Prof. Trevor Darrell


CS Division, University of California, Berkeley

Faculty Director, UC Berkeley PATH

Managing Director, Berkeley Vision and Learning Center

[Google Scholar Page]

Description: Description: Description: Description: C:\Users\trevor\Dropbox\t3\etc\homepage\trevordarrell.jpg

Prof. Darrell 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.


·       CAFFE – Open Source Deep Learning; Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, Trevor Darrell

·       LRCN – Long-term Recurrent Convolutional Networks; Jeff Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell; Recent Results on LCRN Language and Vision Captioning: See our project page (and also P. Dollar’s blog post on related efforts from other groups).

·       LSDA – Large Scale Detector Adaptation; Judy Hoffman, Sergio Guadarrama, Eric Tzeng, Jeff Donahue, Ross Girshick, Trevor Darrell, Kate Saenko

·       RAPTOR – Interactive Detector Learning; Daniel Göhring and Judy Hoffman and Erik Rodner and Kate Saenko, and Trevor Darrell

2015 Publications



·       End-to-End Training of Deep Visuomotor Policies, S Levine, C Finn, T Darrell, P Abbeel, arXiv preprint arXiv:1504.00702


·       Sequence to Sequence--Video to Text, S Venugopalan, M Rohrbach, J Donahue, R Mooney, T Darrell, K Saenko, arXiv preprint arXiv:1505.00487


·       Constrained Convolutional Neural Networks for Weakly Supervised Segmentation, D Pathak, P Krähenbühl, T Darrell, arXiv preprint arXiv:1506.03648




·       Deformable Part Models are Convolutional Neural Networks [full paper] [ext. abstract] Ross Girshick, Forrest Iandola, Trevor Darrell, Jitendra Malik


·       Long-Term Recurrent Convolutional Networks for Visual Recognition and Description [full paper] [ext. abstract] Jeffrey Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell


·       Long-Term Recurrent Convolutional Networks for Visual Recognition and Description [full paper] [ext. abstract] Jeffrey Donahue, Lisa Anne Hendricks, Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, Trevor Darrell


·       Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning [full paper] [ext. abstract] Judy Hoffman, Deepak Pathak, Trevor Darrell, Kate Saenko


·       Fully Convolutional Networks for Semantic Segmentation [full paper] [ext. abstract]
Jonathan Long, Evan Shelhamer, Trevor Darrell


ICCV 2015, (to appear)


·       Deep Dynamic Convolutional Networks

·       Constrained Convolutional Neural Networks for Weakly Supervised Segmentation

·       Simultaneous Deep Transfer Across Domains and Tasks

·       Sequence to Sequence Video to Text

·       Spatial Semantic Regularisation for Large Scale Object Detection



2014 Publications



·       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



















Current Teaching


CS294: Object and Activity Recognition Seminar (2011 - present)



CS280: Computer Vision (Fall 2009) 


CS294: Object and Activity Recognition Seminar (Spring 2009)


Recent Presentations


      Jan 2014 NSF Workshop Talk (pdf)

      Sept 2012 BAVM Invited Talk (pdf) (pptx)

      Sept 2011 IROS Invited Talk

      May 2010 UCB EECS Colloquium





2013 and Prior:

S. Guadarrama, N. Krishnamoorthy, G. Malkarnenkar, S. Venugopalan, R. Mooney, T. Darrell, K. Saenko, YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-shot Recognition, ICCV 2013

Y. Jia and T. Darrell, Latent Task Adaptation with Large-Scale Hierarchies, ICCV 2013

N. Zhang, R. Farrell, F. Iandola, T. Darrell, Deformable part descriptors for fine-grained recognition and attribute prediction, ICCV 2013

Y. Jia, J T Abbott, J. Austerweil, T. Griffiths, T. Darrell, Visual Concept Learning: Combining Machine Vision and Bayesian Generalization on Concept Hierarchies, NIPS 2013

