}}],"syntology_records":11,"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"}}