{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-implicit-temporal-alignment-for-few","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","arxiv_id":"2105.04823","date":"2021-05-11","proceeding":null,"authors":["Songyang Zhang","Jiale Zhou","Xuming He"],"abstract":"Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in real-world applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective context encoding module to incorporate spatial and feature channel context, resulting in better modeling of intra-class variations. To train our model, we develop a multi-task loss for learning video matching, leading to video features with better generalization. Extensive experimental results on two challenging benchmarks, show that our method outperforms the prior arts with a sizable margin on SomethingSomething-V2 and competitive results on Kinetics.","url_abs":"https://arxiv.org/abs/2105.04823v1","url_pdf":"https://arxiv.org/pdf/2105.04823v1.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":"learning-implicit-temporal-alignment-for-few","repo_url":"https://github.com/tonysy/PyAction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something-1","task":"Action Recognition In Videos","dataset":"FS-Something-Something V2-Full","model":"ITANet","rank_in_archive_order":1,"of":2,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"49.2","Top-1 Accuracy(5-Way-5-Shot)":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something-1","task":"Action Recognition In Videos","dataset":"FS-Something-Something V2-Full","model":"OTAM[3]++","rank_in_archive_order":2,"of":2,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"42.8","Top-1 Accuracy(5-Way-5-Shot)":"52.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something","task":"Action Recognition In Videos","dataset":"FS-Something-Something V2-Small","model":"ITANet","rank_in_archive_order":1,"of":2,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"39.8","Top-1 Accuracy(5-Way-5-Shot)":"53.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-fs-something","task":"Action Recognition In Videos","dataset":"FS-Something-Something V2-Small","model":"CMN[35]","rank_in_archive_order":2,"of":2,"metrics":{"Top-1 Accuracy(5-Way-1-Shot)":"36.2","Top-1 Accuracy(5-Way-5-Shot)":"48.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.04823","atlas_url":"https://app.syntology.ai/?focus=2105.04823","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2105.04823"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2105.04823\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2105.04823"},"call":"get_concepts_for_paper(arxiv_id=\"2105.04823\")"}],"by_repo":[{"repo":"tonysy/PyAction","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.03982"],"harvested_for_calls":[{"arxiv_id":"1812.03982","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.03982"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.03982\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f52335c2aa623a839578b009a32ba7af6faab4bafda57044ce864528ba964cbc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}