Y. Jia, O. Vinyals, and T. Darrell. On Compact Codes for Spatially Pooled Features. ICML 2013

H. O. Song, R. Girshick, and T. Darrell, Discriminatively Activated Sparselets, ICML 2013

J. Donahue, J. Hoffman, E. Rodner, K. Saenko, and T. Darrell, Semi-Supervised Domain Adaptation with Instance Constraints, CVPR 2013   

V. Chu, I. McMahon, L. Riano, C. G. McDonald, Q. He, J.  Perez-Tejada, M. Arrigo, N. Fitter, J. Nappo, T. Darrell, and K. J. Kuchenbecker. Using

robotic exploratory procedures to learn the meaning of haptic adjectives. ICRA 2013. Best Cognitive Robotics Paper Award

J. Hoffman, E. Rodner, J. Donahue, T. Darrell, K. Saenko, Efficient Learning of Domain-invariant Image Representations, ICLR 2013 Conference

O. Vinyals, Y. Jia, T. Darrell, Why Size Matters: Feature Coding as Nystrom Sampling, ICLR 2013 Workshop

S. Karayev, M. Fritz, T. Darrell, Timely Object Recognition, NIPS 2012

O. Vinyals, Y. Jia, L. Deng, T. Darrell, Learning with Recursive Perceptual Representations, NIPS 2012

S. Chung, C. Christoudias, T. Darrell, S. Ziniel, L. Kalish, A Novel Image Based Tool to Reunite Children with Their Families after Disasters, AEMJ 

T. Althoff, H. O. Song, T. Darrell, Detection Bank: An Object Detection Based Video Representation for Multimedia Event Recognition, ACM MM 2012

J. Hoffman, B. Kulis, T. Darrell, K. Saenko,  Discovering Latent Domains for Multisource Domain Adaptation, ECCV 2012

H. O. Song, S. Zickler, T. Althoff, R. Girshick, M. Fritz, C. Geyer, P. Felzenszwalb, T. Darrell, Sparselet Models for Efficient Multiclass Object Detection, ECCV 2012

S. Miller, J. Van Den Berg, M. Fritz, T. Darrell, K. Goldberg, P. Abbeel, A geometric approach to robotic laundry folding, IJRR 2012

S. Virtanen, Y. Jia, A. Klami, T. Darrell. Factorized Multi-modal Topic Model. UAI 2012

Y. Xiong, K. Saenko, T. Zickler, T. Darrell, From Pixels to Physics: Probabilistic Color De-rendering, CVPR 2012.

N. Zhang, R. Farrell, T. Darrell. Pose Pooling Kernels for Sub-category Recognition. CVPR 2012

Y. Jia, C. Huang, T. Darrell. Beyond Spatial Pyramids: Receptive Field Learning for Pooled Image Features, CVPR 2012

Y. Jia and T. Darrell, Heavy-tailed Distances for Gradient Based Image Descriptors, NIPS 2011

R. Farrell, O. Oza, N. Zhang, V. Morariu, T. Darrell, and L. Davis, Birdlets: Subordinate Categorization Using Volumetric Primitives and Pose-Normalized Appearance, ICCV 2011.

T. Tuytelaars, M. Fritz, K. Saenko, and T. Darrell, The NBNN Kernel, ICCV 2011.

Y. Jia, M. Salzmann, and T. Darrell, Learning Cross-modality Similarity for Multinomial Data, ICCV 2011.

S. Karayev, A. Janoch, Y. Jia, J. Barron, M. Fritz, K. Saenko, and T. Darrell, A Category-level 3-D Database: Putting the Kinect to Work, in ICCV 2011 Workshop on Consumer Depth Cameras for Computer Vision, 2011.

