{"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/tricornet-a-hybrid-temporal-convolutional-and","title":"TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation","arxiv_id":"1705.07818","date":"2017-05-22","proceeding":null,"authors":["Li Ding","Chenliang Xu"],"abstract":"Action segmentation as a milestone towards building automatic systems to\nunderstand untrimmed videos has received considerable attention in the recent\nyears. It is typically being modeled as a sequence labeling problem but\ncontains intrinsic and sufficient differences than text parsing or speech\nprocessing. In this paper, we introduce a novel hybrid temporal convolutional\nand recurrent network (TricorNet), which has an encoder-decoder architecture:\nthe encoder consists of a hierarchy of temporal convolutional kernels that\ncapture the local motion changes of different actions; the decoder is a\nhierarchy of recurrent neural networks that are able to learn and memorize\nlong-term action dependencies after the encoding stage. Our model is simple but\nextremely effective in terms of video sequence labeling. The experimental\nresults on three public action segmentation datasets have shown that the\nproposed model achieves superior performance over the state of the art.","url_abs":"http://arxiv.org/abs/1705.07818v1","url_pdf":"http://arxiv.org/pdf/1705.07818v1.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":[],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-jigsaws","task":"Action Segmentation","dataset":"JIGSAWS","model":"TricorNet","rank_in_archive_order":4,"of":7,"metrics":{"Accuracy":"82.9","Edit Distance":"86.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.07818","atlas_url":"https://app.syntology.ai/?focus=1705.07818","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}