• Publications
  • Influence
HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition
  • Z. Yan, Hao Zhang, +4 authors Yizhou Yu
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 2 October 2014
TLDR
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Expand
  • 256
  • 27
  • PDF
ModaNet: A Large-scale Street Fashion Dataset with Polygon Annotations
TLDR
We present a new database called ModaNet, a large-scale collection of images based on Paperdoll dataset, fully annotated with polygons on top of the 1 million weakly annotated street images in paperdoll. Expand
  • 50
  • 9
  • PDF
Conditional Image-Text Embedding Networks
TLDR
We propose a Conditional Image-Text Embedding (CITE) network that jointly learns multiple text-conditioned embeddings in a single end-to-end model. Expand
  • 46
  • 8
  • PDF
Large scale visual recommendations from street fashion images
TLDR
We describe a completely automated large scale visual recommendation system for fashion. Expand
  • 111
  • 7
  • PDF
GraB: Visual Saliency via Novel Graph Model and Background Priors
TLDR
We propose an unsupervised bottom-up saliency detection approach by exploiting novel graph structure and background priors. Expand
  • 81
  • 6
  • PDF
HD-CNN: Hierarchical Deep Convolutional Neural Network for Image Classification
TLDR
Improve classification accuracy of deep CNNs using hierarchical classification scheme. Expand
  • 48
  • 6
Style Finder: Fine-Grained Clothing Style Detection and Retrieval
TLDR
We propose a fine-grained learning model and multimedia retrieval framework for attribute-based multimedia retrieval of clothing items and image annotation. Expand
  • 140
  • 4
Region-Based Discriminative Feature Pooling for Scene Text Recognition
TLDR
We present a new feature representation method that automatically learns the most informative sub-regions of each scene character within a multi-class classification framework, whereas each sub-region seamlessly integrates a set of low level image features through integral images. Expand
  • 72
  • 3
  • PDF
Im2depth: Scalable exemplar based depth transfer
TLDR
The rapid increase in number of high quality mobile cameras have opened up an array of new problems in mobile vision. Expand
  • 24
  • 3
  • PDF
Weakly-Supervised Semantic Segmentation via Sub-Category Exploration
TLDR
We propose a simple yet effective approach that introduces a self-supervised task that discovers sub-categories in an unsupervised manner by exploiting the sub-category information. Expand
  • 13
  • 3
  • PDF
...
1
2
3
4
5
...