Stacked Cross Attention for Image-Text Matching
- Kuang-Huei Lee, Xi Chen, G. Hua, Houdong Hu, Xiaodong He
- Computer ScienceEuropean Conference on Computer Vision
- 21 March 2018
Stacked Cross Attention to discover the full latent alignments using both image regions and words in sentence as context and infer the image-text similarity achieves the state-of-the-art results on the MS-COCO and Flickr30K datasets.
A convolutional neural network cascade for face detection
- Haoxiang Li, Zhe L. Lin, Xiaohui Shen, Jonathan Brandt, G. Hua
- Computer ScienceComputer Vision and Pattern Recognition
- 7 June 2015
This work proposes a cascade architecture built on convolutional neural networks (CNNs) with very powerful discriminative capability, while maintaining high performance, and introduces a CNN-based calibration stage after each of the detection stages in the cascade.
Discriminative Learning of Local Image Descriptors
- Matthew A. Brown, G. Hua, S. Winder
- Computer ScienceIEEE Transactions on Pattern Analysis and Machineā¦
- 2011
A set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier are described.
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
- Dongqing Zhang, Jiaolong Yang, Dongqiangzi Ye, G. Hua
- Computer ScienceEuropean Conference on Computer Vision
- 26 July 2018
This work proposes to jointly train a quantized, bit-operation-compatible DNN and its associated quantizers, as opposed to using fixed, handcrafted quantization schemes such as uniform or logarithmic quantization, to address the gap in prediction accuracy between the quantized model and the full-precision model.
Ordinal Regression with Multiple Output CNN for Age Estimation
- Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao, G. Hua
- Computer ScienceComputer Vision and Pattern Recognition
- 1 June 2016
This paper proposes an End-to-End learning approach to address ordinal regression problems using deep Convolutional Neural Network, which could simultaneously conduct feature learning and regression modeling, and achieves the state-of-the-art performance on both the MORPH and AFAD datasets.
Gated Context Aggregation Network for Image Dehazing and Deraining
- Dongdong Chen, Mingming He, G. Hua
- Computer ScienceIEEE Workshop/Winter Conference on Applicationsā¦
- 21 November 2018
An end-to-end gated context aggregation network to directly restore the final haze-free image by adopting the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters.
Labeled Faces in the Wild: A Survey
- E. Learned-Miller, Gary B. Huang, Aruni RoyChowdhury, Haoxiang Li, G. Hua
- Computer Science
- 2016
A review of the contributions to LFW for which the authors have provided results to the curators and the cross cutting topic of alignment and how it is used in various methods is reviewed.
Neural Aggregation Network for Video Face Recognition
- Jiaolong Yang, Peiran Ren, G. Hua
- Computer ScienceComputer Vision and Pattern Recognition
- 17 March 2016
This NAN is trained with a standard classification or verification loss without any extra supervision signal, and it is found that it automatically learns to advocate high-quality face images while repelling low-quality ones such as blurred, occluded and improperly exposed faces.
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
- Qingnan Fan, Jiaolong Yang, G. Hua, Baoquan Chen, D. Wipf
- Computer ScienceIEEE International Conference on Computer Vision
- 11 August 2017
A deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering by estimating edges and reconstructing images using only cascaded convolutional layers arranged such that no handcrafted or application-specific image-processing components are required.
Visual attribute transfer through deep image analogy
- Jing Liao, Y. Yao, Lu Yuan, G. Hua, S. B. Kang
- Computer ScienceACM Transactions on Graphics
- 2 May 2017
The technique finds semantically-meaningful dense correspondences between two input images by adapting the notion of "image analogy" with features extracted from a Deep Convolutional Neutral Network for matching, and is called deep image analogy.
...
...