Trevor Darrell

Biography

In the beginning of July 2015 Prof. Darrell became the new Faculty Director of the California Program for Advanced Transportation Technology (PATH) at the University of California, Berkeley.  He is on the faculty of the CS Division of the EECS Department at UC Berkeley and he is also appointed at the UC-affiliated International Computer Science Institute (ICSI).  Darrell’s group develops algorithms for large-scale perceptual learning, including object and activity recognition and detection, for a variety of applications including multimodal interaction with robots and mobile devices. His interests include computer vision, machine learning, computer graphics, and perception-based human computer interfaces. Prof. Darrell was previously on the faculty of the MIT EECS department from 1999-2008, where he directed the Vision Interface Group. He was a member of the research staff at Interval Research Corporation from 1996-1999, and received the S.M., and PhD. degrees from MIT in 1992 and 1996, respectively. He obtained the B.S.E. degree from the University of Pennsylvania in 1988, having started his career in computer vision as an undergraduate researcher in Ruzena Bajcsy's GRASP lab.

2014 PUBLICATIONS

ICML

• DECAF: A deep convolutional activation feature for generic visual recognition; Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, Trevor Darrell
• On learning to localize objects with minimal supervision; Hyun Oh Song, Ross Girshick, Stefanie Jegelka, Julien Mairal, Zaid Harchaoui, Trevor Darrell

CVPR

•  PANDA: Pose Aligned Networks for Deep Attribute Modeling; Ning Zhang, Manohar Paluri, Marc'Aurelio Ranzato, Trevor Darrell, Lubomir Bourdev
• Rich feature hierarchies for accurate object detection and semantic segmentation; Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik
• Anytime Recognition of Objects and Scenes; Sergey Karayev, Mario Fritz, Trevor Darrell
• Learning Scalable Discriminative Dictionary with Sample Relatedness; Jiashi Feng, Stefanie Jegelka, Shuicheng Yan, Trevor Darrell
• Continuous Manifold Based Adaptation for Evolving Visual Domains; Judy Hoffman, Trevor Darrell, Kate Saenko

ICRA

• Interactive Adaptation of Real-Time Object Detectors; Daniel Göhring and Judy Hoffman and Erik Rodner and Kate Saenko, and Trevor Darrell

RSS

• Open-vocabulary Object Retrieval; Sergio Guadarrama, Erik Rodner, Kate Saenko, Ning Zhang, Ryan Farrell, Jeff Donahue, Trevor Darrell

BMVC

• Recognizing Image Style; Sergey Karayev, Aaron Hertzmann, Holger Winnemoeller, Aseem Agarwala, Trevor Darrell

ECCV

• Part-based R-CNNs for Fine-grained Category Detection, Ning Zhang, Jeff Donahue, Ross Girshick, Trevor Darrell, UC Berkeley

MM

• CAFFE: Convolutional Architecture for Fast Feature Embedding; Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, Trevor Darrell

PAMI

• Modeling Radiometric Uncertainty for Vision with Tone-mapped Color Images; Ying Xiong, Daniel Scharstein, Ayan Chakrabarti, Trevor Darrell, Baochen Sun, Kate Saenko, Todd Zickler

NIPS

• Large Scale Detector Adaptation; Judy Hoffman, Sergio Guadarrama, Eric Tzeng, Jeff Donahue, Ross Girshick, Trevor Darrell, Kate Saenko
• Weakly-supervised Discovery of Visual Pattern Configurations; Hyun Oh Song, Yong Jae Lee, Stefanie Jegelka, Trevor Darrell
• Do Convnets Learn Correspondence? Jon Long, Ning Zhang, Trevor Darrell

arXiv

• DenseNet: Implementing Efficient ConvNet Descriptor Pyramids; Forrest Iandola, Matt Moskewicz, Sergey Karayev, Ross Girshick, Trevor Darrell, Kurt Keutzer
• One-Shot Adaptation of Supervised Deep Convolutional Models; Judy Hoffman, Eric Tzeng, Jeff Donahue, Yangqing Jia, Kate Saenko, Trevor Darrell