Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913907842482176 |
|---|---|
| author | Aganian, Dustin Franze, Erik Eisenbach, Markus Gross, Horst-Michael |
| author_facet | Aganian, Dustin Franze, Erik Eisenbach, Markus Gross, Horst-Michael |
| contents | Effective human action recognition is widely used for cobots in Industry 4.0 to assist in assembly tasks. However, conventional skeleton-based methods often lose keypoint semantics, limiting their effectiveness in complex interactions. In this work, we introduce a novel approach to skeleton-based action recognition that enriches input representations by leveraging word embeddings to encode semantic information. Our method replaces one-hot encodings with semantic volumes, enabling the model to capture meaningful relationships between joints and objects. Through extensive experiments on multiple assembly datasets, we demonstrate that our approach significantly improves classification performance, and enhances generalization capabilities by simultaneously supporting different skeleton types and object classes. Our findings highlight the potential of incorporating semantic information to enhance skeleton-based action recognition in dynamic and diverse environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18721 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition Aganian, Dustin Franze, Erik Eisenbach, Markus Gross, Horst-Michael Computer Vision and Pattern Recognition Machine Learning Robotics Effective human action recognition is widely used for cobots in Industry 4.0 to assist in assembly tasks. However, conventional skeleton-based methods often lose keypoint semantics, limiting their effectiveness in complex interactions. In this work, we introduce a novel approach to skeleton-based action recognition that enriches input representations by leveraging word embeddings to encode semantic information. Our method replaces one-hot encodings with semantic volumes, enabling the model to capture meaningful relationships between joints and objects. Through extensive experiments on multiple assembly datasets, we demonstrate that our approach significantly improves classification performance, and enhances generalization capabilities by simultaneously supporting different skeleton types and object classes. Our findings highlight the potential of incorporating semantic information to enhance skeleton-based action recognition in dynamic and diverse environments. |
| title | Including Semantic Information via Word Embeddings for Skeleton-based Action Recognition |
| topic | Computer Vision and Pattern Recognition Machine Learning Robotics |
| url | https://arxiv.org/abs/2506.18721 |