H. O. Song, M. Fritz, C. Gu and T. Darrell, Visual Grasp Affordances From Appearance-Based Cues, ICCV Workshop on Challenges and Opportunities in Robot Perception, 2011

P. Wang, S. Miller, M. Fritz, T. Darrell, and P. Abbeel, Perception for the Manipulation of Socks, IROS 2011.

K. Saenko, Y. Jia, M. Fritz, J. Long, A. Janoch, A. Shyr, S. Karayev and T. Darrell, Practical 3-D Object Detection Using Category and Instance-Level Appearance Models, IROS 2011

S. Miller, M. Fritz, T. Darrell, and P. Abbeel, Parametrized Shape Models for Clothing, ICRA 2011.

S. Karayev, M. Fritz, S. Fidler, and T. Darrell,  A Probabilistic Model for Recursive Factorized Image Features, CVPR 2011.

B. Kulis, K. Saenko, and T. Darrell, What You Saw is Not What You Get: Domain Adaptation Using Asymmetric Kernel Transforms, CVPR 2011.

A. Shyr, T. Darrell, M. Jordan, and R. Urtasun, Supervised Hierarchical Pitman-Yor Process for Natural Scene Segmentation, CVPR 2011.

T. Owens, K. Saenko, A. Chakrabarti, Y. Xiong, T. Zickler, and T. Darrell.  Learning Object Color Models from Multi-view Constraints, CVPR 2011.

A. Eden, M. Christoudias, and T. Darrell, Finding Lost Children, POV 2011.

Y. Jia, M. Salzmann, and T. Darrell, Factorized Latent Spaces with Structured Sparsity, NIPS 2010.

M. Fritz, K. Saenko, and T. Darrell, Size Matters: Metric Visual Search Constraints from Monocular Metadata,  NIPS 2010.

G. Friedland, O. Vinyals, and T. Darrell, Multimodal Location Estimation. ACM Multimedia 2010.

K. Saenko, B. Kulis, M. Fritz, and T. Darrell, Adapting Visual Category Models to New Domains, ECCV 2010.

M. Christoudias, R. Urtasun, M. Salzmann, and T. Darrell, Learning to Recognize Objects from Unseen Modalities, ECCV 2010.

A. Kapoor, K. Grauman, R. Urtasun, and T. Darrell, Gaussian Processes for Object Categorization, IJCV, 2010.

M. Salzmann, C. H. Ek, R. Urtasun, and T. Darrell. Factorized orthogonal latent spaces. UAI 2010.

M. Fritz, M. Black, G. Bradski, and T. Darrell, An Additive Latent Feature Model for Transparent Object Recognition, NIPS 2009.

Z. Stone, T. Zickler, and T. Darrell, Toward Large-Scale Face Recognition Using Social Network Context, Proc. of the IEEE 2010

B. Kulis and T. Darrell, Learning to Hash with Binary Reconstructive Embeddings, NIPS 2009.

K. Saenko and T. Darrell, Filtering Abstract Senses From Image Search Results, NIPS 2009.

A. Quattoni, X. Carreras, M. Collins, and T. Darrell, An Efficient Projection for L-1/L-Infinity Regularization, ICML 2009.

T. Yeh and T. Darrell, Fast Concurrent Object Localization and Recognition, CVPR 2009.

M. Christoudias, R. Urtasun, A. Kapoor and T. Darrell, Co-training with Noisy Perceptual Observations, CVPR 2009.

A. Geiger, R. Urtasun, and T. Darrell, Rank Priors for Continuous Non-Linear Dimensionality Reduction, CVPR 2009.

M. Frampton, R. Fernandez, P. Ehlen, M. Christoudias, T. Darrell, and S. Peters (2009) Who is ``You? Combining Linguistic and Gaze Features to Resolve Second-Person References in Dialogue, EACL 2009.

K. Saenko, K. Livescu, J. Glass, and T. Darrell, Multistream Articulatory Feature-Based Models for Visual Speech Recognition, TPAMI 2009

K. Saenko, and T. Darrell, Unsupervised Learning of Visual Sense Models for Polysemous Word, NIPS 2008.

T. Yeh, J. Lee, and  T. Darrell, Photo-based Question Answering, ACM Multimedia 2008.

T. Yeh, and T. Darrell, Multimodal Question Answering for Mobile Devices, IUI 2008.

M. Christoudias, R. Urtasun and T. Darrell, Multi-View Learning in the Presence of View Disagreement, UAI 2008.

R. Urtasun, D. J. Fleet, A. Geiger, J. Popovic, T. Darrell and N. D. Lawrence, Topologically-Constrained Latent Variable Models, ICML 2008.

