Frederick W. B. Li

Uncertainty-aware calibrated 3D human motion forecasting with latent conformal prediction

Yue Ma, Frederick W. B. Li, Xiaohui Liang

cn, gb (code pays fourni par la source)

OctMamba: Mamba-based octree context entropy model for point cloud geometry compression

Zhaoyi Jiang, Yi Xu, Frederick W. B. Li, Gary K.L. Tam et autres

Existing learned point cloud compression frameworks face two major limitations: (1) they focus almost exclusively on spatial redundancy and (2) rely on architectures built around local-global transformers or global Mamba blocks. Transformers incur quadratic complexity, while global Mamba lacks the granularity to …

cn, gb (code pays fourni par la source)

Cross-Temporal 3D Gaussian Splatting for Sparse-View Guided Scene Update

Zhenghua An, Yongbiao Xiao, Zhiying Leng, Frederick W. B. Li et autres

Maintaining consistent 3D scene representations over time is a significant challenge in computer vision. Updating 3D scenes from sparse-view observations is crucial for various real-world applications, including urban planning, disaster assessment, and historical site preservation, where dense scans are often unavailable or …

Fine-grained text-driven dual-human motion generation via dynamic hierarchical interaction

Li Mu, Yin Wang, Zhiying Leng, Frederick W. B. Li et autres

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 ultimately to overall motion. Exploiting these properties is vital for dual-human motion generation, while existing methods …

Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization

Kanglei Zhou, Qingyi Pan, Xingxing Zhang, Hubert P. H. Shum et autres

Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation. A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios, which limits the generalization ability of conventional methods. We introduce …

Nurse-Coordinated Multidisciplinary Comprehensive Heart Failure Management Programme: A Propensity-Matched Trial

Polly W.C. Li, D Lee, Esmond Yan‐Hang Fong, Irene Oi‐Lin Ng et autres

AIMS: Despite therapeutic advancements, the prognosis of heart failure (HF) remains poor, with high rates of mortality and readmission, particularly following a HF exacerbation. This study aimed to evaluate the effects of a nurse-coordinated multidisciplinary comprehensive HF management programme on HF patients. …

cn, hk (code pays fourni par la source)

MECA-DETR：Multi-scale Edge-aware Contextual Attention DETR for UAV-based Small Object Detection

Yujie Zhao, Biao Li, Xuefeng Rao, Jiongming Lu et autres

cn (code pays fourni par la source)

Uncertainty-aware Probabilistic 3D Human Motion Forecasting via Invertible Networks

Yue Ma, Kanglei Zhou, Fuyang Yu, Frederick W. B. Li et autres

3D human motion forecasting aims to enable autonomous applications. Estimating uncertainty for each prediction (i.e., confidence based on probability density or quantile) is essential for safety-critical contexts like human-robot collaboration to minimize risks. However, existing diverse motion forecasting approaches struggle with uncertainty …

MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf Interaction

Zhiying Leng, Frederick W. B. Li, Xiaohui Liang

We introduce MOST, a novel MOtion diffuSion model via Temporal clip Banzhaf interaction, aimed at addressing the persistent challenge of generating human motion from rare language prompts. While previous approaches struggle with coarse-grained matching and overlook important semantic cues due to motion …

cn, gb (code pays fourni par la source)

MOST: Motion Diffusion Model for Rare Text via Temporal Clip Banzhaf Interaction

Yin Wang, Mu Li, Zhiying Leng, Frederick W. B. Li et autres

We introduce MOST, a novel motion diffusion model via temporal clip Banzhaf interaction, aimed at addressing the persistent challenge of generating human motion from rare language prompts. While previous approaches struggle with coarse-grained matching and overlook important semantic cues due to motion …

Geometric visual fusion graph neural networks for multi-person human-object interaction recognition in videos

Tanqiu Qiao, Ruochen Li, Frederick W. B. Li, Yoshiki Kubotani et autres

Human-Object Interaction (HOI) recognition in videos requires understanding both visual patterns and geometric relationships as they evolve over time. Visual and geometric features offer complementary strengths. Visual features capture appearance context, while geometric features provide structural patterns. Effectively fusing these multimodal features …

gb, jp (code pays fourni par la source)

Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos

Tanqiu Qiao, Ruochen Li, Frederick W. B. Li, Yoshiki Kubotani et autres

Human-Object Interaction (HOI) recognition in videos requires understanding both visual patterns and geometric relationships as they evolve over time. Visual and geometric features offer complementary strengths. Visual features capture appearance context, while geometric features provide structural patterns. Effectively fusing these multimodal features …