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 Article
Classifying Hand Gestures with a View-Based Distributed Representation
Trevor Darrell,Alex Pentland +1 more
TL;DR: A view-based representation is used to model aspects of the hand relevant to the trained gestures, and is found using an unsupervised clustering technique, which uses normalized correlation networks, with dynamic time warping in the temporal domain, as a distance function for unsuper supervised clustering.
Classifying Collisions with Spatio-Temporal Action Graph Networks.
TL;DR: It is shown that a new model for explicit representation of object interactions significantly improves deep video activity classification for driving collision detection and proposes a Spatio-Temporal Action Graph (STAG) network, which incorporates spatial and temporal relations of objects.
Posted Content
Compositional Video Synthesis with Action Graphs
TL;DR: This work introduces a generative model (AG2Vid) based on Action Graphs, a natural and convenient structure that represents the dynamics of actions between objects over time, allowing for more accurate generation of videos.
Posted Content
SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning.
TL;DR: This work shows that evaluating the learned representations with a self-supervised image rotation task is highly correlated with a standard set of supervised evaluations, and provides an algorithm (SelfAugment) to automatically and efficiently select augmentation policies without using supervised evaluations.
Proceedings Article
Dynamic Feature Selection for Classification on a Budget
TL;DR: The budget-sensitive loss LB presents a hard budget constraint by only accepting answers with CH ≤ B and can be cost-sensitive: answers given with less cost are more valuable than costlier answers.