8 papers
HSTGFormer: Hyper Spatial-Temporal Graph Transformer for 3D Human Pose Estimation
Ruochen Li, Shuang Chen, Wenke E +2
Transformer-based methods have achieved strong performance in monocular 3D human pose estimation, but most existing approaches organise spatial and temporal reasoning as separate s…
MDTD-ArtIR: Benchmarking Image Editing and Restoration Models for Art Image Restoration under Texture-Overlay Degradations
Mridula Vijendran, Shuang Chen, Hubert P. H. Shum
Restoring severely degraded visual media still remains a formidable challenge, as existing methods often hallucinate unnatural textures and contents, struggle with preserving color…
Motion-Adaptive Multi-Scale Temporal Modelling with Skeleton-Constrained Spatial Graphs for Efficient 3D Human Pose Estimation
Ruochen Li, Shuang Chen, Wenke E +2
Accurate 3D human pose estimation from monocular videos requires effective modelling of complex spatial and temporal dependencies. However, existing methods often face challenges i…
CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow
Ruisheng Han, Kanglei Zhou, Shuang Chen +2
Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as i…
BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks
Mridula Vijendran, Shuang Chen, Jingjing Deng +1
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 task…
Deep Learning-Enhanced Visual Monitoring in Hazardous Underwater Environments with a Swarm of Micro-Robots
Shuang Chen, Yifeng He, Barry Lennox +2
Long-term monitoring and exploration of extreme environments, such as underwater storage facilities, is costly, labor-intensive, and hazardous. Automating this process with low-cos…