{"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/efficient-temporal-action-segmentation-via","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","arxiv_id":"2405.15995","date":"2024-05-25","proceeding":null,"authors":["Peiyao Wang","Yuewei Lin","Erik Blasch","Jie Wei","Haibin Ling"],"abstract":"Although the performance of Temporal Action Segmentation (TAS) has improved in recent years, achieving promising results often comes with a high computational cost due to dense inputs, complex model structures, and resource-intensive post-processing requirements. To improve the efficiency while keeping the performance, we present a novel perspective centered on per-segment classification. By harnessing the capabilities of Transformers, we tokenize each video segment as an instance token, endowed with intrinsic instance segmentation. To realize efficient action segmentation, we introduce BaFormer, a boundary-aware Transformer network. It employs instance queries for instance segmentation and a global query for class-agnostic boundary prediction, yielding continuous segment proposals. During inference, BaFormer employs a simple yet effective voting strategy to classify boundary-wise segments based on instance segmentation. Remarkably, as a single-stage approach, BaFormer significantly reduces the computational costs, utilizing only 6% of the running time compared to state-of-the-art method DiffAct, while producing better or comparable accuracy over several popular benchmarks. The code for this project is publicly available at https://github.com/peiyao-w/BaFormer.","url_abs":"https://arxiv.org/abs/2405.15995v1","url_pdf":"https://arxiv.org/pdf/2405.15995v1.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":"efficient-temporal-action-segmentation-via","repo_url":"https://github.com/peiyao-w/baformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-segmentation","task_name":"Action Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"temporal-action-segmentation","task_name":"Temporal Action Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-segmentation-on-50-salads-1","task":"Action Segmentation","dataset":"50 Salads","model":"BaFormer","rank_in_archive_order":3,"of":28,"metrics":{"Acc":"89.5","Edit":"84.2","F1@10%":"89.3","F1@25%":"88.4","F1@50%":"83.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-breakfast-1","task":"Action Segmentation","dataset":"Breakfast","model":"BaFormer","rank_in_archive_order":6,"of":37,"metrics":{"Acc":"76.6","Average F1":"72.4","Edit":"77.3","F1@10%":"79.2","F1@25%":"74.9","F1@50%":"63.2"},"uses_additional_data":false},{"leaderboard":"/sota/action-segmentation-on-gtea-1","task":"Action Segmentation","dataset":"GTEA","model":"BaFormer","rank_in_archive_order":4,"of":28,"metrics":{"Acc":"83.0","Edit":"88.7","F1@10%":"92.0","F1@25%":"91.3","F1@50%":"83.5"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}