• Publications
  • Influence
Learning Deconvolution Network for Semantic Segmentation
TLDR
We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. Expand
  • 1,583
  • 99
  • PDF
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
TLDR
We propose an online visual tracking algorithm by learning discriminative saliency map using Convolutional Neural Network (CNN). Expand
  • 584
  • 69
  • PDF
Decomposing Motion and Content for Natural Video Sequence Prediction
TLDR
We propose a deep neural network for the prediction of future frames in natural video sequences. Expand
  • 294
  • 62
  • PDF
Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
TLDR
We propose a novel hierarchical approach for text-to-image synthesis by inferring semantic layout. Expand
  • 143
  • 17
  • PDF
Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
TLDR
We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations, and learn a separate network for each task. Expand
  • 241
  • 16
  • PDF
The Visual Object Tracking VOT2013 Challenge Results
TLDR
We present the VOT2013 benchmark dataset for evaluation of single-object visual trackers as well as results obtained by the trackers competing in the challenge. Expand
  • 183
  • 11
  • PDF
Learning Hierarchical Semantic Image Manipulation through Structured Representations
TLDR
We present a novel hierarchical framework for semantic image manipulation that allows a user to manipulate images at object-level by adding, removing, and moving one bounding box at a time. Expand
  • 37
  • 9
  • PDF
Weakly Supervised Semantic Segmentation Using Web-Crawled Videos
TLDR
We propose a novel algorithm for weakly supervised semantic segmentation based on image classification with discriminative localization technique to reject false alarms in retrieved videos and identify relevant spatio-temporal volumes within retrieved videos. Expand
  • 84
  • 7
  • PDF
Diversity-Sensitive Conditional Generative Adversarial Networks
TLDR
We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN). Expand
  • 60
  • 7
  • PDF
Learning Transferrable Knowledge for Semantic Segmentation with Deep Convolutional Neural Network
TLDR
We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN) which exploits auxiliary segmentation annotations available for different categories to guide segmentations on images with only image-level class labels. Expand
  • 85
  • 5
  • PDF