{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/ms-tcn-multi-stage-temporal-convolutional-2","title":"MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation","arxiv_id":"2006.09220","date":"2020-06-16","proceeding":null,"authors":["Shijie Li","Yazan Abu Farha","Yun Liu","Ming-Ming Cheng","Juergen Gall"],"abstract":"With the success of deep learning in classifying short trimmed videos, more attention has been focused on temporally segmenting and classifying activities in long untrimmed videos. State-of-the-art approaches for action segmentation utilize several layers of temporal convolution and temporal pooling. Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors. In this paper, we propose a multi-stage architecture for the temporal action segmentation task that overcomes the limitations of the previous approaches. The first stage generates an initial prediction that is refined by the next ones. In each stage we stack several layers of dilated temporal convolutions covering a large receptive field with few parameters. While this architecture already performs well, lower layers still suffer from a small receptive field. To address this limitation, we propose a dual dilated layer that combines both large and small receptive fields. We further decouple the design of the first stage from the refining stages to address the different requirements of these stages. Extensive evaluation shows the effectiveness of the proposed model in capturing long-range dependencies and recognizing action segments. Our models achieve state-of-the-art results on three datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset.","url_abs":"https://arxiv.org/abs/2006.09220v2","url_pdf":"https://arxiv.org/pdf/2006.09220v2.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":"ms-tcn-multi-stage-temporal-convolutional-2","repo_url":"https://github.com/sj-li/MS-TCN2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"MS-TCN++","rank_in_archive_order":21,"of":28,"metrics":{"Acc":"83.7","Edit":"74.3","F1@10%":"80.7","F1@25%":"78.5","F1@50%":"70.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"MS-TCN++(sh)","rank_in_archive_order":23,"of":28,"metrics":{"Acc":" 82.2","Edit":"70.7","F1@10%":"78.7","F1@25%":"76.6","F1@50%":"68.3"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-assembly101","task":"Action Segmentation","dataset":"Assembly101","model":"MS-TCN++","rank_in_archive_order":6,"of":7,"metrics":{"Edit":"30.7","F1@10%":"31.6","F1@25%":"27.8","F1@50%":"20.6","MoF":"37.1"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"MS-TCN++ (I3D)","rank_in_archive_order":27,"of":37,"metrics":{"Acc":"67.6","Average F1":"56.2","Edit":"65.6","F1@10%":"64.1","F1@25%":"58.6","F1@50%":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"MS-TCN++(I3D) (sh)","rank_in_archive_order":28,"of":37,"metrics":{"Acc":"67.3","Average F1":"55.2","Edit":"64.9","F1@10%":"63.3","F1@25%":"57.7","F1@50%":"44.5"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"MS-TCN++","rank_in_archive_order":19,"of":28,"metrics":{"Acc":"80.1","Edit":"83.5","F1@10%":"88.8","F1@25%":"85.7","F1@50%":"76.0"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"MS-TCN++(sh)","rank_in_archive_order":20,"of":28,"metrics":{"Acc":"79.7","Edit":"83.0","F1@10%":"88.2","F1@25%":"86.2","F1@50%":"75.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.09220","atlas_url":"https://app.syntology.ai/?focus=2006.09220","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2006.09220"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.09220\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.09220"},"call":"get_concepts_for_paper(arxiv_id=\"2006.09220\")"}],"by_repo":[{"repo":"sj-li/MS-TCN2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"fce3670e83bc87ac08d4db9210386df379eb4032f1f1d498e9452abf3e06e856","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}