6 papers
Fine-grained text-driven dual-human motion generation via dynamic hierarchical interaction
Mu Li, Yin Wang, Zhiying Leng +3
Human interaction is inherently dynamic and hierarchical, where the dynamic refers to the motion changes with distance, and the hierarchy is from individual to inter-individual and…
Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization
Kanglei Zhou, Qingyi Pan, Xingxing Zhang +4
Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the n…
Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks
Yue Ma, Kanglei Zhou, Fuyang Yu +2
3D human motion forecasting aims to enable autonomous applications. Estimating uncertainty for each prediction (i.e., confidence based on probability density or quantile) is essent…
PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction
Kanglei Zhou, Hubert P. H. Shum, Frederick W. B. Li +2
Long-term Action Quality Assessment (AQA) aims to evaluate the quantitative performance of actions in long videos. However, existing methods face challenges due to domain shifts be…
FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment
Ruisheng Han, Kanglei Zhou, Amir Atapour-Abarghouei +2
Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep le…
Adaptive Score Alignment Learning for Continual Perceptual Quality Assessment of 360-Degree Videos in Virtual Reality
Kanglei Zhou, Zikai Hao, Liyuan Wang +1
Virtual Reality Video Quality Assessment (VR-VQA) aims to evaluate the perceptual quality of 360-degree videos, which is crucial for ensuring a distortion-free user experience. Tra…