Temporal Rate Reduction Clustering for Human Motion Segmentation
Not on the map. Why?
Abstract (arXiv)
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 (TR2C), which jointly learns structured representations and affinity to segment the sequences of frames in video. Specifically, the structured representations learned by TR2C 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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 70 references that are in the map. First posted on arXiv 26 Jun 2025.
Builds on
28 of 70 references.
References · 28
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2020Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reductioncited by 141
- 2015Unsupervised Learning from Narrated Instruction Videoscited by 116
- 2022Temporal Action Segmentation: An Analysis of Modern Techniquescited by 85
- 2019Unsupervised learning of action classes with continuous temporal embeddingcited by 75
- 2021Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentationcited by 58
- 2014Robust and Efficient Subspace Segmentation via Least Squares Regressioncited by 47
- 2022Neural Manifold Clustering and Embeddingcited by 44
16 more
- 2016Oracle Based Active Set Algorithm for Scalable Elastic Net Subspace Clusteringcited by 40
- 2018A Perceptual Prediction Framework for Self Supervised Event Segmentationcited by 40
- 2024Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentationcited by 37
- 2022Self-Supervised Learning via Maximum Entropy Codingcited by 33
- 2016Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Frameworkcited by 26
- 2021Learning a Self-Expressive Network for Subspace Clusteringcited by 24
- 2023Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Modelscited by 22
- 2020A Critique of Self-Expressive Deep Subspace Clusteringcited by 18
- 2024Hierarchical Vector Quantization for Unsupervised Action Segmentationcited by 18
- 2024A Global Geometric Analysis of Maximal Coding Rate Reductioncited by 13
- 2023Unsupervised Manifold Linearizing and Clusteringcited by 12
- 2021CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentationcited by 7
- 2022Consistency and Diversity induced Human Motion Segmentationcited by 7
- 2025Exploring a Principled Framework for Deep Subspace Clusteringcited by 7
- 2021Graph Constrained Data Representation Learning for Human Motion Segmentationcited by 4
- 2019Enhancing temporal segmentation by nonlocal self-similaritycited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.