3 papers
cs.CV2026
PraNet-V2: Dual-Supervised Reverse Attention for Medical Image Segmentation
Bo-Cheng Hu, Ge-Peng Ji, Dian Shao +1
Accurate medical image segmentation is essential for effective diagnosis and treatment. Previously, PraNet-V1 was proposed to enhance polyp segmentation by introducing a reverse at…
cs.CV2025
FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion
Dian Shao, Mingfei Shi, Like Liu
Recognizing fine-grained actions from temporally corrupted skeleton sequences remains a significant challenge, particularly in real-world scenarios where online pose estimation oft…
cs.CV2025
FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance
Dian Shao, Mingfei Shi, Shengda Xu +3
Despite significant advances in video generation, synthesizing physically plausible human actions remains a persistent challenge, particularly in modeling fine-grained semantics an…