Saved in:
Bibliographic Details
Main Authors: Meng, Xianghan, Tong, Zhengyu, Huang, Zhiyuan, Li, Chun-Guang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21249
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915436395757568
author Meng, Xianghan
Tong, Zhengyu
Huang, Zhiyuan
Li, Chun-Guang
author_facet Meng, Xianghan
Tong, Zhengyu
Huang, Zhiyuan
Li, Chun-Guang
contents Human Motion Segmentation (HMS), which aims to partition videos into non-overlapping human motions, has attracted increasing research attention recently. Existing approaches for HMS are mainly dominated by subspace clustering methods, which are grounded on the assumption that high-dimensional temporal data align with a Union-of-Subspaces (UoS) distribution. However, the frames in video capturing complex human motions with cluttered backgrounds may not align well with the UoS distribution. In this paper, we propose a novel approach for HMS, named Temporal Rate Reduction Clustering ($\text{TR}^2\text{C}$), which jointly learns structured representations and affinity to segment the sequences of frames in video. Specifically, the structured representations learned by $\text{TR}^2\text{C}$ enjoy temporally consistency and are aligned well with a UoS structure, which is favorable for addressing the HMS task. We conduct extensive experiments on five benchmark HMS datasets and achieve state-of-the-art performances with different feature extractors. The code is available at: https://github.com/mengxianghan123/TR2C.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21249
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Temporal Rate Reduction Clustering for Human Motion Segmentation
Meng, Xianghan
Tong, Zhengyu
Huang, Zhiyuan
Li, Chun-Guang
Computer Vision and Pattern Recognition
Human Motion Segmentation (HMS), which aims to partition videos into non-overlapping human motions, has attracted increasing research attention recently. Existing approaches for HMS are mainly dominated by subspace clustering methods, which are grounded on the assumption that high-dimensional temporal data align with a Union-of-Subspaces (UoS) distribution. However, the frames in video capturing complex human motions with cluttered backgrounds may not align well with the UoS distribution. In this paper, we propose a novel approach for HMS, named Temporal Rate Reduction Clustering ($\text{TR}^2\text{C}$), which jointly learns structured representations and affinity to segment the sequences of frames in video. Specifically, the structured representations learned by $\text{TR}^2\text{C}$ enjoy temporally consistency and are aligned well with a UoS structure, which is favorable for addressing the HMS task. We conduct extensive experiments on five benchmark HMS datasets and achieve state-of-the-art performances with different feature extractors. The code is available at: https://github.com/mengxianghan123/TR2C.
title Temporal Rate Reduction Clustering for Human Motion Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.21249