Hubert P. H. Shum
YOU?
Author Swipe
Motion In-Betweening for Densely Interacting Characters Open
Motion in-betweening is the problem to synthesize movement between keyposes. Traditional research focused primarily on single characters. Extending them to densely interacting characters is highly challenging, as it demands precise spatial…
Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization Open
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…
Real‐Time and Controllable Reactive Motion Synthesis via Intention Guidance Open
We propose a real‐time method for reactive motion synthesis based on the known trajectory of input character, predicting instant reactions using only historical, user‐controlled motions. Our method handles the uncertainty of future movemen…
Real-time and Controllable Reactive Motion Synthesis via Intention Guidance Open
We propose a real-time method for reactive motion synthesis based on the known trajectory of input character, predicting instant reactions using only historical, user-controlled motions. Our method handles the uncertainty of future movemen…
BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks Open
The pervasive issue of bias in AI presents a significant challenge to painting classification, and is getting more serious as these systems become increasingly integrated into tasks like art curation and restoration. Biases, often arising …
FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment Open
Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep learning approaches often operate as black boxes and are vuln…
Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos Open
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 app…
PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction Open
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 between the pre-trained large-scale action recognition backbo…
Large-Scale Multi-Character Interaction Synthesis Open
Generating large-scale multi-character interactions is a challenging and important task in character animation. Multi-character interactions involve not only natural interactive motions but also characters coordinated with each other for t…
Using Fixed and Mobile Eye Tracking to Understand How Visitors View Art in a Museum: A Study at the Bowes Museum, County Durham, UK Open
The following paper describes a collaborative project involving researchers at Durham University, and professionals at the Bowes Museum, Barnard Castle, County Durham, UK, during which we used fixed and mobile eye tracking to understand ho…
FineCausal: A Causal-Based Framework for Interpretable Fine-Grained Action Quality Assessment Open
Action quality assessment (AQA) is critical for evaluating athletic performance, informing training strategies, and ensuring safety in competitive sports. However, existing deep learning approaches often operate as black boxes and are vuln…
BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction Open
Trajectory prediction allows better decision-making in applications of autonomous vehicles (AVs) or surveillance by predicting the short-term future movement of traffic agents. It is classified into pedestrian or heterogeneous trajectory p…
SEM-Net: Efficient Pixel Modelling for Image Inpainting with Spatially Enhanced SSM Open
Image inpainting aims to repair a partially damaged image based on the information from known regions of the images. Achieving semantically plausible inpainting results is particularly challenging because it requires the reconstructed regi…
BP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction Open
Trajectory prediction allows better decision-making in applications of autonomous vehicles or surveillance by predicting the short-term future movement of traffic agents. It is classified into pedestrian or heterogeneous trajectory predict…
Unified Spatial–Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Prediction Open
Pedestrian trajectory prediction aims to forecast future movements based on historical paths. Spatial-temporal (ST) methods often separately model spatial interactions among pedestrians and temporal dependencies of individuals. They overlo…
Unified Spatial-Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Prediction Open
Pedestrian trajectory prediction aims to forecast future movements based on historical paths. Spatial-temporal (ST) methods often separately model spatial interactions among pedestrians and temporal dependencies of individuals. They overlo…
Adaptive Graph Learning From Spatial Information for Surgical Workflow Anticipation Open
Surgical workflow anticipation is the task of predicting the timing of relevant surgical events from live video data, which is critical in Robotic-Assisted Surgery (RAS). Accurate predictions require the use of spatial information to model…
PHI: Bridging Domain Shift in Long-Term Action Quality Assessment via Progressive Hierarchical Instruction Open
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 between the pre-trained large-scale action recognition backbo…
Artificial intelligence for geometry-based feature extraction, analysis and synthesis in artistic images: a survey Open
Artificial Intelligence significantly enhances the visual art industry by analyzing, identifying and generating digitized artistic images. This review highlights the substantial benefits of integrating geometric data into AI models, addres…
A Comprehensive Survey of Action Quality Assessment: Method and Benchmark Open
Action Quality Assessment (AQA) quantitatively evaluates the quality of human actions, providing automated assessments that reduce biases in human judgment. Its applications span domains such as sports analysis, skill assessment, and medic…
Adaptive Graph Learning from Spatial Information for Surgical Workflow Anticipation Open
Surgical workflow anticipation is the task of predicting the timing of relevant surgical events from live video data, which is critical in Robotic-Assisted Surgery (RAS). Accurate predictions require the use of spatial information to model…
Neural-Code PIFu: High-Fidelity Single Image 3D Human Reconstruction via Neural Code Integration Open
We introduce neural-code PIFu, a novel implicit function for 3D human reconstruction, leveraging neural codebooks, our approach learns recurrent patterns in the feature space and reuses them to improve current features. Many existing metho…
From Category to Scenery: An End-to-End Framework for Multi-person Human-Object Interaction Recognition in Videos Open
Video-based Human-Object Interaction (HOI) recognition explores the intricate dynamics between humans and objects, which are essential for a comprehensive understanding of human behavior and intentions. While previous work has made signifi…
Artificial Intelligence for Geometry-Based Feature Extraction, Analysis and Synthesis in Artistic Images: A Survey Open
Artificial Intelligence significantly enhances the visual art industry by analyzing, identifying and generating digitized artistic images. This review highlights the substantial benefits of integrating geometric data into AI models, addres…
SEM-Net: Efficient Pixel Modelling for image inpainting with Spatially Enhanced SSM Open
Image inpainting aims to repair a partially damaged image based on the information from known regions of the images. \revise{Achieving semantically plausible inpainting results is particularly challenging because it requires the reconstruc…