• Publications
  • Influence
Graph Embedding and Extensions: A General Framework for Dimensionality Reduction
TLDR
We present a general framework called graph embedding, along with its linearization, kernelization, and tensorization, that offers a unified view for understanding and explaining many of the popular dimensionality reduction algorithms such as the ones mentioned above. Expand
  • 1,801
  • 291
  • PDF
A High-Quality Denoising Dataset for Smartphone Cameras
TLDR
We propose a systematic procedure for estimating ground truth for noisy images that can be used to benchmark denoising performance for smartphone cameras. Expand
  • 142
  • 52
  • PDF
GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond
TLDR
The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. Expand
  • 238
  • 41
  • PDF
Graph Embedding and Extensions: A General Framework for Dimensionality Reduction
TLDR
A large family of algorithms - supervised or unsupervised; stemming from statistics or geometry theory - has been designed to provide different solutions to the problem of dimensionality reduction. Expand
  • 856
  • 40
Deformable ConvNets V2: More Deformable, Better Results
TLDR
We present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. Expand
  • 352
  • 38
  • PDF
Marginal Fisher Analysis and Its Variants for Human Gait Recognition and Content- Based Image Retrieval
TLDR
We investigate and extend our previously proposed dimensionality reduction algorithm MFA to gait recognition and CBIR. Expand
  • 279
  • 29
  • PDF
3D shape regression for real-time facial animation
TLDR
We present a real-time performance-driven facial animation system based on 3D shape regression. Expand
  • 309
  • 24
  • PDF
Learning the Change for Automatic Image Cropping
TLDR
We present an automatic cropping technique that accounts for the two primary considerations of people when they crop: removal of distracting content, and enhancement of overall composition. Expand
  • 74
  • 24
  • PDF
Exposure: A White-Box Photo Post-Processing Framework
TLDR
We present a photo retouching system that handles a wide range of post-processing operations within a unified framework, and learns how to apply these operations based on a photo collection representing a user's personal preferences. Expand
  • 97
  • 22
  • PDF
DPSNet: End-to-end Deep Plane Sweep Stereo
TLDR
We present a convolutional neural network called DPSNet (Deep Plane Sweep Network) whose design is inspired by best practices of traditional geometry-based approaches for dense depth reconstruction. Expand
  • 73
  • 21
  • PDF
...
1
2
3
4
5
...