</> Code with Papers by Syntology

Papers › Efficient Two-Step Networks for Temporal Action Segmentation

Efficient Two-Step Networks for Temporal Action Segmentation

30 Apr 2021Neurocomputing 2021 4archive 2025-07-28

Yunheng Li, Zhuben Dong, Kaiyuan Liu, Lin Feng, Lianyu Hu, Jie Zhu, Li Xu, YuHan Wang, Shenglan Liu

Due to boundary ambiguity and over-segmentation issues, identifying all the frames in long untrimmed videos is still challenging. To address these problems, we present the Efficient Two-Step Network (ETSN) with two components. The first step of ETSN is Efficient Temporal Series Pyramid Networks (ETSPNet) that capture both local and global frame-level features and provide accurate predictions of segmentation boundaries. The second step is a novel unsupervised approach called Local Burr Suppression (LBS), which significantly reduces the over-segmentation errors. Our empirical evaluations on the benchmarks including 50Salads, GTEA and Breakfast dataset demonstrate that ETSN outperforms the current state-of-the-art methods by a large margin.

PaperPDFCode

Code

lyhisme/ETSN officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action SegmentationSegmentationTemporal Action SegmentationVocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation 50 Salads ETSN Acc 82.0 #16 of 28 Archive leaderboard report
Action Segmentation 50 Salads ETSN Edit 78.8 #16 of 28 Archive leaderboard report
Action Segmentation 50 Salads ETSN F1@10% 85.2 #16 of 28 Archive leaderboard report
Action Segmentation 50 Salads ETSN F1@25% 83.9 #16 of 28 Archive leaderboard report
Action Segmentation 50 Salads ETSN F1@50% 75.4 #16 of 28 Archive leaderboard report
Action Segmentation Breakfast ETSN Acc 67.8 #19 of 37 Archive leaderboard report
Action Segmentation Breakfast ETSN Average F1 66.4 #19 of 37 Archive leaderboard report
Action Segmentation Breakfast ETSN Edit 70.3 #19 of 37 Archive leaderboard report
Action Segmentation Breakfast ETSN F1@10% 74.0 #19 of 37 Archive leaderboard report
Action Segmentation Breakfast ETSN F1@25% 69.0 #19 of 37 Archive leaderboard report
Action Segmentation Breakfast ETSN F1@50% 56.2 #19 of 37 Archive leaderboard report
Action Segmentation GTEA ETSN Acc 78.2 #14 of 28 Archive leaderboard report
Action Segmentation GTEA ETSN Edit 86.2 #14 of 28 Archive leaderboard report
Action Segmentation GTEA ETSN F1@10% 91.1 #14 of 28 Archive leaderboard report
Action Segmentation GTEA ETSN F1@25% 90.0 #14 of 28 Archive leaderboard report
Action Segmentation GTEA ETSN F1@50% 77.9 #14 of 28 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections