{"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/efficient-video-action-detection-with-token","title":"Efficient Video Action Detection with Token Dropout and Context Refinement","arxiv_id":"2304.08451","date":"2023-04-17","proceeding":"ICCV 2023 1","authors":["Lei Chen","Zhan Tong","Yibing Song","Gangshan Wu","LiMin Wang"],"abstract":"Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor identification. In this work, we propose an end-to-end framework for efficient video action detection (EVAD) based on vanilla ViTs. Our EVAD consists of two specialized designs for video action detection. First, we propose a spatiotemporal token dropout from a keyframe-centric perspective. In a video clip, we maintain all tokens from its keyframe, preserve tokens relevant to actor motions from other frames, and drop out the remaining tokens in this clip. Second, we refine scene context by leveraging remaining tokens for better recognizing actor identities. The region of interest (RoI) in our action detector is expanded into temporal domain. The captured spatiotemporal actor identity representations are refined via scene context in a decoder with the attention mechanism. These two designs make our EVAD efficient while maintaining accuracy, which is validated on three benchmark datasets (i.e., AVA, UCF101-24, JHMDB). Compared to the vanilla ViT backbone, our EVAD reduces the overall GFLOPs by 43% and improves real-time inference speed by 40% with no performance degradation. Moreover, even at similar computational costs, our EVAD can improve the performance by 1.1 mAP with higher resolution inputs. Code is available at https://github.com/MCG-NJU/EVAD.","url_abs":"https://arxiv.org/abs/2304.08451v3","url_pdf":"https://arxiv.org/pdf/2304.08451v3.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":"efficient-video-action-detection-with-token","repo_url":"https://github.com/mcg-nju/evad","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"efficient-video-action-detection-with-token","repo_url":"https://github.com/MCG-NJU/VideoMAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"video-action-detection","task_name":"Video Action Detection"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.08451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08451"}},"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":"deterministic:regex_extraction","url":"https://github.com/MCG-NJU/EVAD","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"f1ba368c5af15b64","entry":"DropPath","repo":"MCG-NJU/EVAD","repo_kind":"official","path":"projects/evad/models/vit_model.py","file_url":"https://github.com/MCG-NJU/EVAD/blob/HEAD/projects/evad/models/vit_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f1ba368c5af15b64"}},{"code_sha256_prefix":"0c40243389e69366","entry":"KTPAttention","repo":"MCG-NJU/EVAD","repo_kind":"official","path":"projects/evad/models/vit_model.py","file_url":"https://github.com/MCG-NJU/EVAD/blob/HEAD/projects/evad/models/vit_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0c40243389e69366"}},{"code_sha256_prefix":"3e41f5a8960a91c2","entry":"KTPBlock","repo":"MCG-NJU/EVAD","repo_kind":"official","path":"projects/evad/models/vit_model.py","file_url":"https://github.com/MCG-NJU/EVAD/blob/HEAD/projects/evad/models/vit_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3e41f5a8960a91c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}