• Publications
  • Influence
A novel approach to enable semantic and visual image summarization for exploratory image search
TLDR
A novel scheme to incorporate topic network and representativeness-based sampling for achieving semantic and visual summarization and visualization of large-scale collections of Flickr images and experiments on large- scale image collections with diverse semantics have provided very positive results. Expand
Deep Multi-task Learning for Large-Scale Image Classification
TLDR
This work can use back propagation to simultaneously refine both the relevant node classifiers (at different levels of the concept ontology) and the deep CNNs according to a joint objective function and achieve very competitive results on both the accuracy and the cost of feature extraction for large-scale image classification. Expand
Similarity Measurement Based on Trigonometric Function Distance
TLDR
An algorithm for object shape analysis is designed, and experiments based on trigonometric function distance are conducted, giving an encouraging high recognition rate by using the new similarity measurement. Expand
JustClick: Personalized Image Recommendation via Exploratory Search From Large-Scale Flickr Images
TLDR
A novel framework to enable personalized image recommendation via exploratory search from large-scale collections of Flickr images, where a small set of most representative images are recommended for the given image topic according to their representativeness scores and Kernel principal component analysis and hyperbolic visualization are seamlessly integrated. Expand
Fractional Orthogonal Fourier-Mellin Moments for Pattern Recognition
TLDR
This paper proposes a new method to construct FOFMMs by using a continuous parameter t, which has the same number of zeros as OFMMs with the same degree, but the zeros of FO FMMs polynomial are more uniformly distributed than which of OFM Ms and the first zero is closer to the origin. Expand
Multiscale shape context and re-ranking for deformable shape retrieval
TLDR
A distinct multiscale shape context (MSC) method for isometric 3D shape description and retrieval that is advantageous in solving the domain offset deficiency for intra-class shapes and an efficient while robust re-ranking algorithm by metric mapping is designed to alleviate the errors of the feature space. Expand
Efficient logo recognition by local feature groups
TLDR
Using generalized Hough transform to identify local features that are invariant across images, this paper can efficiently add spatial information into groups of local features and enhance the discriminative power of local feature. Expand
Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders
TLDR
This paper proposes Laplacian pyramid auto-encoders, a straightforward modification of the deep convolutionalAuto-encoder architecture for unsupervised representation learning, and Experimental results showed that LaplACian pyramid benefited the classification and reconstruction performance of deep auto- encoder approaches, and batch normalization is critical to get deepAutoEncoder approaches to begin learning. Expand
Exploration in improving retrieval quality and robustness for deformable non-rigid 3D shapes
TLDR
A novel fusion method for multiple feature fusion, which turns out to be superior to weighted sum approach with a low complexity, and a new retrieval guidance algorithm based on category prediction is introduced. Expand
...
1
2
3
4
5
...