• Publications
  • Influence
Locality-constrained Linear Coding for image classification
tl;dr
This paper presents a simple but effective coding scheme called Locality-constrained Linear Coding (LLC) in place of the VQ coding in traditional SPM, achieving state-of-the-art performance on several benchmarks. Expand
  • 3,102
  • 596
  • Open Access
Image Super-Resolution Via Sparse Representation
tl;dr
This paper presents a new approach to single-image superresolution, based upon sparse signal representation. Expand
  • 3,660
  • 543
  • Open Access
Image super-resolution as sparse representation of raw image patches
tl;dr
This paper addresses the problem of generating a super-resolution (SR) image from a single low-resolution input image. Expand
  • 1,289
  • 122
  • Open Access
Linear spatial pyramid matching using sparse coding for image classification
tl;dr
We develop an extension of the SPM method, by generalizing vector quantization to sparse coding followed by multi-scale spatial max pooling, and propose a linear SPM kernel based on SIFT sparse codes. Expand
  • 1,073
  • 114
  • Open Access
Deep Networks for Image Super-Resolution with Sparse Prior
tl;dr
We show that a sparse coding model particularly designed for super-resolution can be incarnated as a neural network, and trained in a cascaded structure from end to end. Expand
  • 485
  • 60
  • Open Access
Learning With $\ell ^{1}$-Graph for Image Analysis
tl;dr
The graph construction procedure essentially determines the potentials of those graph-oriented learning algorithms for image analysis. Expand
  • 539
  • 52
  • Open Access
Coupled Dictionary Training for Image Super-Resolution
tl;dr
In this paper, we propose a novel coupled dictionary training method for single-image super-resolution (SR) based on patchwise sparse recovery. Expand
  • 622
  • 51
Fine-grained recognition without part annotations
tl;dr
We present a method for fine-grained classification which does not require part annotations at training time, setting a new state-of-the-art on the CUB2011 and cars-196 datasets. Expand
  • 317
  • 48
  • Open Access
RAPID: Rating Pictorial Aesthetics using Deep Learning
tl;dr
We present the RAPID (RAting PIctorial aesthetics using Deep learning) system, which adopts a novel deep neural network approach to enable automatic feature learning. Expand
  • 228
  • 43
  • Open Access
Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks
tl;dr
We use Convolutional Neural Networks to solve the extremely challenging problem of image sentiment analysis. Expand
  • 278
  • 40
  • Open Access