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
Simultaneous Deep Transfer Across Domains and Tasks.
TL;DR: The authors proposed a new CNN architecture to exploit unlabeled and sparsely labeled target domain data, simultaneously optimizing for domain invariance to facilitate domain transfer and uses a soft label distribution matching loss to transfer information between tasks.
Proceedings ArticleDOI
Perception for the manipulation of socks
TL;DR: This work considers the perceptual challenges inherent in the robotic manipulation of previously unseen socks, with the end goal of manipulation by a household robot for laundry.
Book ChapterDOI
Adversarial Continual Learning
Sayna Ebrahimi,Sayna Ebrahimi,Franziska Meier,Roberto Calandra,Trevor Darrell,Marcus Rohrbach +5 more
TL;DR: Adversarial Continual Learning (ACL) as discussed by the authors proposes a hybrid continual learning framework that learns a disjoint representation for task-invariant and task-specific features required to solve a sequence of tasks.
Proceedings ArticleDOI
On modelling nonlinear shape-and-texture appearance manifolds
TL;DR: This paper proposes two nonlinear techniques for modelling shape-and-texture appearance manifolds and employs a nearest-neighbor method to find a local set of shapes and images that can be morphed to explain a new input.
Proceedings ArticleDOI
Gesture + play: full-body interaction for virtual environments
TL;DR: Several different interaction styles are compared, based on an analysis of the space of possible perceptual interface abstractions for full-body navigation and the results of a wizard-of-oz study of user preferences, for passive, real-time articulated tracking with standard cameras and personal computers.