{"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/tall-temporal-activity-localization-via","title":"TALL: Temporal Activity Localization via Language Query","arxiv_id":"1705.02101","date":"2017-05-05","proceeding":"ICCV 2017 10","authors":["Jiyang Gao","Chen Sun","Zhenheng Yang","Ram Nevatia"],"abstract":"This paper focuses on temporal localization of actions in untrimmed videos.\nExisting methods typically train classifiers for a pre-defined list of actions\nand apply them in a sliding window fashion. However, activities in the wild\nconsist of a wide combination of actors, actions and objects; it is difficult\nto design a proper activity list that meets users' needs. We propose to\nlocalize activities by natural language queries. Temporal Activity Localization\nvia Language (TALL) is challenging as it requires: (1) suitable design of text\nand video representations to allow cross-modal matching of actions and language\nqueries; (2) ability to locate actions accurately given features from sliding\nwindows of limited granularity. We propose a novel Cross-modal Temporal\nRegression Localizer (CTRL) to jointly model text query and video clips, output\nalignment scores and action boundary regression results for candidate clips.\nFor evaluation, we adopt TaCoS dataset, and build a new dataset for this task\non top of Charades by adding sentence temporal annotations, called\nCharades-STA. We also build complex sentence queries in Charades-STA for test.\nExperimental results show that CTRL outperforms previous methods significantly\non both datasets.","url_abs":"http://arxiv.org/abs/1705.02101v2","url_pdf":"http://arxiv.org/pdf/1705.02101v2.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":"tall-temporal-activity-localization-via","repo_url":"https://github.com/jiyanggao/TALL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/WuJie1010/TSP-PRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/WuJie1010/Temporally-language-grounding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/mrsalehi/ground-sentence-video","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/runzhouge/MAC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/tencentarc/umt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/yeliudev/R2-Tuning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/2023-MindSpore-1/ms-code-217/tree/main/tall","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/2023-MindSpore-1/ms-code-7/tree/main/tall","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/MindSpore-paper-code-2/code3/tree/main/tall","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/kingcong/tall","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"tall-temporal-activity-localization-via","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/tall","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[{"slug":"charades-sta","name":"Charades-STA","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.02101","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}