Temporal Rate Reduction Clustering for Human Motion Segmentation

💥 News 💥

[2025.6.26] Our paper is accepted by ICCV 2025! The paper is now accessible at arXiv.

👀 About TR2C

$\text{TR}^2\text{C}$ jointly learns structured representations and affinity to segment the frame sequences in video. Specifically, the structured representations learned by $\text{TR}^2\text{C}$ maintain temporally consistent and align well with a Union-of-Subspaces structure, which is favorable for the Human Motion Segmentation task.

# Run on Weizmann dataset
python train.py --data weiz

# Run on Keck dataset
python train.py --data keck

# Run on UT dataset
python train.py --data ut

# Run on MAD dataset
python train.py --data mad

# Run on YouTube dataset
python train.py --data youtube

📜 License

Our code is distributed under the CC BY-NC 4.0 license.