Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Ranjay Krishna

Ranjay Krishna

On the Opportunities and Risks of Foundation Models


Aug 18, 2021
Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Kohd, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, Aditi Raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W. Thomas, Florian Tramèr, Rose E. Wang, William Wang, Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou, Percy Liang

Figure 1 for On the Opportunities and Risks of Foundation Models
Figure 2 for On the Opportunities and Risks of Foundation Models
Figure 3 for On the Opportunities and Risks of Foundation Models
Figure 4 for On the Opportunities and Risks of Foundation Models
* Authored by the Center for Research on Foundation Models (CRFM) at the Stanford Institute for Human-Centered Artificial Intelligence (HAI) 
  Access Paper or Ask Questions

Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering


Jul 06, 2021
Siddharth Karamcheti, Ranjay Krishna, Li Fei-Fei, Christopher D. Manning

Figure 1 for Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
Figure 2 for Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
Figure 3 for Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
Figure 4 for Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
* Accepted at ACL-IJCNLP 2021. 17 pages, 16 Figures 
  Access Paper or Ask Questions

AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning


Mar 30, 2021
Madeleine Grunde-McLaughlin, Ranjay Krishna, Maneesh Agrawala

Figure 1 for AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
Figure 2 for AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
Figure 3 for AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
Figure 4 for AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning
* 8 pages, 15 pages supplementary, 12 figures. To be published in CVPR 2021 
  Access Paper or Ask Questions

Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning


Nov 10, 2020
Rachel Gardner, Maya Varma, Clare Zhu, Ranjay Krishna

Figure 1 for Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning
Figure 2 for Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning
Figure 3 for Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning
Figure 4 for Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning
* Published at the 6th Workshop on Noisy User-generated Text (W-NUT) 2020 at EMNLP (6 pages, 4 figures) 
  Access Paper or Ask Questions

Conceptual Metaphors Impact Perceptions of Human-AI Collaboration


Aug 05, 2020
Pranav Khadpe, Ranjay Krishna, Li Fei-Fei, Jeffrey Hancock, Michael Bernstein

Figure 1 for Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
Figure 2 for Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
Figure 3 for Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
Figure 4 for Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
* PACM HCI Volume 4 CSCW 2, 2020 
 * CSCW 2020 
  Access Paper or Ask Questions

Action Genome: Actions as Composition of Spatio-temporal Scene Graphs


Dec 15, 2019
Jingwei Ji, Ranjay Krishna, Li Fei-Fei, Juan Carlos Niebles

Figure 1 for Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
Figure 2 for Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
Figure 3 for Action Genome: Actions as Composition of Spatio-temporal Scene Graphs
Figure 4 for Action Genome: Actions as Composition of Spatio-temporal Scene Graphs

  Access Paper or Ask Questions

Deep Bayesian Active Learning for Multiple Correct Outputs


Dec 08, 2019
Khaled Jedoui, Ranjay Krishna, Michael Bernstein, Li Fei-Fei

Figure 1 for Deep Bayesian Active Learning for Multiple Correct Outputs
Figure 2 for Deep Bayesian Active Learning for Multiple Correct Outputs
Figure 3 for Deep Bayesian Active Learning for Multiple Correct Outputs
Figure 4 for Deep Bayesian Active Learning for Multiple Correct Outputs
* 18 pages, 9 figures 
  Access Paper or Ask Questions

Visual Relationships as Functions: Enabling Few-Shot Scene Graph Prediction


Jun 14, 2019
Apoorva Dornadula, Austin Narcomey, Ranjay Krishna, Michael Bernstein, Li Fei-Fei

Figure 1 for Visual Relationships as Functions: Enabling Few-Shot Scene Graph Prediction
Figure 2 for Visual Relationships as Functions: Enabling Few-Shot Scene Graph Prediction
Figure 3 for Visual Relationships as Functions: Enabling Few-Shot Scene Graph Prediction
Figure 4 for Visual Relationships as Functions: Enabling Few-Shot Scene Graph Prediction
* 15 pages, 8 figures, preprint 
  Access Paper or Ask Questions

Scene Graph Prediction with Limited Labels


Apr 25, 2019
Vincent S. Chen, Paroma Varma, Ranjay Krishna, Michael Bernstein, Christopher Re, Li Fei-Fei

