Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation
About
Skeleton-based Temporal Action Segmentation involves the dense action classification of variable-length skeleton sequences. Current approaches primarily apply graph-based networks to extract framewise, whole-body-level motion representations, and use one-hot encoded labels for model optimization. However, whole-body motion representations do not capture fine-grained part-level motion representations and the one-hot encoded labels neglect the intrinsic semantic relationships within the language-based action definitions. To address these limitations, we propose a novel method named Language-assisted Human Part Motion Representation Learning (LPL), which contains a Disentangled Part Motion Encoder (DPE) to extract dual-level (i.e., part and whole-body) motion representations and a Language-assisted Distribution Alignment (LDA) strategy for optimizing spatial relations within representations. Specifically, after part-aware skeleton encoding via DPE, LDA generates dual-level action descriptions to construct a textual embedding space with the help of a large-scale language model. Then, LDA motivates the alignment of the embedding space between text descriptions and motions. This alignment allows LDA not only to enhance intra-class compactness but also to transfer the language-encoded semantic correlations among actions to skeleton-based motion learning. Moreover, we propose a simple yet efficient Semantic Offset Adapter to smooth the cross-domain misalignment. Our experiments indicate that LPL achieves state-of-the-art performance across various datasets (e.g., +4.4\% Accuracy, +5.6\% F1 on the PKU-MMD dataset). Moreover, LDA is compatible with existing methods and improves their performance (e.g., +4.8\% Accuracy, +4.3\% F1 on the LARa dataset) without additional inference costs.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Skeleton-based Temporal Action Segmentation | PKU-MMD (X-sub) | Accuracy74.7 | 35 | |
| Temporal action segmentation | LARa | Accuracy76.1 | 26 | |
| Temporal action segmentation | TCG-15 | Accuracy88.8 | 25 | |
| Skeleton-based Temporal Action Segmentation | PKU-MMD (X-view) | Accuracy70 | 21 | |
| Temporal action segmentation | PKU-MMD X-view v2 | Accuracy70 | 13 |