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
Multiple-view object recognition in band-limited distributed camera networks
Allen Y. Yang,Subhransu Maji,C. Mario Christoudias,Trevor Darrell,Jitendra Malik,S. Shankar Sastry +5 more
TL;DR: The classical problem of object recognition in low-power, low-bandwidth distributed camera networks is studied and it is shown that between a network of cameras, high-dimensional SIFT histograms share a joint sparse pattern corresponding to a set of common features in 3-D.
Proceedings ArticleDOI
IDeixis: image-based Deixis for finding location-based information
TL;DR: This work introduces a point-by-photograph paradigm, where users can specify a location simply by taking pictures, and uses content-based image retrieval methods to search the web or other databases for matching images and their source pages to find relevant location-based information.
Posted Content
Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
TL;DR: This paper proposes the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA), and provides a finite sample bound for both classification and regression problems under Semi-DA.
Posted Content
TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
TL;DR: Task-Aware Feature Embedding Networks (TAFE-Nets) as mentioned in this paper learn how to adapt the image representation to a new task in a meta learning fashion, which is composed of a meta learner and a prediction network.
Proceedings ArticleDOI
Generalized Orderless Pooling Performs Implicit Salient Matching
TL;DR: In this paper, the authors generalize average and bilinear pooling to α-pooling, allowing for learning the pooling strategy during training, and present a novel way to visualize decisions made by these approaches.