• Publications
  • Influence
Image classification by non-negative sparse coding, low-rank and sparse decomposition
We propose an image classification framework by leveraging the non-negative sparse coding, low-rank and sparse matrix decomposition techniques (LR-Sc+ SPM). First, we propose a new non-negativeExpand
  • 168
  • 6
  • PDF
Two-Step Quantization for Low-bit Neural Networks
Every bit matters in the hardware design of quantized neural networks. However, extremely-low-bit representation usually causes large accuracy drop. Thus, how to train extremely-low-bit neuralExpand
  • 47
  • 6
  • PDF
Image classification by search with explicitly and implicitly semantic representations
We model the explicitly and implicitly semantic representations for image classification.Explicitly semantic representations are obtained using learned models with supervision.Implicitly semanticExpand
  • 15
  • 4
Image classification using spatial pyramid robust sparse coding
Recently, the sparse coding based codebook learning and local feature encoding have been widely used for image classification. The sparse coding model actually assumes the reconstruction errorExpand
  • 42
  • 3
  • PDF
Image classification by non-negative sparse coding, correlation constrained low-rank and sparse decomposition
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). First, we proposeExpand
  • 53
  • 2
  • PDF
Image classification using Harr-like transformation of local features with coding residuals
Recently, the bag-of-visual-words (BoW) model has been proven very effective for image classification. However, most researchers used local features directly while neglecting their spatialExpand
  • 28
  • 2
  • PDF
Camera Compensation Using a Feature Projection Matrix for Person Reidentification
Matching individuals within a group of spatially nonoverlapping surveillance cameras, also known as person reidentification, has recently attracted a lot of research interest. Current methods mainlyExpand
  • 31
  • 2
  • PDF
Camera Network Based Person Re-identification by Leveraging Spatial-Temporal Constraint and Multiple Cameras Relations
With the rapid development of multimedia technology and vast demand on video investigation, long-term cross-camera object tracking is increasingly important in the practical surveillance scene.Expand
  • 15
  • 2
  • PDF
Body Joint Guided 3-D Deep Convolutional Descriptors for Action Recognition
3-D convolutional neural networks (3-D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied toExpand
  • 26
  • 1
  • PDF
Fine-Grained Image Classification via Low-Rank Sparse Coding With General and Class-Specific Codebooks
This paper tries to separate fine-grained images by jointly learning the encoding parameters and codebooks through low-rank sparse coding (LRSC) with general and class-specific codebook generation.Expand
  • 33
  • 1
  • PDF