• Publications
  • Influence
Mining Travel Patterns from Geotagged Photos
TLDR
We use the wealth of community-contributed geotagged photos to analyze people’s travel patterns at the local level of a tour destination. Expand
  • 183
  • 14
  • PDF
Joint multi-label multi-instance learning for image classification
TLDR
We propose an integrated multi- label multi-instance learning (MLMIL) approach based on hidden conditional random fields (HCRFs), which simultaneously captures both the connections between semantic labels and regions, and the correlations among the labels in a single formulation. Expand
  • 235
  • 13
  • PDF
Aspect Ranking: Identifying Important Product Aspects from Online Consumer Reviews
TLDR
In this paper, we dedicate to the topic of aspect ranking, which aims to automatically identify important product aspects from consumer reviews. Expand
  • 219
  • 12
  • PDF
Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognition
TLDR
We propose to learn fine-grained features from hundreds of part proposals by Trilinear Attention Sampling Network (TASN) in an efficient teacher-student manner. Expand
  • 77
  • 12
  • PDF
Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search
TLDR
We propose an approach that simultaneously utilizes both visual and textual information to estimate the relevance of user tagged images using a hypergraph learning approach. Expand
  • 394
  • 11
  • PDF
Adaptive Transfer Network for Cross-Domain Person Re-Identification
TLDR
We propose a novel adaptive transfer network (ATNet) for effective cross-domain person re-identification. Expand
  • 71
  • 9
  • PDF
Comparative Deep Learning of Hybrid Representations for Image Recommendations
TLDR
We design a dual-net deep network, in which the two sub-networks map input images and preferences of users into a same latent semantic space, and then the distances between images and users in the latent space are calculated to make decisions. Expand
  • 71
  • 8
  • PDF
Multi-Scale Triplet CNN for Person Re-Identification
TLDR
In this paper, we propose a multi-scale triplet convolutional neural network which captures visual appearance of a person at various scales. Expand
  • 141
  • 7
Visual query suggestion: Towards capturing user intent in internet image search
TLDR
Query suggestion is an effective approach to bridge the Intention Gap between the users' search intents and queries. Expand
  • 133
  • 7
Graph-based semi-supervised learning with multiple labels
TLDR
We propose a novel graph-based learning framework in the setting of semi-supervised learning with multiple labels. Expand
  • 128
  • 7
  • PDF