{"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/co-training-transformer-with-videos-and","title":"Co-training Transformer with Videos and Images Improves Action Recognition","arxiv_id":"2112.07175","date":"2021-12-14","proceeding":null,"authors":["BoWen Zhang","Jiahui Yu","Christopher Fifty","Wei Han","Andrew M. Dai","Ruoming Pang","Fei Sha"],"abstract":"In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos. This approach has achieved good empirical performance especially with recent transformer-based video architectures. While recently many works aim to design more advanced transformer architectures for action recognition, less effort has been made on how to train video transformers. In this work, we explore several training paradigms and present two findings. First, video transformers benefit from joint training on diverse video datasets and label spaces (e.g., Kinetics is appearance-focused while SomethingSomething is motion-focused). Second, by further co-training with images (as single-frame videos), the video transformers learn even better video representations. We term this approach as Co-training Videos and Images for Action Recognition (CoVeR). In particular, when pretrained on ImageNet-21K based on the TimeSFormer architecture, CoVeR improves Kinetics-400 Top-1 Accuracy by 2.4%, Kinetics-600 by 2.3%, and SomethingSomething-v2 by 2.3%. When pretrained on larger-scale image datasets following previous state-of-the-art, CoVeR achieves best results on Kinetics-400 (87.2%), Kinetics-600 (87.9%), Kinetics-700 (79.8%), SomethingSomething-v2 (70.9%), and Moments-in-Time (46.1%), with a simple spatio-temporal video transformer.","url_abs":"https://arxiv.org/abs/2112.07175v1","url_pdf":"https://arxiv.org/pdf/2112.07175v1.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":[],"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"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"CoVeR (JFT-3B)","rank_in_archive_order":39,"of":207,"metrics":{"Acc@1":"87.2","Acc@5":"97.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"CoVeR (JFT-300M)","rank_in_archive_order":49,"of":207,"metrics":{"Acc@1":"86.3","Acc@5":"97.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"CoVeR (JFT-3B)","rank_in_archive_order":24,"of":65,"metrics":{"Top-1 Accuracy":"87.9","Top-5 Accuracy":"97.8"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-600","task":"Action Classification","dataset":"Kinetics-600","model":"CoVeR (JFT-300M)","rank_in_archive_order":26,"of":65,"metrics":{"Top-1 Accuracy":"86.8","Top-5 Accuracy":"97.3"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"CoVeR (JFT-3B)","rank_in_archive_order":15,"of":36,"metrics":{"Top-1 Accuracy":"79.8","Top-5 Accuracy":"94.9"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-kinetics-700","task":"Action Classification","dataset":"Kinetics-700","model":"CoVeR (JFT-300M)","rank_in_archive_order":18,"of":36,"metrics":{"Top-1 Accuracy":"78.5","Top-5 Accuracy":"94.2"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-moments-in-time","task":"Action Classification","dataset":"MiT","model":"CoVeR(JFT-3B)","rank_in_archive_order":6,"of":29,"metrics":{"Top 1 Accuracy":"46.1","Top 5 Accuracy":"75.4"},"uses_additional_data":true},{"leaderboard":"/sota/action-classification-on-moments-in-time","task":"Action Classification","dataset":"MiT","model":"CoVeR(JFT-300M)","rank_in_archive_order":7,"of":29,"metrics":{"Top 1 Accuracy":"45.0","Top 5 Accuracy":"73.9"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"CoVeR(JFT-3B)","rank_in_archive_order":35,"of":123,"metrics":{"Top-1 Accuracy":"70.9","Top-5 Accuracy":"92.5"},"uses_additional_data":true},{"leaderboard":"/sota/action-recognition-in-videos-on-something","task":"Action Recognition","dataset":"Something-Something V2","model":"CoVeR(JFT-300M)","rank_in_archive_order":40,"of":123,"metrics":{"Top-1 Accuracy":"69.8","Top-5 Accuracy":"91.9"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.07175","atlas_url":"https://app.syntology.ai/?focus=2112.07175","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":"2112.07175"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.07175\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.07175"},"call":"get_concepts_for_paper(arxiv_id=\"2112.07175\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"029e03ecc455232319575702045cb4d1299837879d660b7a95348388c8b6d097","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}