• Publications
  • Influence
Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching
TLDR
Leveraging on the recent developments in convolutional neural networks (CNNs), matching dense correspondence from a stereo pair has been cast as a learning problem, with performance exceeding traditional approaches. Expand
  • 233
  • 43
  • PDF
Deep Convolutional Neural Network for Image Deconvolution
TLDR
We use the convolutional neural network (CNN) to learn the deconvolution operation without the need to know the cause of visual artifacts. Expand
  • 559
  • 32
  • PDF
Deep Edge-Aware Filters
TLDR
A deep convolutional neural network with a gradient domain training procedure gives rise to a powerful tool to approximate various filters without knowing the original models and implementation details. Expand
  • 114
  • 25
  • PDF
3D Human Pose Estimation in the Wild by Adversarial Learning
TLDR
In this paper, we propose an adversarial learning framework, which distills the 3D human pose structures learned from the fully annotated constrained 3D pose dataset to in-the-wild images with only 2D pose annotations. Expand
  • 165
  • 16
  • PDF
Shepard Convolutional Neural Networks
TLDR
In this paper, we draw on Shepard interpolation and design Shepard Convolutional Neural Networks (ShCNN) which efficiently realizes end-to-end trainable TVI operators in the network. Expand
  • 99
  • 8
  • PDF
Look, Listen and Learn - A Multimodal LSTM for Speaker Identification
TLDR
We propose a multimodal LSTM architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input. Expand
  • 75
  • 6
  • PDF
Learning Dual Convolutional Neural Networks for Low-Level Vision
TLDR
We propose a general dual convolutional neural network (DualCNN) for low-level vision problems, e.g., super-resolution, edge-preserving filtering, deraining and dehazing. Expand
  • 68
  • 6
  • PDF
LSTM Pose Machines
  • Yue Luo, J. Ren, +5 authors L. Lin
  • Computer Science
  • IEEE/CVF Conference on Computer Vision and…
  • 18 December 2017
TLDR
We showed that if we were to impose the weight sharing scheme to the multi-stage CNN, it could be re-written as a Recurrent Neural Network (RNN). Expand
  • 48
  • 6
  • PDF
Deep Multimodal Speaker Naming
TLDR
We propose a novel convolutional neural networks (CNN) based learning framework to tackle the task of speaker naming. Expand
  • 38
  • 6
  • PDF
Deep Reasoning with Knowledge Graph for Social Relationship Understanding
TLDR
We propose an end-to-end trainable Graph Reasoning Model (GRM), in which a propagation mechanism is learned to propagate node message through the graph to explore the interaction between persons of interest and the contextual objects. Expand
  • 45
  • 6
  • PDF