{"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/enriching-local-and-global-contexts-for","title":"Enriching Local and Global Contexts for Temporal Action Localization","arxiv_id":"2107.12960","date":"2021-07-27","proceeding":"ICCV 2021 10","authors":["Zixin Zhu","Wei Tang","Le Wang","Nanning Zheng","Gang Hua"],"abstract":"Effectively tackling the problem of temporal action localization (TAL) necessitates a visual representation that jointly pursues two confounding goals, i.e., fine-grained discrimination for temporal localization and sufficient visual invariance for action classification. We address this challenge by enriching both the local and global contexts in the popular two-stage temporal localization framework, where action proposals are first generated followed by action classification and temporal boundary regression. Our proposed model, dubbed ContextLoc, can be divided into three sub-networks: L-Net, G-Net and P-Net. L-Net enriches the local context via fine-grained modeling of snippet-level features, which is formulated as a query-and-retrieval process. G-Net enriches the global context via higher-level modeling of the video-level representation. In addition, we introduce a novel context adaptation module to adapt the global context to different proposals. P-Net further models the context-aware inter-proposal relations. We explore two existing models to be the P-Net in our experiments. The efficacy of our proposed method is validated by experimental results on the THUMOS14 (54.3\\% at tIoU@0.5) and ActivityNet v1.3 (56.01\\% at tIoU@0.5) datasets, which outperforms recent states of the art. Code is available at https://github.com/buxiangzhiren/ContextLoc.","url_abs":"https://arxiv.org/abs/2107.12960v2","url_pdf":"https://arxiv.org/pdf/2107.12960v2.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":"enriching-local-and-global-contexts-for","repo_url":"https://github.com/buxiangzhiren/contextloc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.12960","atlas_url":"https://app.syntology.ai/?focus=2107.12960","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}