I teach machines to see like people and interact with people. As modern machines struggle to fully conceptualize the visual world, my research bootstraps machine learning using frameworks from behavioral and social sciences.
Ranjay Krishna is an Assistant Professor at the Paul G. Allen School of Computer Science & Engineering. His research lies at the intersection of computer vision and human computer interaction. This research has received best paper, outstanding paper, and orals at CVPR, ACL, CSCW, NeurIPS, UIST, and ECCV, and has been reported by Science, Forbes, the Wall Street Journal, and PBS NOVA. His research has been supported by Google, Amazon, Cisco, Toyota Research Institute, NSF, ONR, and Yahoo. He holds a bachelor's degree in Electrical & Computer Engineering and in Computer Science from Cornell University, a master's degree in Computer Science from Stanford University and a Ph.D. in Computer Science from Stanford University. RECENT PAPER HIGHLIGHTS
[Dec 2024] Our Multilingual diversity for LLMs paper will appear as an Spotlist at NeurIPS 2024, awarded to top 5% of submissions. [June 2024] Our Visual Program Distillation paper will appear as an Oral at CVPR 2024, awarded to top 5% of submissions. [May 2024] Our Selective Visual Representations paper will appear as a Spotlight at ICLR 2024, awarded to top 5% of submissions. [Dec 2023] Our DataComp paper will appear as an Oral at NeurIPS 2023, awarded to top (0.6%) submissions. [Dec 2023] Our Quilt-1M will appear as an Oral at NeurIPS 2023, awarded to top (0.6%) submissions. [Oct 2023] Our paper on Explanations and human-AI decision making got awarded a Best Paper Honorable Mention at CSCW 2023 [Mar 2023] Our CREPE paper was recognized as a Highlight at CVPR 2023, awarded to top 2.5% of submissions. [Nov 2022] Our work won the Madrona Prize for the most commercializable research project. [Nov 2022] Our work at PNAS 2022 has been covered by the press at Science and TechXplore. [Sep 2022] Our large scale AI deployment interacting and learning from real human interactions online appears at PNAS 2022. [Oct 2021] Our active learning paper will receive an Outstanding paper at ACL 2021, awarded to top 6 papers at the conference. RECENT TALKS [Jun 2024] One of the keynotes at CVPR 2024 workshop on Evaluation of Generative Foundation Models [Jun 2024] One of the keynotes at CVPR 2024 workshop on Computer Vision with Humans in the Loop [April 2023] Invited DUB seminar talk at the University of Washington [Oct 2023] One of the keynotes at ICCV 2023 workshop on Scene Graphs and Graph Representation Learning [Oct 2023] One of the keynotes at ICCV 2023 workshop on On Closing The Loop Between vision an language [Aug 2023] Distinguished talk on Compositionally at Salesforce AI [July 2023] Talk on Embodied Intelligence at the AAAI 2023 Inaugural Summer Symposium on Embodied Intelligence [Jun 2023] One of the keynotes at CVPR 2023 workshop on New Frontiers in Vision and Language Reasoning. [Oct 2021] Talk at ICCV 2021 workshop on Compositionality in Computer Vision. [Jul 2021] Talk at ICML 2021 workshop on Humans in the learning loop . [Apr 2021] Ph.D. defence talk at Stanford University and graduated with a distinction in teaching for instructing 5 courses. RECENT WORKSHOPS [Jun 2024] Synthetic Data for Computer Vision at CVPR 2024 [Oct 2023] International Challenge on Compositional and Multimodal Perception at ICCV 2023 [Jul 2023] Artificial Intelligence and Human-Computer Interaction at ICML 2023 [Oct 2022] Compositionality in Computer Vision workshop at ECCV 2022. [Oct 2021] Compositionality in Computer Vision workshop at ICCV 2021. [Aug 2020] International Challenge on Compositional and Multimodal Perception workshop at ECCV 2020. [Jun 2020] Compositionality in Computer Vision workshop at CVPR 2020. Compositionality in Computer Vision workshop at CVPR 2020. [Jun 2020] ActivityNet Challenge on Dense Captioning Events in Videos at CVPR 2020. [Oct 2019] Scene Graph Representation and Learning. [Oct 2019] Co-organizer and a guest editor for an IEEE TPAMI special issue on Graphs in Vision and Pattern Analysis. Pre-prints & working papers
ACademic Publications
Non-Archival PAPERS
|
Ph.D. @ Stanford University, 2021
Co-advised by Fei-Fei Li and Michael Bernstein. Curriculum Vitae [2023] Google scholar Research statement [2021] Teaching statement [2021] Diversity statement [2021] CONTACT
ranjay [at] cs [dot] washington [dot] edu Bill & Melinda Gates Center Room 304 3800 E Stevens Way NE, Seattle, WA 98195 TEACHING
University of Washington: CSE 599H: AI vs IA [2023] CSE 493G1: Deep learning [2023] [2024] CSE 455: Computer Vision [2024] Stanford University: CS231N: Convolutional Neural Networks for Visual Recognition [2020] [2021] CS131 Computer Vision: Foundations and Applications [2019] [2018] [2017] - [Link to all assignments] - [Link to the crowdsourced class notes book] RESEARCH GROUP
PhD students
Cheng-Yu Hsieh
(2022-) Jieyu Zhang
(2023-) Chenhao Zheng
(2024-) Masters and undergraduate students
Long term collaborating PhD students
Yushi Hu with Noah Smith
Arijit Ray with Kate Saenko
Former PostDocs
- Wei-Chiu Ma (Faculty @ Cornell) Former masters students - Sho Arora - Ines Chami - Apoorva Dornadula - Oliver Groth - Mayank Kumar - Mona Gandhi - Donsuk Lee Former undergraduate students - Stephanie Chen - Vincent Chen - Shubhang Desai - Omer Gul - Kenji Hata - Jerry Hong - Khaled Jedoui - Pranav Khadpe - Joshua Kravitz - Michelle Lam - Jihyeon Janel Lee - Austin Narcomey - Junwon Park Former PhD mentees - Sebastin Santy - Done He - Jingwei Ji - Siddharth Karamcheti Selected TalksVenue: CVPR 2024 - Computer Vision and Pattern Recognition
Panel: CVPR: past, present, and future Venue: CVPR 2020 - Computer Vision and Pattern Recognition
Title: Compositionally in Computer Vision [slides][video][workshop] Venue: CVPR 2020 - Computer Vision and Pattern Recognition
Title: Dense Captioning Events in Videos [slides][video][workshop] Venue: ECCV 2016 - European Conference on Computer Vision
Title: Visual Relationship Detection with Language Priors [pdf][project][slides][poster][video] Venue: CHI 2016 - Conference on Human Factors in Computer Systems
Title: Embracing Error to Enable Rapid Crowdsourcing [pdf][slides] MISCELLANEOUS
Trailer for a documentary
Venue: PBS NOVA Title: Can we build a brain? Year: 2018 Complete documentary
Venue: PBS NOVA Title: Can we build a brain? Year: 2018 |