5 papers · 1 filter
LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference
Junkun Jiang, Ho Yin Au, Jingyu Xiang +1
Human motion is highly expressive and naturally aligned with language, yet prevailing methods relying heavily on joint text-motion embeddings struggle to synthesize temporally accu…
Learning Context-Adaptive Motion Priors for Masked Motion Diffusion Models with Efficient Kinematic Attention Aggregation
Junkun Jiang, Jie Chen, Ho Yin Au +1
Vision-based motion capture solutions often struggle with occlusions, which result in the loss of critical joint information and hinder accurate 3D motion reconstruction. Other wea…
SOSControl: Enhancing Human Motion Generation through Saliency-Aware Symbolic Orientation and Timing Control
Ho Yin Au, Junkun Jiang, Jie Chen
Traditional text-to-motion frameworks often lack precise control, and existing approaches based on joint keyframe locations provide only positional guidance, making it challenging…
Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework
Junkun Jiang, Jie Chen
Monocular 3D human pose estimation poses significant challenges due to the inherent depth ambiguities that arise during the reprojection process from 2D to 3D. Conventional approac…
SFSegNet: Parse Freehand Sketches using Deep Fully Convolutional Networks
Junkun Jiang, Ruomei Wang, Shujin Lin +1
Parsing sketches via semantic segmentation is attractive but challenging, because (i) free-hand drawings are abstract with large variances in depicting objects due to different dra…