{"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/rethinking-video-vits-sparse-video-tubes-for","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","arxiv_id":"2212.03229","date":"2022-12-06","proceeding":"CVPR 2023 1","authors":["AJ Piergiovanni","Weicheng Kuo","Anelia Angelova"],"abstract":"We present a simple approach which can turn a ViT encoder into an efficient video model, which can seamlessly work with both image and video inputs. By sparsely sampling the inputs, the model is able to do training and inference from both inputs. The model is easily scalable and can be adapted to large-scale pre-trained ViTs without requiring full finetuning. The model achieves SOTA results and the code will be open-sourced.","url_abs":"https://arxiv.org/abs/2212.03229v1","url_pdf":"https://arxiv.org/pdf/2212.03229v1.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":"rethinking-video-vits-sparse-video-tubes-for","repo_url":"https://github.com/daniel-code/TubeViT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition-in-videos-2","task_name":"Action Recognition In Videos"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"TubeViT-L","rank_in_archive_order":2,"of":49,"metrics":{"MAP":"66.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"TubeViT-H (ImageNet-1k)","rank_in_archive_order":7,"of":207,"metrics":{"Acc@1":"90.9","Acc@5":"98.9","FLOPs (G) x views":"176400x4x3","Parameters (M)":"632"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"TubeVit-L (ImageNet-1k)","rank_in_archive_order":10,"of":207,"metrics":{"Acc@1":"90.2","Acc@5":"98.6","FLOPs (G) x views":"95300x4x3","Parameters (M)":"307"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"TubeVit-B (ImageNet-1k)","rank_in_archive_order":24,"of":207,"metrics":{"Acc@1":"88.6","Acc@5":"97.6","FLOPs (G) x views":"8700x3x4","Parameters (M)":"86"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"TubeVit-H","rank_in_archive_order":2,"of":65,"metrics":{"Top-1 Accuracy":"91.8","Top-5 Accuracy":"98.9"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"TubeVit-L","rank_in_archive_order":4,"of":65,"metrics":{"Top-1 Accuracy":"91.5","Top-5 Accuracy":"98.7"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"TubeVit-B","rank_in_archive_order":7,"of":65,"metrics":{"Top-1 Accuracy":"90.9","Top-5 Accuracy":"97.3"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"TubeViT-L","rank_in_archive_order":4,"of":36,"metrics":{"Top-1 Accuracy":"83.8","Top-5 Accuracy":"96.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"TubeViT-L","rank_in_archive_order":8,"of":123,"metrics":{"Top-1 Accuracy":"76.1","Top-5 Accuracy":"95.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.03229","atlas_url":"https://app.syntology.ai/?focus=2212.03229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03229"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daniel-code/TubeViT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"e1389b364f3c75ab","entry":"get_2d_sincos_pos_embed","repo":"daniel-code/TubeViT","repo_kind":"listed","path":"tubevit/positional_encoding.py","file_url":"https://github.com/daniel-code/TubeViT/blob/HEAD/tubevit/positional_encoding.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1389b364f3c75ab"}},{"code_sha256_prefix":"715aab11d1b73ce8","entry":"get_2d_sincos_pos_embed_from_grid","repo":"daniel-code/TubeViT","repo_kind":"listed","path":"tubevit/positional_encoding.py","file_url":"https://github.com/daniel-code/TubeViT/blob/HEAD/tubevit/positional_encoding.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"715aab11d1b73ce8"}},{"code_sha256_prefix":"23745849d316e5ae","entry":"get_3d_sincos_pos_embed","repo":"daniel-code/TubeViT","repo_kind":"listed","path":"tubevit/positional_encoding.py","file_url":"https://github.com/daniel-code/TubeViT/blob/HEAD/tubevit/positional_encoding.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23745849d316e5ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}