• Publications
  • Influence
Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval
TLDR
A novel coding framework called Cross-Age Reference Coding (CARC), which is able to encode the low-level feature of a face image with an age-invariant reference space and can achieve state-of-the-art performance on both the dataset and other widely used dataset for face recognition across age, MORPH dataset. Expand
Deep learning of binary hash codes for fast image retrieval
TLDR
This work proposes an effective deep learning framework to generate binary hash codes for fast image retrieval by employing a hidden layer for representing the latent concepts that dominate the class labels in convolutional neural networks. Expand
Face Recognition and Retrieval Using Cross-Age Reference Coding With Cross-Age Celebrity Dataset
TLDR
Experimental results show that although state-of-the-art methods can achieve competitive performance compared to average human performance, majority votes of several humans can achieve much higher performance on this task and the gap between machine and human would imply possible directions for further improvement of cross-age face recognition in the future. Expand
Ordinal hyperplanes ranker with cost sensitivities for age estimation
TLDR
The experimental results demonstrate that the proposed approach outperforms conventional multiclass-based and regression-based approaches as well as recently developed ranking-based age estimation approaches. Expand
Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks
TLDR
Experimental results on three different visual analysis tasks including image matching, image retrieval, and object recognition clearly demonstrate the effectiveness of the proposed unsupervised deep learning approach called DeepBit. Expand
Multiple Kernel Fuzzy Clustering
TLDR
A multiple kernel fuzzy c-means (MKFC) algorithm that is more immune to ineffective kernels and irrelevant features and automatically adjusting the kernel weights, which makes the choice of kernels less crucial. Expand
Affinity aggregation for spectral clustering
TLDR
AASC seeks for an optimal combination of affinity matrices so that it is more immune to ineffective affinities and irrelevant features, which enables the construction of similarity or distance-metric measures for clustering less crucial. Expand
RANSAC-Based DARCES: A New Approach to Fast Automatic Registration of Partially Overlapping Range Images
TLDR
A new method, the RANSAC-based DARCES method (data-aligned rigidity-constrained exhaustive search based on random sample consensus), which can solve the partially overlapping 3D registration problem without any initial estimation. Expand
Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks
TLDR
Compared with state-of-the-art approaches, SSDH achieves higher retrieval accuracy, while the classification performance is not sacrificed; yet it is effective and outperforms other hashing approaches on several benchmarks and large datasets. Expand
A Ranking Approach for Human Ages Estimation Based on Face Images
TLDR
This paper proposes a ranking-based framework consisting of a set of binary queries, where each query collects a binary-classification-based comparison result that is fused to predict the age of a person when inferring a person's age. Expand
...
1
2
3
4
5
...