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
Spatio-Temporal Action Graph Networks
Roei Herzig,Elad Levi,Huijuan Xu,Hang Gao,Eli Brosh,Xiaolong Wang,Amir Globerson,Trevor Darrell +7 more
TL;DR: In this article, an inter-object graph representation for activity recognition based on a disentangled graph embedding with direct observation of edge appearance is proposed, which uses explicit appearance for high order relations derived from object-object interaction, formed over regions that are the union of the spatial extent of constituent objects.
Proceedings ArticleDOI
Photo-based question answering
TL;DR: This work develops a three-layer system architecture for photo-based QA that brings together recent technical achievements in question answering and image matching and leverages community experts to handle the most difficult cases.
Posted Content
Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity
TL;DR: This paper investigates a modular co-evolution strategy: a collection of primitive agents learns to dynamically self-assemble into composite bodies while also learning to coordinate their behavior to control these bodies.
Proceedings Article
Deep Mixture of Experts via Shallow Embedding
Xin Wang,Fisher Yu,Lisa Dunlap,Yi-An Ma,Ruth Wang,Azalia Mirhoseini,Trevor Darrell,Joseph E. Gonzalez +7 more
TL;DR: This work explores a mixture of experts (MoE) approach to deep dynamic routing, which activates certain experts in the network on a per-example basis, and shows that Deep-MoEs are able to achieve higher accuracy with lower computation than standard convolutional networks.
Proceedings ArticleDOI
Recognizing gaze aversion gestures in embodied conversational discourse
TL;DR: This work analyzes eye gestures during interaction with an animated embodied agent and proposes a non-intrusive vision-based approach to estimate eye gaze and recognize eye gestures that can visually differentiate whether a user is thinking about a response or is waiting for the agent or robot to take its turn.