• Publications
  • Influence
Unsupervised Salience Learning for Person Re-identification
TLDR
We apply adjacency constrained patch matching to build dense correspondence between image pairs, which shows effectiveness in handling misalignment caused by large viewpoint and pose variations. Expand
  • 956
  • 110
  • PDF
Saliency detection by multi-context deep learning
TLDR
We propose a multi-context deep learning framework to model saliency of objects in images by taking global and local context into account. Expand
  • 664
  • 94
  • PDF
Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
TLDR
Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough. Expand
  • 751
  • 88
  • PDF
Visual Tracking with Fully Convolutional Networks
TLDR
We conduct in-depth study on the properties of CNN features offline pre-trained on massive image data and classification task on ImageNet. Expand
  • 776
  • 84
  • PDF
Learning Mid-level Filters for Person Re-identification
TLDR
We propose a novel approach of learning mid-level filters from automatically discovered patch clusters for person re-identification that are view-invariant and discriminatively learned. Expand
  • 518
  • 57
  • PDF
Person Re-identification by Salience Matching
TLDR
We exploit the pair wise salience distribution relationship between pedestrian images, and solve the person re-identification problem by proposing a salience matching strategy. Expand
  • 462
  • 50
  • PDF
Hybrid Task Cascade for Instance Segmentation
TLDR
Cascade is a classic yet powerful architecture that has boosted performance on various tasks. Expand
  • 236
  • 49
  • PDF
Libra R-CNN: Towards Balanced Learning for Object Detection
TLDR
We propose Libra R-CNN, a simple but effective framework towards balanced learning for object detection. Expand
  • 195
  • 48
  • PDF
Quality Aware Network for Set to Set Recognition
  • Yu Liu, J. Yan, Wanli Ouyang
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 11 April 2017
TLDR
This paper targets on the problem of set to set recognition, which learns the metric between two image sets. Expand
  • 205
  • 40
  • PDF
Joint Deep Learning for Pedestrian Detection
TLDR
We propose a unified deep model for jointly learning feature extraction, a part deformation model, an occlusion model and classification. Expand
  • 533
  • 36
  • PDF