Jonathan Brandt

Fellow, Director of the Media Intelligence Lab

San Jose

Jonathan is the Director of the Media Intelligence Lab at Adobe Research. His areas of research interest span a broad range of topics in computer vision, machine learning, and artificial intelligence.

The Media Intelligence Lab is an interdisciplinary research team that contributes vision and imaging technologies across Adobe’s product line, including Photoshop, Lightroom, Photoshop Elements, Adobe Experience Manager, After Effects, Premiere Pro, and Adobe Stock. Additionally, the lab pursues a vibrant research program in natural language understanding with many applications spanning Adobe’s PDF ecosystem, as well as to general user interaction, including intelligent help and search.

In the last several years, the Media Intelligence Lab has been pioneering the application of Deep Learning to a range of vision and language problems relevant to Adobe’s products. Fundamentally, they seek high-level representations at the cusp of images and language that can serve as the currency of intelligence for creative tools.

The Media Intelligence Lab has an active student internship program and numerous university collaboration projects. Much of our research appears regularly in major vision conferences such CVPR, ICCV, and ECCV. Jonathan invites computer vision, machine learning, natural language processing and artificial intelligence PhD students to contact him regarding internships.

Prior to joining Adobe in 2003, he was a member of the technical staff at Silicon Graphics and a visiting professor at the Japan Advanced Institute of Science and Technology in Ishikawa, Japan. His first job out of school was at the NASA Jet Propulsion Lab, where he was an engineer on the Galileo project.

He received his master’s and Ph.D. in computer science at the University of California, Davis, and a B.S. in electrical engineering from the University of Illinois, Urbana Champaign.

Publications

StreamHover: Livestream Transcript Summarization and Annotation

Cho, S., Dernoncourt, F., Ganter, T., Bui, T., Lipka, N., Chang, W., Jin, H., Brandt, J., Foroosh, H., Liu, F. (Nov. 9, 2021)

Empirical Methods in Natural Language Processing (EMNLP)

Spatial-Semantic Image Search by Visual Feature Synthesis

Mai, L., Jin, H., Lin, Z., Fang, C., Brandt, J., Liu, F. (Jul. 28, 2017)

Spotlight Presentation

Computer Vision and Pattern Recognition (2017)

Top-down Neural Attention by Excitation Backprop

Zhang, J., Lin, Z., Brandt, J., Shen, X., Sclaroff, S. (Oct. 8, 2016)

European Conference on Computer Vision (ECCV)

Top-down Neural Attention by Excitation Backprop

Zhang, J., Lin, Z., Brandt, J., Shen, X., Sclaroff, S., Zhang, Z. (Sep. 12, 2016)

European Conference on Computer Vision (ECCV)

Shortlist Selection with Residual-Aware Distance Estimator for K-Nearest Neighbor Search

Heo, J., Lin, Z., Shen, X., Brandt, J., Yoon, S. (Jun. 26, 2016)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

A Multi-Level Contextual Model For Person Recognition in Photo Albums

Li, H., Brandt, J., Lin, Z., Shen, X., Hua, G. (Jun. 26, 2016)

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Discovering Primary Objects in Videos by Saliency Fusion and Iterative Appearance Estimation

Yang, J., Zhao, G., Yang, J., Shen, X., Lin, Z., Price, B., Brandt, J. (Jun. 1, 2016)

IEEE Transactions on Circuits and Systems for Video Technology

DeepFont: Identify Your Font from an Image

Wang, Z., Yang, J., Jin, H., Shechtman, E., Agarwala, A., Brandt, J., Huang, T. (Oct. 1, 2015)

ACM International Conference on Multimedia (MM'15)

DeepFont: A System for Font Recognition and Similarity

Wang, Z., Yang, J., Jin, H., Brandt, J., Shechtman, E., Agarwala, A., Wang, Z., Song, Y., Hseih, J., Kong, S., Huang, T. (Oct. 1, 2015)

ACM International Conference on Multimedia (MM'15)

A Convolutional Neural Network Cascade for Face Detection

Li, H., Lin, Z., Shen, X., Brandt, J., Hua, G. (Jun. 23, 2015)

IEEE Conference on Computer Vision and Pattern Recognition

Real-World Font Recognition Using Deep Network and Domain Adaptation

Wang, Z., Yang, J., Jin, H., Shechtman, E., Agarwala, A., Brandt, J., Huang, T. (May. 7, 2015)

ICLR 2015

Selective Pooling Vector for Fine-Grained Recognition

Chen, G., Yang, J., Jin, H., Shechtman, E., Brandt, J., Han, T. (Jan. 1, 2015)

IEEE Winter Conference on Applications of Computer Vision (WACV'15)

Consensus of Regression for Occlusion-Robust Facial Feature Localization

Yu, X., Lin, Z., Brandt, J., Metaxas, D. (Sep. 6, 2014)

European Conference on Computer Vision

Nonparametric Context Modeling of Local Appearance for Pose- and Expression- Robust Facial Landmark Localization

Smith, B., Brandt, J., Lin, Z., Zhang, L. (Jun. 24, 2014)

Computer Vision and Pattern Recognition

Efficient Boosted Exemplar-Based Face Detection

Li, H., Lin, Z., Brandt, J., Shen, X., Hua, G. (Jun. 24, 2014)

Computer Vision and Pattern Recognition

Spatially-Constrained Similarity Measure for Large-Scale Object Retrieval

Shen, X., Lin, Z., Brandt, J., Wu, Y. (Jun. 1, 2014)

