{"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/temporal-convolutional-networks-a-unified","title":"Temporal Convolutional Networks: A Unified Approach to Action Segmentation","arxiv_id":"1608.08242","date":"2016-08-29","proceeding":null,"authors":["Colin Lea","Rene Vidal","Austin Reiter","Gregory D. Hager"],"abstract":"The dominant paradigm for video-based action segmentation is composed of two\nsteps: first, for each frame, compute low-level features using Dense\nTrajectories or a Convolutional Neural Network that encode spatiotemporal\ninformation locally, and second, input these features into a classifier that\ncaptures high-level temporal relationships, such as a Recurrent Neural Network\n(RNN). While often effective, this decoupling requires specifying two separate\nmodels, each with their own complexities, and prevents capturing more nuanced\nlong-range spatiotemporal relationships. We propose a unified approach, as\ndemonstrated by our Temporal Convolutional Network (TCN), that hierarchically\ncaptures relationships at low-, intermediate-, and high-level time-scales. Our\nmodel achieves superior or competitive performance using video or sensor data\non three public action segmentation datasets and can be trained in a fraction\nof the time it takes to train an RNN.","url_abs":"http://arxiv.org/abs/1608.08242v1","url_pdf":"http://arxiv.org/pdf/1608.08242v1.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":"temporal-convolutional-networks-a-unified","repo_url":"https://github.com/Around-30/Kaggle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-jigsaws","task":"Action Segmentation","dataset":"JIGSAWS","model":"TCN","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy":"81.4","Edit Distance":"83.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1608.08242","atlas_url":"https://app.syntology.ai/?focus=1608.08242","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}