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
Proton: A visuo-haptic data acquisition system for robotic learning of surface properties
Alex Burka,Siyao Hu,Stuart Helgeson,Shweta Krishnan,Yang Gao,Lisa Anne Hendricks,Trevor Darrell,Katherine J. Kuchenbecker +7 more
TL;DR: The design and construction of the Proton is detailed, a multimodal data acquisition system that a human operator can use to gather the envisioned data set and detail the calibration process for the motion and force sensing systems, as well as a proof-of-concept surface discrimination experiment.
Dissertation
Matching sets of features for efficient retrieval and recognition
Trevor Darrell,Kristen Grauman +1 more
TL;DR: The pyramid match algorithm is introduced, which efficiently forms an implicit partial matching between two sets of feature vectors, and is robust to clutter or outlier features, a critical advantage for handling images with variable backgrounds, occlusions, and viewpoint changes.
Posted Content
Deep Spatial Autoencoders for Visuomotor Learning
TL;DR: In this article, a deep spatial autoencoder is used to acquire a set of feature points that describe the environment for the current task, such as the positions of objects, and then learns a motion skill with these feature points using an efficient reinforcement learning method based on local linear models.
Journal Article
Large scale visual recognition through adaptation using joint representation and multiple instance learning
Judy Hoffman,Deepak Pathak,Eric Tzeng,Jonathan Long,Sergio Guadarrama,Trevor Darrell,Kate Saenko +6 more
TL;DR: This work provides a novel formulation of a joint multiple instance learning method that includes examples from object-centric data with image-level labels when available, and also performs domain transfer learning to improve the underlying detector representation.
Posted Content
Monocular Plan View Networks for Autonomous Driving
TL;DR: In this paper, the authors propose a simple transformation of observations into a bird's eye view, also known as plan view, for end-to-end control of vehicles and pedestrians in the first person view and project them into an overhead plan view.