• Publications
  • Influence
Learning to Detect Salient Objects with Image-Level Supervision
  • L. Wang, H. Lu, +4 authors X. Ruan
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 21 July 2017
We leverage the observation that image-level tags provide important cues of foreground salient objects, and develop a weakly supervised learning method for saliency detection using image- level tags only. Expand
  • 257
  • 96
  • PDF
Visual Tracking with Fully Convolutional Networks
We conduct in-depth study on the properties of CNN features offline pre-trained on massive image data and classification task on ImageNet. Expand
  • 767
  • 83
  • PDF
Deep networks for saliency detection via local estimation and global search
This paper presents a saliency detection algorithm by integrating both local estimation and global search by using a deep neural network which learns local patch features to determine the saliency value of each pixel. Expand
  • 452
  • 61
  • PDF
Saliency Detection with Recurrent Fully Convolutional Networks
We propose a recurrent fully convolutional network for saliency detection, which is able to incorporate saliency prior knowledge into the CNNs for more accurate inference. Expand
  • 363
  • 58
  • PDF
Salient Object Detection with Recurrent Fully Convolutional Networks
We propose a new saliency detection method based on recurrent fully convolutional networks (RFCNs). Expand
  • 80
  • 14
STCT: Sequentially Training Convolutional Networks for Visual Tracking
We propose a sequential training method for convolutional neural networks (CNNs) to effectively transfer pre-trained deep features for online visual tracking. Expand
  • 214
  • 13
  • PDF
Structured Siamese Network for Real-Time Visual Tracking
We propose a local structure learning method, which simultaneously considers the local patterns of the target and their structural relationships for more accurate target tracking. Expand
  • 101
  • 12
  • PDF
End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks
In this paper, we propose a new image super-resolution (SR) approach based on a convolutional neural network (CNN), which jointly learns the feature extraction, upsampling, and high-resolution reconstruction modules, yielding a completely end-to-end trainable deep CNN. Expand
  • 91
  • 10
  • PDF
Learning regression and verification networks for long-term visual tracking
In this work, we propose a novel long-term tracking framework based on deep regression and verification networks. Expand
  • 33
  • 9
  • PDF
Deep visual tracking: Review and experimental comparison
We review the state-of-the-art visual tracking methods based on deep learning and show that: (1) The usage of convolutional neural network (CNN) model could significantly improve the tracking performance, while using the CNN model for template matching is usually faster. Expand
  • 215
  • 8