• Publications
  • Influence
Visual saliency based on multiscale deep features
  • Guanbin Li, Y. Yu
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 30 March 2015
TLDR
In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks, which have had many successes in visual recognition tasks. Expand
Deep Contrast Learning for Salient Object Detection
  • Guanbin Li, Y. Yu
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 7 March 2016
TLDR
In this paper, we propose an end-to-end deep contrast network to overcome the aforementioned limitations. Expand
Instance-Level Salient Object Segmentation
TLDR
In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Expand
Visual Saliency Detection Based on Multiscale Deep CNN Features
  • Guanbin Li, Y. Yu
  • Computer Science
  • IEEE Transactions on Image Processing
  • 7 September 2016
TLDR
In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks, which have had many successes in visual recognition tasks. Expand
Mesh editing with poisson-based gradient field manipulation
TLDR
We introduce a novel approach to mesh editing with the Poisson equation as the theoretical foundation that modifies the original mesh geometry implicitly through gradient field manipulation. Expand
Efficient View-Dependent Image-Based Rendering with Projective Texture-Mapping
TLDR
This paper presents how the image-based rendering technique of view-dependent texture-mapping (VDTM) can be efficiently implemented using projective texture mapping, a feature commonly available in polygon graphics hardware. Expand
Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks
  • Z. Li, Y. Yu
  • Computer Science, Biology
  • IJCAI
  • 25 April 2016
TLDR
In this paper, we propose an end-to-end deep network that predicts protein secondary structures from integrated local and global contextual features. Expand
An L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition
TLDR
We introduce an image transform based on the L1 norm for piecewise image flattening. Expand
Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-Tuning
  • Weifeng Ge, Y. Yu
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 28 February 2017
TLDR
We introduce a deep transfer learning scheme, called selective joint fine-tuning, for improving the performance of deep learning tasks with insufficient training data. Expand
Automatic Photo Adjustment Using Deep Neural Networks
TLDR
We present an automatic photo enhancement method inspired by deep machine learning and introduce an image descriptor accounting for the semantics of an image. Expand
...
1
2
3
4
5
...