Papers › Improving Action Segmentation via Graph-Based Temporal Reasoning

Improving Action Segmentation via Graph-Based Temporal Reasoning

1 Jun 2020CVPR 2020 6archive 2025-07-28

Yifei Huang, Yusuke Sugano, Yoichi Sato

Temporal relations among multiple action segments play an important role in action segmentation especially when observations are limited (e.g., actions are occluded by other objects or happen outside a field of view). In this paper, we propose a network module called Graph-based Temporal Reasoning Module (GTRM) that can be built on top of existing action segmentation models to learn the relation of multiple action segments in various time spans. We model the relations by using two Graph Convolution Networks (GCNs) where each node represents an action segment. The two graphs have different edge properties to account for boundary regression and classification tasks, respectively. By applying graph convolution, we can update each node's representation based on its relation with neighboring nodes. The updated representation is then used for improved action segmentation. We evaluate our model on the challenging egocentric datasets namely EGTEA and EPIC-Kitchens, where actions may be partially observed due to the viewpoint restriction. The results show that our proposed GTRM outperforms state-of-the-art action segmentation models by a large margin. We also demonstrate the effectiveness of our model on two third-person video datasets, the 50Salads dataset and the Breakfast dataset.

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 SegmentationSegmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Segmentation Breakfast GTRM Acc 65.0 #29 of 37 Archive leaderboard report
Action Segmentation Breakfast GTRM Average F1 51.6 #29 of 37 Archive leaderboard report
Action Segmentation Breakfast GTRM Edit 58.7 #29 of 37 Archive leaderboard report
Action Segmentation Breakfast GTRM F1@10% 57.5 #29 of 37 Archive leaderboard report
Action Segmentation Breakfast GTRM F1@25% 54.0 #29 of 37 Archive leaderboard report
Action Segmentation Breakfast GTRM F1@50% 43.3 #29 of 37 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.

Methods

Convolution

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