2 papers
cs.CV2026
Multi-Modal Hyper-Graph Fusion for Low-Light Crowd Counting
Hao-Yuan Ma, Li Zhang, Yushi Qiu +3
Crowd counting is a fundamental task in computer vision. However, crowd counting in low-light environments remains largely underexplored, despite its practical importance in the re…
cs.LG2020
Train-by-Reconnect: Decoupling Locations of Weights from their Values
Yushi Qiu, Reiji Suda
What makes untrained deep neural networks (DNNs) different from the trained performant ones? By zooming into the weights in well-trained DNNs, we found it is the location of weight…