G
Gao Huang
Researcher at Tsinghua University
Publications - 164
Citations - 43663
Gao Huang is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Feature (computer vision). The author has an hindex of 37, co-authored 124 publications receiving 26697 citations. Previous affiliations of Gao Huang include Cornell University & University of Science and Technology of China.
Papers
More filters
Proceedings Article
Self-Supervised Discovering of Interpretable Features for Reinforcement Learning.
TL;DR: In this paper, a self-supervised interpretable network (SSINet) is employed to produce fine-grained attention masks for highlighting task-relevant information, which constitutes most evidence for the agent's decisions.
Posted Content
Adaptive Focus for Efficient Video Recognition
TL;DR: In this article, a reinforcement learning based approach for efficient spatially adaptive video recognition (AdaFocus) is proposed, where a light-weighted ConvNet is first adopted to quickly process the full video sequence, whose features are used by a recurrent policy network to localize the most task-relevant regions.
Journal ArticleDOI
Large scale air pollution prediction with deep convolutional networks
TL;DR: Wang et al. as discussed by the authors presented a novel method to handle the data effectively, which converted the observed data from irregularly distributed monitoring stations into a regular image-like pollution map, which can then be processed with advanced deep convolutional networks.
Proceedings ArticleDOI
Non-linear neighborhood component analysis based on constructive neural networks
Chen Qin,Shiji Song,Gao Huang +2 more
TL;DR: This paper proposes a novel non-linear supervised metric learning algorithm that combines the neighborhood component analysis method with constructive neural networks which gradually increase the network size during the training process, overcoming the limitations of traditional metric learning algorithms.
Posted Content
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
TL;DR: In this paper, the authors propose a novel framework that performs efficient image classification by processing a sequence of relatively small inputs, which are strategically selected from the original image with reinforcement learning.