T
Trevor Darrell
Researcher at University of California, Berkeley
Publications - 734
Citations - 222973
Trevor Darrell is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 148, co-authored 678 publications receiving 181113 citations. Previous affiliations of Trevor Darrell include Massachusetts Institute of Technology & Boston University.
Papers
More filters
Proceedings ArticleDOI
Combining object and feature dynamics in probabilistic tracking
TL;DR: This work proposes a probabilistic framework for incorporating global dynamics knowledge into the local feature extraction processes and shows the utility of this framework for improving feature tracking and thus shape and motion estimates in a batch factorization algorithm.
Finding lost children
TL;DR: In this article, a Content-Based Image Retrieval search using attributes and user feedback is proposed to speed up the reunification of children with their families should they get separated in a disaster.
Journal ArticleDOI
Introduction to the CVIU special issue on Parts and Attributes
Posted Content
Learning Compact Convolutional Neural Networks with Nested Dropout
TL;DR: In this article, the authors explore the impact of nested dropout on the convolutional layers in a CNN trained by backpropagation, and show that it can provide a simple and systematic way to determine the optimal representation size with respect to the desired accuracy and desired task and data complexity.
Proceedings ArticleDOI
Real-time audio-visual tracking for meeting analysis
TL;DR: An audio-visual tracking system that can estimate the location of multiple people, detect the current speaker and build a model of interaction between people in a meeting is demonstrated.