1.6k citations · 6.8k across the 186 of their papers we have counts for
8 papers · 1 filter
ResizeMix: Mixing Data with Preserved Object Information and True Labels
Jie Qin, Jiemin Fang, Qian Zhang +3
Data augmentation is a powerful technique to increase the diversity of data, which can effectively improve the generalization ability of neural networks in image recognition tasks.…
EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search
Wenqiang Zhang, Jiemin Fang, Xinggang Wang +1
Human pose estimation from image and video is a vital task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration…
Deep multi-metric learning for text-independent speaker verification
Jiwei Xu, Xinggang Wang, Bin Feng +1
Text-independent speaker verification is an important artificial intelligence problem that has a wide spectrum of applications, such as criminal investigation, payment certificatio…
Boundary-preserving Mask R-CNN
Tianheng Cheng, Xinggang Wang, Lichao Huang +1
Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perfo…
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
Jiemin Fang, Yuzhu Sun, Qian Zhang +4
Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural n…
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
Yifu Zhang, Chunyu Wang, Xinggang Wang +2
Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID…
AlignSeg: Feature-Aligned Segmentation Networks
Zilong Huang, Yunchao Wei, Xinggang Wang +3
Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic s…
Fast Neural Network Adaptation via Parameter Remapping and Architecture Search
Jiemin Fang, Yuzhu Sun, Kangjian Peng +4
Deep neural networks achieve remarkable performance in many computer vision tasks. Most state-of-the-art (SOTA) semantic segmentation and object detection approaches reuse neural n…