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
Book ChapterDOI
SkipNet: Learning Dynamic Routing in Convolutional Networks
TL;DR: This work introduces SkipNet, a modified residual network, that uses a gating network to selectively skip convolutional blocks based on the activations of the previous layer, and proposes a hybrid learning algorithm that combines supervised learning and reinforcement learning to address the challenges of non-differentiable skipping decisions.
Posted Content
Large-Scale Study of Curiosity-Driven Learning
TL;DR: The authors performed a large-scale study of purely curiosity-driven learning, i.e., without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite, and found that curiosity is a type of intrinsic reward function which uses prediction error as reward signal.
Proceedings ArticleDOI
Localizing Moments in Video with Natural Language
Lisa Anne Hendricks,Lisa Anne Hendricks,Oliver Wang,Eli Shechtman,Josef Sivic,Trevor Darrell,Bryan Russell +6 more
TL;DR: In this paper, a Moment Context Network (MCNCLN) is proposed to localize natural language queries in videos by integrating local and global video features over time, which can identify a specific temporal segment, or moment, from a video given a natural language text description.
Patent
Background estimation and segmentation based on range and color
TL;DR: In this article, the color segmentation of a foreground object in a given frame of an image sequence is carried out by comparing the image frames with background statistics relating to range and normalized color in a complementary manner.
Book ChapterDOI
Grounding of Textual Phrases in Images by Reconstruction
TL;DR: A novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly, and demonstrates the effectiveness on the Flickr 30k Entities and ReferItGame datasets.