Brian Price
Principal Scientist
Adobe Research
Email:
As a research scientist at Adobe, I research Computer Vision, develop new technologies, transfer them to Adobe products, and work with universities and PhD students through collaborations and internships. (See full bio here)
Research Interests: Computer Vision, Graphics, and Machine Learning, especially segmentation (interactive object selection, matting, panoptic/semantic segmentation, video segmentation), image synthesis, and document understanding.
Latest News
ICDAR 2021
Sep 8, 2021
This week is ICDAR. I gave a talk on our DVQA work at the DocVQA workshop. I also have a paper there, "Visual FUDGE: Form Understanding via Dynamic Graph Editing." Check it out on my Papers page.
CVPR 2021
Jun 21, 2021
I'm attending CVPR (remotely) this week. I have one paper, Rethinking Text Segmentation: A Novel Dataset and a Text-Specific Refinement Approach. Check it out on Thursday or on my Papers page.
WACV
Jan 6, 2021
I have a paper being presented in WACV 2021 today, Deep Interactive Thin Object Selection. Head to my Papers page to check it out.
Recent Publications
Visual FUDGE: Form Understanding via Dynamic Graph Editing
Brian Davis, Bryan Morse, Brian Price, Chris Tensmeyer, Curtis Wigington
ICDAR 2021
[Paper]
Rethinking Text Segmentation: A Novel Dataset and a Text-Specific Refinement Approach
Xingqian Xu, Zhifei Zhang, Zhaowen Wang, Brian Price, Zhonghao Wang, Humphrey Shi
CVPR 2021
[PDF]
Measuring Human Perception to Improve Handwritten Document Transcription
Samuel Grieggs, Bingyu Shen, Greta Rauch, Pei Li, Jiaqi Ma, David Chiang,
Brian Price, Walter Scheirer
PAMI 2021
[PDF]
Recent Patents
Identifying Target Objects using Scale-Diverse Segmentation Neural Networks
Scott Cohen, Long Mai, Jun Hao Liew, Brian Price
GB Patent 2583794. Nov 10, 2021.
Joint Depth Estimation and Semantic Segmentation from a Single Image.
Scott Cohen, Zhe Lin, Brian Price, Xiaohui Shen, Peng Wang
CN Patent ZL2016101833670. Oct. 22, 2021.
Image Matting using Deep Learning
Brian Price, Scott Cohen, Ning Xu, Stephen Schiller
AU Patent 2017254848. Oct. 14, 2021.
Technologies Highlights
Object-aware Refine Edge
A few years back I helped to advise on the creation of the Select and Mask workspace in Photoshop that allows users to select objects in images. Photoshop added a new mode that allows for improved extraction of hair for complex images. This mode is a follow on to our Deep Image Matting paper from CVPR 2017.