75 citations · 87 across the 5 of their papers we have counts for
5 papers
Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation
Weide Liu, Xiangfei Kong, Tzu-Yi Hung +1
Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This…
Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification
Jianlou Si, Honggang Zhang, Chun-Guang Li +4
Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods b…
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
Jason Kuen, Xiangfei Kong, Zhe Lin +4
It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference c…
Microscopic Muscle Image Enhancement
Xiangfei Kong, Lin Yang
We propose a robust image enhancement algorithm dedicated for muscle fiber specimen images captured by optical microscopes. Blur or out of focus problems are prevalent in muscle im…
DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows
Jason Kuen, Xiangfei Kong, Gang Wang +1
Deluge Networks (DelugeNets) are deep neural networks which efficiently facilitate massive cross-layer information inflows from preceding layers to succeeding layers. The connectio…