# Consistency and Diversity induced Human Motion Segmentation

arXiv: https://arxiv.org/abs/2202.04861 · HTML: https://mlsanity.com/paper/2202.04861/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 79 references that are in the map.
- First posted on arXiv 10 Feb 2022.

## Builds on (most cited first, 15 of 15)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Simultaneous Deep Transfer Across Domains and Tasks](https://mlsanity.com/paper/1510.02192/) (2015)
- [Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning](https://mlsanity.com/paper/1806.06193/) (2018)
- [Deep Subspace Clustering Networks](https://mlsanity.com/paper/1709.02508/) (2017)
- [Robust and Efficient Subspace Segmentation via Least Squares Regression](https://mlsanity.com/paper/1404.6736/) (2014)
- [Joint Geometrical and Statistical Alignment for Visual Domain Adaptation](https://mlsanity.com/paper/1705.05498/) (2017)
- [Subspace Clustering by Block Diagonal Representation](https://mlsanity.com/paper/1805.09243/) (2018)
- [Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning](https://mlsanity.com/paper/1511.03476/) (2015)
- [A deep matrix factorization method for learning attribute representations](https://mlsanity.com/paper/1509.03248/) (2015)
- [Deep Transfer Learning for Person Re-identification](https://mlsanity.com/paper/1611.05244/) (2016)
- [Approximating Spectral Clustering via Sampling: a Review](https://mlsanity.com/paper/1901.10204/) (2019)

## Built on by (most cited first, 7 of 7)

- [Feature Aggregation and Propagation Network for Camouflaged Object Detection](https://mlsanity.com/paper/2212.00990/) (2022)
- [Block-Diagonal Guided DBSCAN Clustering](https://mlsanity.com/paper/2404.01341/) (2024)
- [Exploring the Robustness of Human Parsers Towards Common Corruptions](https://mlsanity.com/paper/2309.00938/) (2023)
- [Temporal Rate Reduction Clustering for Human Motion Segmentation](https://mlsanity.com/paper/2506.21249/) (2025)
- [Temporal Visual Semantics-Induced Human Motion Understanding with Large Language Models](https://mlsanity.com/paper/2512.22249/) (2025)
- [MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images](https://mlsanity.com/paper/2505.18741/) (2025)
- [Jointly Learning Structured Representations and Stabilized Affinity for Human Motion Segmentation](https://mlsanity.com/paper/2605.05753/) (2026)

## Abstract (arXiv)

Subspace clustering is a classical technique that has been widely used for human motion segmentation and other related tasks. However, existing segmentation methods often cluster data without guidance from prior knowledge, resulting in unsatisfactory segmentation results. To this end, we propose a novel Consistency and Diversity induced human Motion Segmentation (CDMS) algorithm. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces, in which transfer subspace learning is conducted on different layers to capture multi-level information. A multi-mutual consistency learning strategy is carried out to reduce the domain gap between the source and target data. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance. Moreover, to preserve the temporal correlations, an enhanced graph regularizer is imposed on the learned representation coefficients and the multi-level representations of the source data. The proposed model can be efficiently solved using the Alternating Direction Method of Multipliers (ADMM) algorithm. Extensive experimental results on public human motion datasets demonstrate the effectiveness of our method against several state-of-the-art approaches.