Hongsheng Li

Latest

• P2SGrad: Refined Gradients for Optimizing Deep Face Models
• Crafting GBD-Net for Object Detection
• Eliminating Background-Bias for Robust Person Re-Identification
• Jointly Learning Deep Features, Deformable Parts, Occlusion and Classification for Pedestrian Detection
• T-CNN: Tubelets With Convolutional Neural Networks for Object Detection From Videos
• DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks
• Object Detection in Videos with Tubelet Proposal Networks
• Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification