• Publications
  • Influence
The application of two-level attention models in deep convolutional neural network for fine-grained image classification
TLDR
We propose to apply visual attention to fine-grained classification task using deep neural network to improve both the what and where aspects. Expand
  • 488
  • 33
  • PDF
Learning Cross-Media Joint Representation With Sparse and Semisupervised Regularization
TLDR
In this paper, we propose a novel feature learning algorithm for cross-media data, called joint representation learning (JRL), which is able to explore jointly the correlation and semantic information in a unified optimization framework. Expand
  • 148
  • 25
Cross-Media Shared Representation by Hierarchical Learning with Multiple Deep Networks
TLDR
Inspired by the progress of deep neural network (DNN) in single-media retrieval, the researchers have applied the cross-media multiple deep network (CMDN) to exploit the complex cross media correlation by hierarchical learning. Expand
  • 107
  • 14
  • PDF
SSDH: Semi-Supervised Deep Hashing for Large Scale Image Retrieval
  • J. Zhang, Y. Peng
  • Computer Science
  • IEEE Transactions on Circuits and Systems for…
  • 28 July 2016
TLDR
We propose the semi-supervised deep hashing approach, to perform more effective hash function learning by simultaneously preserving semantic similarity and underlying data structures. Expand
  • 69
  • 14
  • PDF
CCL: Cross-modal Correlation Learning With Multigrained Fusion by Hierarchical Network
TLDR
In this paper, a cross-modal correlation learning approach has been proposed with multi-grained fusion by hierarchical network and the experimental results show our CCL approach achieves the best performance. Expand
  • 100
  • 11
  • PDF
Unsupervised Generative Adversarial Cross-modal Hashing
TLDR
We propose an Unsupervised Generative Adversarial Cross-modal Hashing approach (UGACH), which makes full use of GAN's ability for unsupervised representation learning to exploit the underlying manifold structure of cross-Modal data. Expand
  • 61
  • 9
  • PDF
Semi-Supervised Cross-Media Feature Learning With Unified Patch Graph Regularization
TLDR
We propose a semi-supervised cross-media feature learning algorithm with unified patch graph regularization (S2UPG), which is able to model all different media types simultaneously in the same graph. Expand
  • 82
  • 8
Error-Driven Incremental Learning in Deep Convolutional Neural Network for Large-Scale Image Classification
TLDR
This paper focuses on incremental learning of deep convolutional neural network (DCNN) in image classification task. Expand
  • 145
  • 7
  • PDF
Heterogeneous Metric Learning with Joint Graph Regularization for Cross-Media Retrieval
TLDR
In this paper, we propose a joint graph regularized heterogeneous metric learning (JGRHML) algorithm, which integrates the structure of different media into a joint Graph regularization. Expand
  • 91
  • 7
MHTN: Modal-Adversarial Hybrid Transfer Network for Cross-Modal Retrieval
TLDR
This paper proposes a modal-adversarial hybrid transfer network (MHTN), which aims to realize knowledge transfer from a single-modal source domain to a cross- modal target domain and learn cross-Modal common representation. Expand
  • 39
  • 7
  • PDF