Papers › Language-Assisted Skeleton Action Understanding for Skeleton-Based Temporal Action Segmentation

Language-Assisted Skeleton Action Understanding for Skeleton-Based Temporal Action Segmentation

31 Oct 2024European Conference on Computer Vision (ECCV2024) 2024 10archive 2025-07-28

Haoyu Ji, Bowen Chen, Xinglong Xu, Weihong Ren, Zhiyong Wang, Honghai Liu

Skeleton-based Temporal Action Segmentation (STAS) aims to densely segment and classify human actions in long, untrimmed skeletal motion sequences. Existing STAS methods primarily model spatial dependencies among joints and temporal relationships among frames to generate frame-level one-hot classifications. However, these methods overlook the deep mining of semantic relations among joints as well as actions at a linguistic level, which limits the comprehensiveness of skeleton action understanding. In this work, we propose a Language-assisted Skeleton Action Understanding (LaSA) method that leverages the language modality to assist in learning semantic relationships among joints and actions. Specifically, in terms of joint relationships, the Joint Relationships Establishment (JRE) module establishes correlations among joints in the feature sequence by applying attention between joint texts and differentiates distinct joints by embedding joint texts as positional embeddings. Regarding action relationships, the Action Relationships Supervision (ARS) module enhances the discrimination across action classes through contrastive learning of single-class action-text pairs and models the semantic associations of adjacent actions by contrasting mixed-class clip-text pairs. Performance evaluation on five public datasets demonstrates that LaSA achieves state-of-the-art results. Code is available at https://github.com/HaoyuJi/LaSA.

PaperPDFCode

Code

HaoyuJi/LaSA mentioned in paperpytorch 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 SegmentationAction UnderstandingContrastive LearningRepresentation LearningSkeleton Based Action RecognitionSkeleton Based Action SegmentationTemporal Action SegmentationVideo Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionContrastive LearningSoftmax

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