DiffAct++: Diffusion Action Segmentation

D Liu, Q Li, AD Dinh, T Jiang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Understanding long-form videos requires precise temporal action segmentation. While
existing studies typically employ multi-stage models that follow an iterative refinement …

Resfusion: Prior Residual Noise embedded Denoising Diffusion Probabilistic Models

S Zhenning, D Changsheng, P Bin, X Xueshuo… - arxiv preprint arxiv …, 2023 - arxiv.org
Recently, Denoising Diffusion Probabilistic Models have been widely used in image
segmentation, by generating segmentation masks conditioned on the input image. However …

Multi-feature and Multi-branch Action Segmentation Framework for Modeling Long-Short-Term Dependencies

J Hong, Y Long, Y Luo, Q Qi… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Pioneer efforts have been dedicated to action segmentation that predicts what step is
occurring in a video frame. Existing studies focus on improving the accuracy of video …

ResEnsemble-DDPM: Residual Denoising Diffusion Probabilistic Models for Ensemble Learning

S Zhenning, D Changsheng, X Xueshuo, P Bin… - arxiv preprint arxiv …, 2023 - arxiv.org
Nowadays, denoising diffusion probabilistic models have been adapted for many image
segmentation tasks. However, existing end-to-end models have already demonstrated …