M. Christoudias, R. Urtasun and T. Darrell, Unsupervised Feature Selection via Distributed Coding for Multi-view Object Recognition, CVPR 2008.

A. Quattoni, M. Collins, and T. Darrell, Transfer Learning for Image Classification with Sparse Prototype Representations, CVPR 2008.

T. Yeh, J. Lee, and  T. Darrell, Dynamic Visual Category Learning, CVPR 2008.

R. Urtasun, and T. Darrell, Sparse probabilistic regression for activity-independent human pose inference, CVPR 2008.

T. Yeh, J. Lee, and T. Darrell, Scalable classifiers for Internet vision tasks, IEEE Workshop on Internet Vision 2008.

Z. Stone, T. Zickler, and T. Darrell, Autotagging Facebook: Social Network Context Improves Photo Annotation,   IEEE Workshop on Internet Vision 2008.



Older publications:



Older projects, classes, and meetings organized


Darrell Group (UCB/ICSI) – (2013 Group Spotlight Presentations)


     Dr. Stefanie Jegelka (Joint with Mike Jordan)

     Dr. Sergio Guardarrama

     Dr. Jiashi Feng

     Dr. Marcus Rohrback

PhD Students: 

Sergey Karayev

Yanqqing Jia

Hyun Oh Song

Ning Zhang

Jon Long

Judy Hoffman

Jeff Donahue

Evan Shelhammer

Eric Tzeng

Lisa Hendricks




Previous Postdocs (not including former students)

     Dr. Eric Rodner


     Dr. Ryan Farrell


     Dr. Lorenzo Riano 


     Dr. Daniel Goehring

     Dr. Brian Kulis

Dr. David Demirdjian


Dr. Raquel Urtasun


Dr. Mario Fritz


Dr. Matthieu Salzmann


Dr. Sanja Fidler (visiting)


Dr. Nicholas Cebron


Dr. Carl Ek


Dr. Peer Stelldinger


Graduated PhD. Students:

Alex Shyr, Incorporating Supervision for Visual Recognition and Segmentation, Sept 2011 [Startup]


Ashley Eden, Finding Lost Children, Dec 2010 [Dreamworks]

Mario Christoudas, Probabilistic Models for Semi-Supervised Learning and Coding, Aug 2009 [Postdoc, EPFL]

Kate Saenko, Image Sense Disambiguation: A Multimodal Approach, Aug 2009 [Faculty UML]

Tom Yeh, Interacting with Computers using Images for Search and Automation, May 2009 [Postdoc, UMD]

Ariadna Quattoni, Transfer Learning Algorithms for Image Classification, May 2009 [Postdoc, Barcelona]

Sy Bor Wang, Communication Error Detection Using Facial Expressions, May 2008 [Research Scientist, Trimble Navigations]


Louis-Philippe Morency, Dialogue Context and Visual Gesture Recognition, Oct 2006 [Research Scientist, USC]


Kristen Grauman, Matching sets of features for efficient retrieval and recognition, Aug. 2006 [Assistant Professor, CS, University of Texas, Austin]


Leonid Taycher, Statistical methods for dynamic visual processing, Aug 2006 [Google Boston]


Kevin Wilson, Learning Uncertainty Models for Audiovisual Speech Source Localization in Real-World Environments, Aug 2006 [Research Scientist, MERL]


Gregory Shakhnarovich, Learning Features for Visual Classification, Oct. 2005 [Assistant Professor, TTI-C]


Ali Rahimi, Learning to Transform Time Series with a Few Examples, Oct. 2005 [Intel Research Laboratories, Berkeley]


Graduated MS Students:

Allie Janoch

Trevor Owens

 Previous Graduate Visitors:

Tim Althoff


Tobias Baumgartner