# Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation

arXiv: https://arxiv.org/abs/2410.06353 · HTML: https://mlsanity.com/paper/2410.06353/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 58 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 30 of 39)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Temporal Convolutional Networks for Action Segmentation and Detection](https://mlsanity.com/paper/1611.05267/) (2016)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [ASFormer: Transformer for Action Segmentation](https://mlsanity.com/paper/2110.08568/) (2021)
- [PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding](https://mlsanity.com/paper/1703.07475/) (2017)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [Alleviating Over-segmentation Errors by Detecting Action Boundaries](https://mlsanity.com/paper/2007.06866/) (2020)
- [Temporal Action Segmentation: An Analysis of Modern Techniques](https://mlsanity.com/paper/2210.10352/) (2022)
- [Diffusion Action Segmentation](https://mlsanity.com/paper/2303.17959/) (2023)
- [Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2206.13028/) (2022)
- [UnLoc: A Unified Framework for Video Localization Tasks](https://mlsanity.com/paper/2308.11062/) (2023)
- [Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation](https://mlsanity.com/paper/2209.00638/) (2022)
- [Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos](https://mlsanity.com/paper/2203.14104/) (2022)
- [Generative Action Description Prompts for Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.05318/) (2022)
- [Global2Local: Efficient Structure Search for Video Action Segmentation](https://mlsanity.com/paper/2101.00910/) (2021)
- [Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2211.02219/) (2022)
- [How Much Temporal Long-Term Context is Needed for Action Segmentation?](https://mlsanity.com/paper/2308.11358/) (2023)
- [Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2305.12398/) (2023)

## Built on by (most cited first, 2 of 2)

- [LaDy: Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal Modulation](https://mlsanity.com/paper/2603.24097/) (2026)
- [Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation](https://mlsanity.com/paper/2603.24134/) (2026)

## Abstract (arXiv)

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.