{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/temporal-alignment-free-video-matching-for-1","title":"Temporal Alignment-Free Video Matching for Few-shot Action Recognition","arxiv_id":"2504.05956","date":"2025-04-08","proceeding":"CVPR 2025 1","authors":["SuBeen Lee","WonJun Moon","Hyun Seok Seong","Jae-Pil Heo"],"abstract":"Few-Shot Action Recognition (FSAR) aims to train a model with only a few labeled video instances. A key challenge in FSAR is handling divergent narrative trajectories for precise video matching. While the frame- and tuple-level alignment approaches have been promising, their methods heavily rely on pre-defined and length-dependent alignment units (e.g., frames or tuples), which limits flexibility for actions of varying lengths and speeds. In this work, we introduce a novel TEmporal Alignment-free Matching (TEAM) approach, which eliminates the need for temporal units in action representation and brute-force alignment during matching. Specifically, TEAM represents each video with a fixed set of pattern tokens that capture globally discriminative clues within the video instance regardless of action length or speed, ensuring its flexibility. Furthermore, TEAM is inherently efficient, using token-wise comparisons to measure similarity between videos, unlike existing methods that rely on pairwise comparisons for temporal alignment. Additionally, we propose an adaptation process that identifies and removes common information across classes, establishing clear boundaries even between novel categories. Extensive experiments demonstrate the effectiveness of TEAM. Codes are available at github.com/leesb7426/TEAM.","url_abs":"https://arxiv.org/abs/2504.05956v1","url_pdf":"https://arxiv.org/pdf/2504.05956v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"temporal-alignment-free-video-matching-for-1","repo_url":"https://github.com/leesb7426/team","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"few-shot-action-recognition","task_name":"Few Shot Action Recognition"},{"task_slug":"few-shot-action-recognition","task_name":"Few-Shot action recognition"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.05956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05956"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/leesb7426/TEAM","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"6d69fb99b137b915","entry":"Bottleneck_Perceptron_2_layer","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d69fb99b137b915"}},{"code_sha256_prefix":"6ae60d8c5e429a3a","entry":"PositionalEncoding","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ae60d8c5e429a3a"}},{"code_sha256_prefix":"0060f57ddf7114e9","entry":"ScaledDotProductAttention","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0060f57ddf7114e9"}},{"code_sha256_prefix":"17d17d0d53b48796","entry":"extract_class_indices","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"17d17d0d53b48796"}},{"code_sha256_prefix":"452f223140521ecb","entry":"CNN_FSHead","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"452f223140521ecb"}},{"code_sha256_prefix":"5caa732fbf4d1338","entry":"Discriminative_Pattern_Matching","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5caa732fbf4d1338"}},{"code_sha256_prefix":"84f673c127a6088b","entry":"TEAM","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"84f673c127a6088b"}},{"code_sha256_prefix":"05ef23fdf5293c37","entry":"TEAM_pos","repo":"leesb7426/TEAM","repo_kind":"official","path":"model.py","file_url":"https://github.com/leesb7426/TEAM/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"05ef23fdf5293c37"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}