• Publications
  • Influence
Locality-constrained Linear Coding for image classification
TLDR
This paper presents a simple but effective coding scheme called Locality-constrained Linear Coding (LLC) in place of the VQ coding in traditional SPM, using the locality constraints to project each descriptor into its local-coordinate system, and the projected coordinates are integrated by max pooling to generate the final representation. Expand
Image Super-Resolution Via Sparse Representation
TLDR
This paper presents a new approach to single-image superresolution, based upon sparse signal representation, which generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. Expand
Linear spatial pyramid matching using sparse coding for image classification
TLDR
An extension of the SPM method is developed, by generalizing vector quantization to sparse coding followed by multi-scale spatial max pooling, and a linear SPM kernel based on SIFT sparse codes is proposed, leading to state-of-the-art performance on several benchmarks by using a single type of descriptors. Expand
Linear spatial pyramid matching using sparse coding for image classification
TLDR
An extension of the SPM method is developed, by generalizing vector quantization to sparse coding followed by multi-scale spatial max pooling, and a linear SPM kernel based on SIFT sparse codes is proposed, leading to state-of-the-art performance on several benchmarks by using a single type of descriptors. Expand
Image super-resolution as sparse representation of raw image patches
TLDR
It is shown that a small set of randomly chosen raw patches from training images of similar statistical nature to the input image generally serve as a good dictionary, in the sense that the computed representation is sparse and the recovered high-resolution image is competitive or even superior in quality to images produced by other SR methods. Expand
Deep Networks for Image Super-Resolution with Sparse Prior
TLDR
This paper shows 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, and leads to much more efficient and effective training, as well as a reduced model size. Expand
Coupled Dictionary Training for Image Super-Resolution
TLDR
This paper demonstrates that the coupled dictionary learning method can outperform the existing joint dictionary training method both quantitatively and qualitatively and speed up the algorithm approximately 10 times by learning a neural network model for fast sparse inference and selectively processing only those visually salient regions. Expand
Fine-grained recognition without part annotations
TLDR
This work proposes a method for fine-grained recognition that uses no part annotations, based on generating parts using co-segmentation and alignment, which is combined in a discriminative mixture. Expand
Learning With $\ell ^{1}$-Graph for Image Analysis
TLDR
Compared with the conventional k -nearest-neighbor graph and ¿-ball graph, the ¿1-graph possesses the advantages: greater robustness to data noise, (2) automatic sparsity, and (3) adaptive neighborhood for individual datum. Expand
Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks
TLDR
The proposed CNN can achieve better performance in image sentiment analysis than competing algorithms and is able to improve the performance on Twitter images by inducing domain transfer with a small number of manually labeled Twitter images. Expand
...
1
2
3
4
5
...