{"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/uniformerv2-spatiotemporal-learning-by-arming","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","arxiv_id":null,"date":"2022-09-22","proceeding":"ICLR2023 submitted 2022 9","authors":["Anonymous"],"abstract":"Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they exhibit limitations in tackling local video redundancy, due to the blind global comparison among tokens. UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format. However, this model has to require a tiresome and complicated image-pretraining phrase, before being finetuned on videos. This blocks its wide usage in practice. On the contrary, open-sourced ViTs are readily available and well-pretrained with rich image supervision. Based on these observations, we propose a generic paradigm to build a powerful family of video networks, by arming the pretrained ViTs with efficient UniFormer designs. We call this family UniFormerV2, since it inherits the concise style of the UniFormer block. But it contains brand-new local and global relation aggregators, which allow for preferable accuracy-computation balance by seamlessly integrating advantages from both ViTs and UniFormer. Without any bells and whistles, our UniFormerV2 gets the state-of-the-art recognition performance on 8 popular video benchmarks, including scene-related Kinetics-400/600/700 and Moments in Time, temporal-related Something-Something V1/V2, untrimmed ActivityNet and HACS. In particular, it is the first model to achieve 90% top-1 accuracy on Kinetics-400, to our best knowledge. The models will be released afterward.","url_abs":"https://openreview.net/forum?id=d77RVuVg-Mf","url_pdf":"https://openreview.net/pdf?id=d77RVuVg-Mf","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":"uniformerv2-spatiotemporal-learning-by-arming","repo_url":"https://github.com/OpenGVLab/UniFormerV2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"uniformerv2-spatiotemporal-learning-by-arming","repo_url":"https://github.com/innat/UniFormerV2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-activitynet","task":"Action Classification","dataset":"ActivityNet","model":"UniFormerV2-L","rank_in_archive_order":1,"of":1,"metrics":{"Top 1 Accuracy":"94.7","Top 5 Accuracy":"99.5"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"UniFormerV2-L (ViT-L, 336)","rank_in_archive_order":11,"of":207,"metrics":{"Acc@1":"90.0","Acc@5":"98.4","FLOPs (G) x views":"75300x3x2","Parameters (M)":"354"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"UniFormerV2-L","rank_in_archive_order":10,"of":65,"metrics":{"Top-1 Accuracy":"90.1","Top-5 Accuracy":"98.5"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"UniFormerV2-L","rank_in_archive_order":8,"of":36,"metrics":{"Top-1 Accuracy":"82.7","Top-5 Accuracy":"96.2"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-moments-in-time","task":"Action Classification","dataset":"MiT","model":"UniFormerV2-L","rank_in_archive_order":4,"of":29,"metrics":{"Top 1 Accuracy":"47.8","Top 5 Accuracy":"76.9"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-on-hacs","task":"Action Recognition","dataset":"HACS","model":"UniFormerV2-L","rank_in_archive_order":2,"of":8,"metrics":{"Top 1 Accuracy":"95.5","Top 5 Accuracy":"99.8"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something-1","task":"Action Recognition","dataset":"Something-Something V1","model":"UniFormerV2-L","rank_in_archive_order":7,"of":74,"metrics":{"Top 1 Accuracy":"62.7","Top 5 Accuracy":"88.0"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"UniFormerV2-L","rank_in_archive_order":23,"of":123,"metrics":{"GFLOPs":"5154","Top-1 Accuracy":"73.0","Top-5 Accuracy":"94.5"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"OpenGVLab/UniFormerV2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2211.09552"],"harvested_for_calls":[{"arxiv_id":"2211.09552","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.09552"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.09552\")"}]},{"repo":"innat/UniFormerV2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"322488903782d21733ac74c9e9f48600073dcfd5cabbd33d42607824b44f3c3e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}