J
Jonathan Huang
Researcher at University of Texas MD Anderson Cancer Center
Publications - 93
Citations - 12892
Jonathan Huang is an academic researcher from University of Texas MD Anderson Cancer Center. The author has contributed to research in topics: Object detection & Ranking. The author has an hindex of 36, co-authored 85 publications receiving 9523 citations. Previous affiliations of Jonathan Huang include Carnegie Mellon University & Google.
Papers
More filters
Proceedings ArticleDOI
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Jonathan Huang,Vivek Rathod,Chen Sun,Menglong Zhu,Anoop Korattikara,Alireza Fathi,Ian Fischer,Zbigniew Wojna,Yang Song,Sergio Guadarrama,Kevin Murphy +10 more
TL;DR: A unified implementation of the Faster R-CNN, R-FCN and SSD systems is presented and the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures is traced out.
Book ChapterDOI
Progressive Neural Architecture Search
Chenxi Liu,Barret Zoph,Maxim Neumann,Jonathon Shlens,Wei Hua,Li-Jia Li,Li Fei-Fei,Li Fei-Fei,Alan L. Yuille,Jonathan Huang,Kevin Murphy +10 more
TL;DR: In this article, a sequential model-based optimization (SMBO) strategy is proposed to search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space.
Book ChapterDOI
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
TL;DR: In this article, it was shown that it is possible to replace many of the expensive 3D convolutions by low-cost 2D convolution, and the best result was achieved when replacing the 3D CNNs at the bottom of the network, suggesting that temporal representation learning on high-level semantic features is more useful.
Proceedings ArticleDOI
Generation and Comprehension of Unambiguous Object Descriptions
TL;DR: The authors proposed a method that can generate an unambiguous description (known as a referring expression) of a specific object or region in an image, and which can also comprehend or interpret such an expression to infer which object is being described.
Posted Content
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
TL;DR: It is shown that it is possible to replace many of the 3D convolutions by low-cost 2D convolution, suggesting that temporal representation learning on high-level “semantic” features is more useful.