arrow
返回

Linguistic-Driven Partial Semantic Relevance Learning for Skeleton-Based Action Recognition

delete2024-07-26
delete0
delete
OA
AI
Q
Qixiu Chen
Y
Yingan Liu *
P
Peng Huang
J
Jiani Huang
DOI:10.3390/s24154860delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Skeleton-based action recognition, renowned for its computational efficiency and indifference to lighting variations, has become a focal point in the realm of motion analysis. However, most current methods typically only extract global skeleton features, overlooking the potential semantic relationships among various partial limb motions. For instance, the subtle differences between actions such as brush teeth and brush hair are mainly distinguished by specific elements. Although combining limb movements provides a more holistic representation of an action, relying solely on skeleton points proves inadequate for capturing these nuances. Therefore, integrating detailed linguistic descriptions into the learning process of skeleton features is essential. This motivates us to explore integrating fine-grained language descriptions into the learning process of skeleton features to capture more discriminative skeleton behavior representations. To this end, we introduce a new Linguistic-Driven Partial Semantic Relevance Learning framework (LPSR) in this work. While using state-of-the-art large language models to generate linguistic descriptions of local limb motions and further constrain the learning of local motions, we also aggregate global skeleton point representations and textual representations (which generated from an LLM) to obtain a more generalized cross-modal behavioral representation. On this basis, we propose a cyclic attentional interaction module to model the implicit correlations between partial limb motions. Numerous ablation experiments demonstrate the effectiveness of the method proposed in this paper, and our method also obtains state-of-the-art results.
Keyword:
skeleton-based action recognition
cross-modal
transformer
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Sensors 封面图
Sensors
IF:
3.5
论文数:
7.2W
被引数:
20.9W

机构

N
Nanjing Forestry University
学者数:
2.0W
论文数: 1.6W
被引数: 3.2W
引用论文

引用论文

err分享
err收藏
Evaluation of the Effect of Systolic Blood Pressure and Pulse Pressure on Cognitive Function: The Women's Health and Aging Study II
err2011-12-09
err0
errOAAI
errSevil Yasar; Jean Y. Ko; Stephanie Nothelle; Michelle M. Mielke; Michelle C. Carlson
err分享
err收藏
err分享
err收藏
Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks
err2018-04-01
err423
errOAAI
errLiu, Jun; Wang, Gang; Duan, Ling-Yu; Abdiyeva, Kamila; Kot, Alex C.
err分享
err收藏
学者 查看更多内容