S
Steve Branson
Researcher at California Institute of Technology
Publications - 21
Citations - 8770
Steve Branson is an academic researcher from California Institute of Technology. The author has contributed to research in topics: Motion estimation & Support vector machine. The author has an hindex of 18, co-authored 21 publications receiving 7048 citations. Previous affiliations of Steve Branson include University of California, San Diego.
Papers
More filters
The Caltech-UCSD Birds-200-2011 Dataset
TL;DR: CUB-200-2011 as mentioned in this paper is an extended version of CUB200, which roughly doubles the number of images per category and adds new part localization annotations, annotated with bounding boxes, part locations, and at-ribute labels.
Caltech-UCSD Birds 200
Peter Welinder,Steve Branson,Takeshi Mita,Catherine Wah,Florian Schroff,Serge Belongie,Pietro Perona +6 more
TL;DR: Caltech-UCSD Birds 200 (CUB-200) is a challenging image dataset annotated with 200 bird species to enable the study of subordinate categorization, which is not possible with other popular datasets that focus on basic level categories.
Proceedings Article
The Multidimensional Wisdom of Crowds
TL;DR: A method for estimating the underlying value of each image from (noisy) annotations provided by multiple annotators, based on a model of the image formation and annotation process, which predicts ground truth labels on both synthetic and real data more accurately than state of the art methods.
Book ChapterDOI
Visual recognition with humans in the loop
Steve Branson,Catherine Wah,Florian Schroff,Boris Babenko,Peter Welinder,Pietro Perona,Serge Belongie +6 more
TL;DR: The results demonstrate that incorporating user input drives up recognition accuracy to levels that are good enough for practical applications, while at the same time, computer vision reduces the amount of human interaction required.
Posted Content
Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
TL;DR: An architecture for fine-grained visual categorization that approaches expert human performance in the classification of bird species recognition is proposed, and a novel graph-based clustering algorithm for learning a compact pose normalization space is proposed.