• Publications
  • Influence
Image classification by non-negative sparse coding, low-rank and sparse decomposition
TLDR
We propose an image classification framework by leveraging the non-negative sparse coding, low-rank and sparse matrix decomposition techniques (LR-Sc+ SPM) to extract local features' information in order to represent images. Expand
  • 169
  • 6
  • PDF
Two-Step Quantization for Low-bit Neural Networks
TLDR
In this paper, we propose a Two-Step Quantization (TSQ) framework for low-bit quantized neural networks: code learning and transformation function learning based on the learned codes. Expand
  • 49
  • 6
  • PDF
Image classification by search with explicitly and implicitly semantic representations
TLDR
We propose a novel image classification method by explicitly and implicitly representing the images with searching strategy. Expand
  • 16
  • 4
Image classification using spatial pyramid robust sparse coding
TLDR
We propose a new sparse coding based image classification method by spatial pyramid robust sparse coding (SP-RSC). Expand
  • 42
  • 3
  • PDF
Image classification by non-negative sparse coding, correlation constrained low-rank and sparse decomposition
TLDR
We propose an image classification framework by leveraging the non-negative sparse coding, correlation constrained low rank and sparse matrix decomposition technique (CCLR-Sc+SPM) to decompose the feature vectors of images into a low-rank and sparse error matrix by considering the correlations between images. Expand
  • 55
  • 2
  • PDF
Image classification using Harr-like transformation of local features with coding residuals
TLDR
We propose a novel image classification method using Harr-like transformation of local features with additional consideration of coding residuals. Expand
  • 28
  • 2
  • PDF
Camera Compensation Using a Feature Projection Matrix for Person Reidentification
TLDR
Matching individuals within a group of spatially nonoverlapping surveillance cameras, also known as person reidentification, has recently attracted a lot of research interest. Expand
  • 31
  • 2
  • PDF
Camera Network Based Person Re-identification by Leveraging Spatial-Temporal Constraint and Multiple Cameras Relations
TLDR
We introduce a probabilistic method named Camera Network based Person Re-identification CNPR, to address the novel CNPR problem. Expand
  • 16
  • 2
  • PDF
Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition
TLDR
In this paper, we propose a novel joints-pooled 3D deep convolutional descriptor (JDD) which can take advantages of body joints and C3D for action recognition. Expand
  • 27
  • 1
  • PDF
Fine-Grained Image Classification via Low-Rank Sparse Coding With General and Class-Specific Codebooks
TLDR
This paper tries to separate fine-grained images by jointly learning the encoding parameters and codebooks through low-rank sparse coding with general and class-specific codebook generation. Expand
  • 35
  • 1
  • PDF