IEEE Trans. on Pattern Analysis and Machine Intelligence

Large-scale visual font recognition

Chen, G., Yang, J., Jin, H., Brandt, J., Shechtman, E., Agarwala, A., Han, T. (Jun. 1, 2014)

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)

Exemplar-based Graph Matching for Robust Facial Landmark Localization

Zhou, F., Brandt, J., Lin, Z. (Dec. 1, 2013)

Proceedings of the IEEE International Conference on Computer Vision (ICCV 2013), December 2013

Probabilistic Elastic Part Model for Unsupervised Face Detector Adaptation

Li, H., Hua, G., Lin, Z., Brandt, J. (Dec. 1, 2013)

International Conference of Computer Vision

Detecting and Aligning Faces by Image Retrieval

Shen, X., Lin, Z., Brandt, J., Wu, Y. (Jun. 25, 2013)

Proceedings of IEEE conference on Computer Vision and Pattern Recognition (CVPR), June 2013.

Exemplar-Based Face Parsing

Smith, B., Zhang, L., Brandt, J., Lin, Z., Yang, J. (Jun. 25, 2013)

Proceedings of IEEE conference on Computer Vision and Pattern Recognition (CVPR), June 2013.

Probabilistic Elastic Matching for Pose Variant Face Verification

Li, H., Hua, G., Lin, Z., Brandt, J., Yang, J. (Jun. 25, 2013)

Proceedings of IEEE conference on Computer Vision and Pattern Recognition (CVPR), June 2013.

Interactive facial feature localization

Le, V., Brandt, J., Lin, Z., Bourdev, L., Huang, T. (Oct. 7, 2012)

European Conf. Computer Vision

Mobile Product Image Search by Automatic Query Object Extraction

Shen, X., Lin, Z., Brandt, J., Wu, Y. (Oct. 7, 2012)

European Conference of Computer Vision

Object Retrieval and Localization with Spatially-Constrained Similarity Measure and k-NN Re-ranking

Shen, X., Lin, Z., Brandt, J., Avidan, S., Wu, Y. (May. 1, 2012)

IEEE Conference on Computer Vision and Pattern Recognition , 2012.

A Local Bag-of Features Model for Large-Scale Object Retrieval

Lin, Z., Brandt, J. (Sep. 5, 2010)

European Conference on Computer Vision , 2010.

Transform Coding for Fast Approximate Nearest Neighbor Search in High Dimensions

Brandt, J. (Feb. 1, 2010)

In Proc. IEEE Conference on Vision and Pattern Recognition

Robust object detection via soft cascade

Bourdev, L., Brandt, J. (Sep. 13, 2005)

In 2005 Conference on Computer Vision and Pattern Recognition (CVPR 2005) , 236–243

Derivative-based optical flow estimation: controlled comparison of first- and second-order methods

Brandt, J. (Dec. 30, 1994)

MVA '94: IAPR Workshop on Machine Vision Applications , pp. 464--469, December 1994

Finite-differencing errors in gradient-based optical flow estimation

Brandt, J. (Nov. 29, 1994)

IEEE International Conference on Image Processing , Vol. 2, pp. 775--779, Nov. 1994

Analysis of bias in gradient-based optical-flow estimation

Brandt, J. (Oct. 31, 1994)

IEEE Asilomar Conference on Signals, Systems, and Computers , pp. 721--725, October 1994

The skeleton metric: a tool for quantitative shape comparison

Brandt, J., Algazi, V. (Feb. 14, 1993)

SPIE Imaging Science and Technology '93 , February 1993

Multi-scale isotropic morphology and shape approximation using the Voronoi diagram

Brandt, J. (Nov. 29, 1992)

SPIE Vision Geometry , November 1992

Continuous skeleton computation by Voronoi diagram

Brandt, J., Algazi, V. (May. 31, 1992)

CVGIP: Image Understanding , 55(3):329-338, May 1992

Describing a solid with the three-dimensional skeleton

Brandt, J. (Jan. 30, 1992)

Curves and Surfaces in Computer Vision and Graphics III , Joseph D. Warren, Editor, Proc. SPIE 1830, 258-269 (1992)

Lossy encoding of document images with the continuous skeleton

Brandt, J., Algazi, V. (Jan. 30, 1992)

Visual Communications and Image Processing '92 , Petros Maragos, Editor, Proc. SPIE 1818, 663-673 (1992)

An algorithm for the computation of the Hutchinson distance

Brandt, J., Cabrelli, C., Molter, U. (Oct. 25, 1991)

Information Processing Letters , 40:113-117, October 25, 1991

Computing a stable, connected skeleton from discrete data

Brandt, J., Algazi, V. (Jul. 30, 1991)

IEEE Conf. on Computer Vision and Pattern Recognition , pp. 666-667, June 1991

Medial axis representation and encoding of scanned documents

Brandt, J., Jain, A., Algazi, V. (Jun. 30, 1991)

Journal of Visual Communication and Image Representation , 2(2):151-165, June 1991

Using color image maps to study collisions in the three-body problem

Brandt, J., Park, A. (Jan. 30, 1991)

The Visual Computer , 6(7):13-18, 1991

A medial axis transform algorithm for compression and vectorization of document images

Brandt, J., Jain, A. (May. 31, 1989)

IEEE Int. Conf. on Acoustics, Speech, and Signal Processing . pp. 1850-1853. May 1989

News