Papers › Depthwise Separable Temporal Convolutional Network for Action Segmentation

Depthwise Separable Temporal Convolutional Network for Action Segmentation

19 Jan 20212020 International Conference on 3D Vision (3DV) 2021 1archive 2025-07-28

Basavaraj Hampiholi, Christian Jarvers, Wolfgang Mader, Heiko Neumann

Fine-grained temporal action segmentation in long, untrimmed RGB videos is a key topic in visual human- machine interaction. Recent temporal convolution based approaches either use encoder-decoder(ED) architecture or dilations with doubling factor in consecutive convolution layers to segment actions in videos. However ED networks operate on low temporal resolution and the dilations in suc- cessive layers cause gridding artifacts problem. We propose depthwise separable temporal convolution network (DS- TCN) that operates on full temporal resolution and with re- duced gridding effects. The basic component of DS-TCN is residual depthwise dilated block (RDDB). We explore the trade-off between large kernels and small dilation rates us- ing RDDB. We show that our DS-TCN is capable of captur- ing long-term dependencies as well as local temporal cues efficiently. Our evaluation on three benchmark datasets, GTEA, 50Salads, and Breakfast demonstrates that DS-TCN outperforms the existing ED-TCN and dilation based TCN baselines even with comparatively fewer parameters.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Action SegmentationDecoderTemporal Action Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation 50 Salads DS-TCN Acc 80.0 #26 of 28 Archive leaderboard report
Action Segmentation 50 Salads DS-TCN Edit 70.0 #26 of 28 Archive leaderboard report
Action Segmentation 50 Salads DS-TCN F1@10% 77.0 #26 of 28 Archive leaderboard report
Action Segmentation 50 Salads DS-TCN F1@25% 74.43 #26 of 28 Archive leaderboard report
Action Segmentation 50 Salads DS-TCN F1@50% 65.78 #26 of 28 Archive leaderboard report
Action Segmentation Breakfast DS-TCN Acc 70.75 #25 of 37 Archive leaderboard report
Action Segmentation Breakfast DS-TCN Average F1 59.6 #25 of 37 Archive leaderboard report
Action Segmentation Breakfast DS-TCN Edit 69.02 #25 of 37 Archive leaderboard report
Action Segmentation Breakfast DS-TCN F1@10% 67.70 #25 of 37 Archive leaderboard report
Action Segmentation Breakfast DS-TCN F1@25% 62.05 #25 of 37 Archive leaderboard report
Action Segmentation Breakfast DS-TCN F1@50% 49.18 #25 of 37 Archive leaderboard report
Action Segmentation GTEA DS-TCN Acc 78.10 #24 of 28 Archive leaderboard report
Action Segmentation GTEA DS-TCN Edit 84.05 #24 of 28 Archive leaderboard report
Action Segmentation GTEA DS-TCN F1@10% 88.30 #24 of 28 Archive leaderboard report
Action Segmentation GTEA DS-TCN F1@25% 85.44 #24 of 28 Archive leaderboard report
Action Segmentation GTEA DS-TCN F1@50% 72.84 #24 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