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
Posted Content
Hierarchical Style-based Networks for Motion Synthesis
TL;DR: This paper proposes a self-supervised method for generating long-range, diverse and plausible behaviors to achieve a specific goal location through bi-linear transformation modelling, and demonstrates the generated sequences are useful as subgoals for actual physical execution in the animated world.
Proceedings ArticleDOI
Supervised hierarchical Pitman-Yor process for natural scene segmentation
TL;DR: This paper adds label information into the previously unsupervised model by adding constraints on the parameter space during the variational learning phase and evaluates the effectiveness of the formulation on the La-belMe natural scene dataset.
Book ChapterDOI
Light field appearance manifolds
TL;DR: A novel 3D appearance model using image-based rendering techniques, which can represent complex lighting conditions, structures, and surfaces and overcomes the limitations of polygonal based appearance models and uses light fields that are acquired in real-time.
Posted Content
Similarity R-C3D for Few-shot Temporal Activity Detection.
TL;DR: The Similarity R-C3D method outperforms previous work on three large-scale benchmarks for temporal activity detection in the few-shot setting and is end-to-end trainable and can benefit from more few- shot examples.
Posted Content
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data
Lisa Anne Hendricks,Subhashini Venugopalan,Marcus Rohrbach,Raymond J. Mooney,Kate Saenko,Trevor Darrell +5 more
TL;DR: Deep Compositional Captioner (DCC) as mentioned in this paper is proposed to address the task of generating descriptions of novel objects which are not present in paired image-sentence datasets by leveraging large object recognition datasets and external text corpora.