{"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/actionclip-a-new-paradigm-for-video-action","title":"ActionCLIP: A New Paradigm for Video Action Recognition","arxiv_id":"2109.08472","date":"2021-09-17","proceeding":null,"authors":["Mengmeng Wang","Jiazheng Xing","Yong liu"],"abstract":"The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new datasets with unseen concepts. In this paper, we provide a new perspective on action recognition by attaching importance to the semantic information of label texts rather than simply mapping them into numbers. Specifically, we model this task as a video-text matching problem within a multimodal learning framework, which strengthens the video representation with more semantic language supervision and enables our model to do zero-shot action recognition without any further labeled data or parameters requirements. Moreover, to handle the deficiency of label texts and make use of tremendous web data, we propose a new paradigm based on this multimodal learning framework for action recognition, which we dub \"pre-train, prompt and fine-tune\". This paradigm first learns powerful representations from pre-training on a large amount of web image-text or video-text data. Then it makes the action recognition task to act more like pre-training problems via prompt engineering. Finally, it end-to-end fine-tunes on target datasets to obtain strong performance. We give an instantiation of the new paradigm, ActionCLIP, which not only has superior and flexible zero-shot/few-shot transfer ability but also reaches a top performance on general action recognition task, achieving 83.8% top-1 accuracy on Kinetics-400 with a ViT-B/16 as the backbone. Code is available at https://github.com/sallymmx/ActionCLIP.git","url_abs":"https://arxiv.org/abs/2109.08472v1","url_pdf":"https://arxiv.org/pdf/2109.08472v1.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":"actionclip-a-new-paradigm-for-video-action","repo_url":"https://github.com/sallymmx/actionclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"actionclip-a-new-paradigm-for-video-action","repo_url":"https://github.com/towhee-io/towhee","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":"prompt-engineering","task_name":"Prompt Engineering"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-charades","task":"Action Classification","dataset":"Charades","model":"ActionCLIP (ViT-B/16)","rank_in_archive_order":20,"of":49,"metrics":{"MAP":"44.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-classification-on-kinetics-400","task":"Action Classification","dataset":"Kinetics-400","model":"ActionCLIP (CLIP-pretrained)","rank_in_archive_order":65,"of":207,"metrics":{"Acc@1":"83.8","Acc@5":"97.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-recognition-in-videos-on-kinetics-400-1","task":"Action Recognition In Videos","dataset":"Kinetics-400","model":"ActionCLIP (ViT-B/16)","rank_in_archive_order":2,"of":3,"metrics":{"Top-1 Accuracy":"83.8"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.08472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.08472"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/sallymmx/actionclip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/towhee-io/towhee","reach":null}],"summary":{"ran_draft_wrong":4,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"98f385d847636a3e","entry":"basic_clean","repo":"sallymmx/actionclip","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"3ac6b7d76e8e3584","entry":"drop_path","repo":"sallymmx/actionclip","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ac6b7d76e8e3584"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"sallymmx/actionclip","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"5cb5985f521b3573","entry":"trunc_normal_","repo":"sallymmx/actionclip","repo_kind":"official","path":"modules/Visual_Prompt.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/modules/Visual_Prompt.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cb5985f521b3573"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"sallymmx/actionclip","repo_kind":"official","path":"clip/simple_tokenizer.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"32ddc30d944082d7","entry":"build_model","repo":"sallymmx/actionclip","repo_kind":"official","path":"clip/model.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32ddc30d944082d7"}},{"code_sha256_prefix":"05e54562ede2ec25","entry":"get_augmentation","repo":"sallymmx/actionclip","repo_kind":"official","path":"utils/Augmentation.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/utils/Augmentation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05e54562ede2ec25"}},{"code_sha256_prefix":"64716f16ca4d4f3e","entry":"get_model_path","repo":"sallymmx/actionclip","repo_kind":"official","path":"clip/model_zoo.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/model_zoo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64716f16ca4d4f3e"}},{"code_sha256_prefix":"709707cd7d31c7f4","entry":"load","repo":"sallymmx/actionclip","repo_kind":"official","path":"clip/clip.py","file_url":"https://github.com/sallymmx/actionclip/blob/HEAD/clip/clip.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"709707cd7d31c7f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}