3 papers
cs.CV2026
ShapeGaussian: High-Fidelity 4D Human Reconstruction in Monocular Videos via Vision Priors
Zhenxiao Liang, Ning Zhang, Youbao Tang +4
We introduce ShapeGaussian, a high-fidelity, template-free method for 4D human reconstruction from casual monocular videos. Generic reconstruction methods lacking robust vision pri…
cs.CL2024
ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue
Zhangpu Li, Changhong Zou, Suxue Ma +13
The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical co…
cs.SD2024
Bidirectional Autoregressive Diffusion Model for Dance Generation
Canyu Zhang, Youbao Tang, Ning Zhang +4
Dance serves as a powerful medium for expressing human emotions, but the lifelike generation of dance is still a considerable challenge. Recently, diffusion models have showcased r…