H
Hao Ye
Researcher at Chinese Academy of Sciences
Publications - 50
Citations - 2863
Hao Ye is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has an hindex of 15, co-authored 50 publications receiving 2103 citations. Previous affiliations of Hao Ye include East China Normal University & Fudan University.
Papers
More filters
Journal ArticleDOI
Arbitrary-Oriented Scene Text Detection via Rotation Proposals
TL;DR: The Rotation Region Proposal Networks are designed to generate inclined proposals with text orientation angle information that are adapted for bounding box regression to make the proposals more accurately fit into the text region in terms of the orientation.
Journal ArticleDOI
Arbitrary-Oriented Scene Text Detection via Rotation Proposals
TL;DR: RRPN as mentioned in this paper proposes a rotation region proposal network to generate inclined text proposals with text orientation angle information, which is then adapted for bounding box regression to make the proposals more accurately fit into the text region in terms of the orientation.
Proceedings ArticleDOI
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification
TL;DR: Wang et al. as discussed by the authors proposed a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos.
Proceedings ArticleDOI
Multi-Stream Multi-Class Fusion of Deep Networks for Video Classification
TL;DR: A multi-stream framework that is able to exploit multimodal features that are more comprehensive than those previously attempted and produces significantly better results than the state of the arts on two popular benchmarks, 92.2% on UCF-101 (without using audio) and 84.9% on Columbia Consumer Videos.
Proceedings ArticleDOI
Evolving boxes for fast vehicle detection
TL;DR: It is shown intriguingly that by applying different feature fusion techniques, the initial boxes can be refined for both localization and recognition.