Temporal Rate Reduction Clustering for Human Motion Segmentation
This work addresses human motion segmentation for video analysis, presenting an incremental improvement over existing subspace clustering methods.
The paper tackles the problem of human motion segmentation in videos, where existing subspace clustering methods struggle with complex motions and cluttered backgrounds, by proposing Temporal Rate Reduction Clustering (TR²C) that jointly learns structured representations and affinity, achieving state-of-the-art performance on five benchmark datasets.
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.