{"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/diagnosing-error-in-temporal-action-detectors","title":"Diagnosing Error in Temporal Action Detectors","arxiv_id":"1807.10706","date":"2018-07-27","proceeding":"ECCV 2018 9","authors":["Humam Alwassel","Fabian Caba Heilbron","Victor Escorcia","Bernard Ghanem"],"abstract":"Despite the recent progress in video understanding and the continuous rate of\nimprovement in temporal action localization throughout the years, it is still\nunclear how far (or close?) we are to solving the problem. To this end, we\nintroduce a new diagnostic tool to analyze the performance of temporal action\ndetectors in videos and compare different methods beyond a single scalar\nmetric. We exemplify the use of our tool by analyzing the performance of the\ntop rewarded entries in the latest ActivityNet action localization challenge.\nOur analysis shows that the most impactful areas to work on are: strategies to\nbetter handle temporal context around the instances, improving the robustness\nw.r.t. the instance absolute and relative size, and strategies to reduce the\nlocalization errors. Moreover, our experimental analysis finds the lack of\nagreement among annotator is not a major roadblock to attain progress in the\nfield. Our diagnostic tool is publicly available to keep fueling the minds of\nother researchers with additional insights about their algorithms.","url_abs":"http://arxiv.org/abs/1807.10706v1","url_pdf":"http://arxiv.org/pdf/1807.10706v1.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":"diagnosing-error-in-temporal-action-detectors","repo_url":"https://github.com/HumamAlwassel/DETAD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.10706","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}