GGCN: Gait Recognition with Generate Network and Convolutional Neural Network
A generate-network and CNN framework for robust gait recognition.
Distilling Multi-view Diffusion Models into 3D Generators
Fast single-image-to-3D Gaussian generation via multi-view diffusion distillation.
Semantic-aware Contrastive Learning via Multi-prompt Alignment
Semantic-aware contrastive learning with multi-source, multi-modal prompt alignment.
zhuoran-zhao
Progressive Semantic Learning for Unsupervised Skeleton-based Action Recognition
Progressive semantic learning for unsupervised skeleton-based action recognition.
MFNet: Multi-Feature Fusion Network for Real-Time Semantic Segmentation in Road Scenes
Multi-feature fusion for real-time road-scene semantic segmentation.
mengxu-lu
RPNet: Gait Recognition with Relationships Between Each Body-Parts
Part-relationship modeling for robust gait recognition.