{"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/transferring-textual-knowledge-for-visual","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","arxiv_id":"2207.01297","date":"2022-07-04","proceeding":null,"authors":["Wenhao Wu","Zhun Sun","Wanli Ouyang"],"abstract":"Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. Along with the growth of computational capacity, we now have open-source vision-language pre-trained models in large scales of the model architecture and amount of data. In this study, we focus on transferring knowledge for video classification tasks. Conventional methods randomly initialize the linear classifier head for vision classification, but they leave the usage of the text encoder for downstream visual recognition tasks undiscovered. In this paper, we revise the role of the linear classifier and replace the classifier with the different knowledge from pre-trained model. We utilize the well-pretrained language model to generate good semantic target for efficient transferring learning. The empirical study shows that our method improves both the performance and the training speed of video classification, with a negligible change in the model. Our simple yet effective tuning paradigm achieves state-of-the-art performance and efficient training on various video recognition scenarios, i.e., zero-shot, few-shot, general recognition. In particular, our paradigm achieves the state-of-the-art accuracy of 87.8% on Kinetics-400, and also surpasses previous methods by 20~50% absolute top-1 accuracy under zero-shot, few-shot settings on five popular video datasets. Code and models can be found at https://github.com/whwu95/Text4Vis .","url_abs":"https://arxiv.org/abs/2207.01297v4","url_pdf":"https://arxiv.org/pdf/2207.01297v4.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":"transferring-textual-knowledge-for-visual","repo_url":"https://github.com/whwu95/text4vis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transferring-textual-knowledge-for-visual","repo_url":"https://github.com/whwu95/ATM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"transferring-textual-knowledge-for-visual","repo_url":"https://github.com/whwu95/BIKE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transferring-textual-knowledge-for-visual","repo_url":"https://github.com/whwu95/Cap4Video","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"transferring-textual-knowledge-for-visual","repo_url":"https://github.com/whwu95/GPT4Vis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","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":"classification-1","task_name":"Classification"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-recognition","task_name":"Video Recognition"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"Text4Vis (CLIP ViT-L/14)","rank_in_archive_order":30,"of":207,"metrics":{"Acc@1":"87.8","Acc@5":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-activitynet","task":"Action Recognition","dataset":"ActivityNet","model":"Text4Vis (w/ ViT-L)","rank_in_archive_order":1,"of":16,"metrics":{"mAP":"96.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-ucf101","task":"Action Recognition","dataset":"UCF101","model":"Text4Vis","rank_in_archive_order":11,"of":91,"metrics":{"3-fold Accuracy":"98.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-activitynet","task":"Zero-Shot Action Recognition","dataset":"ActivityNet","model":"Text4Vis","rank_in_archive_order":2,"of":5,"metrics":{"Top-1 Accuracy":"84.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-hmdb51","task":"Zero-Shot Action Recognition","dataset":"HMDB51","model":"Text4Vis","rank_in_archive_order":7,"of":29,"metrics":{"Top-1 Accuracy":"58.4"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-kinetics","task":"Zero-Shot Action Recognition","dataset":"Kinetics","model":"Text4Vis","rank_in_archive_order":7,"of":20,"metrics":{"Top-1 Accuracy":"68.9","Top-5 Accuracy":"90.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset":"UCF101","model":"Text4Vis","rank_in_archive_order":6,"of":35,"metrics":{"Top-1 Accuracy":"85.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.01297","atlas_url":"https://app.syntology.ai/?focus=2207.01297","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":"2207.01297"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2207.01297\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2207.01297"},"call":"get_concepts_for_paper(arxiv_id=\"2207.01297\")"}],"by_repo":[{"repo":"whwu95/text4vis","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2024.findings-acl.747"],"harvested_for_calls":[]},{"repo":"whwu95/ATM","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2307.08908"],"harvested_for_calls":[{"arxiv_id":"2307.08908","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2307.08908"},"call":"get_harvested_code_for_paper(arxiv_id=\"2307.08908\")"}]},{"repo":"whwu95/BIKE","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.00184"],"harvested_for_calls":[{"arxiv_id":"2301.00184","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.00184"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.00184\")"}]},{"repo":"whwu95/Cap4Video","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.00184"],"harvested_for_calls":[{"arxiv_id":"2301.00184","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.00184"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.00184\")"}]},{"repo":"whwu95/GPT4Vis","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2311.15732"],"harvested_for_calls":[{"arxiv_id":"2311.15732","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.15732"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.15732\")"}]}],"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":"6da1fbefdbfdb1feac42ce7c8092ac4de0fc19a40c2886740d8567cbd64660b9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}