G
Gabriel Takacs
Researcher at Stanford University
Publications - 43
Citations - 2764
Gabriel Takacs is an academic researcher from Stanford University. The author has contributed to research in topics: Image retrieval & Histogram. The author has an hindex of 25, co-authored 43 publications receiving 2713 citations. Previous affiliations of Gabriel Takacs include Intel & Microsoft.
Papers
More filters
Proceedings ArticleDOI
Outdoors augmented reality on mobile phone using loxel-based visual feature organization
Gabriel Takacs,Vijay Chandrasekhar,Natasha Gelfand,Yingen Xiong,Wei-Chao Chen,Thanos Bismpigiannis,Radek Grzeszczuk,Kari Pulli,Bernd Girod +8 more
TL;DR: An outdoors augmented reality system for mobile phones that matches camera-phone images against a large database of location-tagged images using a robust image retrieval algorithm and shows a smart-phone implementation that achieves a high image matching rate while operating in near real-time.
Journal ArticleDOI
Mobile Visual Search
Bernd Girod,Vijay Chandrasekhar,David Chen,Ngai-Man Cheung,Radek Grzeszczuk,Yuriy Reznik,Gabriel Takacs,Sam S. Tsai,Ramakrishna Vedantham +8 more
TL;DR: Mobile phones have evolved into powerful image and video processing devices equipped with high-resolution cameras, color displays, and hardware-accelerated graphics, which enables a new class of applications that use the camera phone to initiate search queries about objects in visual proximity to the user.
Proceedings ArticleDOI
CHoG: Compressed histogram of gradients A low bit-rate feature descriptor
TL;DR: A framework for computing low bit-rate feature descriptors with a 20× reduction in bit rate is proposed and it is shown how to efficiently compute distances between descriptors in their compressed representation eliminating the need for decoding.
Journal ArticleDOI
Compressed Histogram of Gradients: A Low-Bitrate Descriptor
Vijay Chandrasekhar,Gabriel Takacs,David Chen,Sam S. Tsai,Yuriy Reznik,Radek Grzeszczuk,Bernd Girod +6 more
TL;DR: A framework for computing low bit-rate feature descriptors with a 20× reduction in bit rate compared to state-of-the-art descriptors is proposed and it is shown how to efficiently compute distances between descriptors in the compressed domain eliminating the need for decoding.
Proceedings ArticleDOI
Unified Real-Time Tracking and Recognition with Rotation-Invariant Fast Features
TL;DR: This work presents a method that unifies tracking and video content recognition with applications to Mobile Augmented Reality (MAR), and introduces the Radial Gradient Transform (RGT) and an approximate RGT, yielding the Rotation-Invariant, Fast Feature (RIFF) descriptor.