T
Thomas Leung
Researcher at Google
Publications - 12
Citations - 5272
Thomas Leung is an academic researcher from Google. The author has contributed to research in topics: Image processing & Anisotropic diffusion. The author has an hindex of 7, co-authored 10 publications receiving 4641 citations. Previous affiliations of Thomas Leung include Fujifilm Holdings Corporation.
Papers
More filters
Proceedings ArticleDOI
Geo-Aware Networks for Fine-Grained Recognition
Grace Chu,Brian Potetz,Weijun Wang,Andrew Howard,Yang Song,Fernando Brucher,Thomas Leung,Hartwig Adam +7 more
TL;DR: This is the first paper which systematically examined various ways of incorporating geolocated information into fine-grained image classification through the use of geolocation priors, post-processing or feature modulation, and makes a strong case for incorporatingGeolocation information in fine-grade recognition models for both server and on-device.
Patent
Method and apparatus for performing constrained spectral clustering of digital image data
Yang Song,Thomas Leung +1 more
TL;DR: In this article, a method and an apparatus process digital images is presented to access element data representing a plurality of elements belonging to a plurality in order to obtain inter-relational data results relating to the elements.
Patent
Method and apparatus for diffusion based illumination normalization
Troy Chinen,Thomas Leung +1 more
TL;DR: In this paper, an exemplar illumination normalization method is provided which includes receiving an input image having at least one spurious edge directly resulting from illumination, performing anisotropic diffusion on the input image to form a diffusion image, and removing at the least 1 spurious edge using the diffusion image.
Posted Content
Geo-Aware Networks for Fine-Grained Recognition
Grace Chu,Brian Potetz,Weijun Wang,Andrew Howard,Yang Song,Fernando Brucher,Thomas Leung,Hartwig Adam +7 more
TL;DR: In this article, the authors systematically examined various ways of incorporating geolocation information into fine-grained image classification through the use of geo-location priors, post-processing or feature modulation.