Figure 1 for Scene Graph Prediction with Limited Labels
Figure 2 for Scene Graph Prediction with Limited Labels
Figure 3 for Scene Graph Prediction with Limited Labels
Figure 4 for Scene Graph Prediction with Limited Labels
* 10 pages, 9 figures 
  Access Paper or Ask Questions

HYPE: Human eYe Perceptual Evaluation of Generative Models


Apr 24, 2019
Sharon Zhou, Mitchell Gordon, Ranjay Krishna, Austin Narcomey, Durim Morina, Michael S. Bernstein

Figure 1 for HYPE: Human eYe Perceptual Evaluation of Generative Models
Figure 2 for HYPE: Human eYe Perceptual Evaluation of Generative Models
Figure 3 for HYPE: Human eYe Perceptual Evaluation of Generative Models
Figure 4 for HYPE: Human eYe Perceptual Evaluation of Generative Models
* https://hype.stanford.edu 
  Access Paper or Ask Questions

Information Maximizing Visual Question Generation


Mar 27, 2019
Ranjay Krishna, Michael Bernstein, Li Fei-Fei

Figure 1 for Information Maximizing Visual Question Generation
Figure 2 for Information Maximizing Visual Question Generation
Figure 3 for Information Maximizing Visual Question Generation
Figure 4 for Information Maximizing Visual Question Generation
* IEEE Conference on Computer Vision and Pattern Recognition, 2019 
 * CVPR 2019 
  Access Paper or Ask Questions

The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary


Aug 23, 2018
Bernard Ghanem, Juan Carlos Niebles, Cees Snoek, Fabian Caba Heilbron, Humam Alwassel, Victor Escorcia, Ranjay Krishna, Shyamal Buch, Cuong Duc Dao

Figure 1 for The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary
Figure 2 for The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary
Figure 3 for The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary
Figure 4 for The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary
* CVPR Workshop 2018 challenge summary 
  Access Paper or Ask Questions

Referring Relationships


Mar 29, 2018
Ranjay Krishna, Ines Chami, Michael Bernstein, Li Fei-Fei

Figure 1 for Referring Relationships
Figure 2 for Referring Relationships
Figure 3 for Referring Relationships
Figure 4 for Referring Relationships
* CVPR 2018, 19 pages, 12 figures, includes supplementary material 
  Access Paper or Ask Questions

Dense-Captioning Events in Videos


May 02, 2017
Ranjay Krishna, Kenji Hata, Frederic Ren, Li Fei-Fei, Juan Carlos Niebles

Figure 1 for Dense-Captioning Events in Videos
Figure 2 for Dense-Captioning Events in Videos
Figure 3 for Dense-Captioning Events in Videos
Figure 4 for Dense-Captioning Events in Videos
* 16 pages, 16 figures 
  Access Paper or Ask Questions

A Hierarchical Approach for Generating Descriptive Image Paragraphs


Apr 10, 2017
Jonathan Krause, Justin Johnson, Ranjay Krishna, Li Fei-Fei

Figure 1 for A Hierarchical Approach for Generating Descriptive Image Paragraphs
Figure 2 for A Hierarchical Approach for Generating Descriptive Image Paragraphs
Figure 3 for A Hierarchical Approach for Generating Descriptive Image Paragraphs
Figure 4 for A Hierarchical Approach for Generating Descriptive Image Paragraphs
* CVPR 2017 spotlight 
  Access Paper or Ask Questions

A Glimpse Far into the Future: Understanding Long-term Crowd Worker Quality


Nov 01, 2016
Kenji Hata, Ranjay Krishna, Li Fei-Fei, Michael S. Bernstein

Figure 1 for A Glimpse Far into the Future: Understanding Long-term Crowd Worker Quality
Figure 2 for A Glimpse Far into the Future: Understanding Long-term Crowd Worker Quality
Figure 3 for A Glimpse Far into the Future: Understanding Long-term Crowd Worker Quality
Figure 4 for A Glimpse Far into the Future: Understanding Long-term Crowd Worker Quality
* 10 pages, 11 figures, accepted CSCW 2017 
  Access Paper or Ask Questions

Visual Relationship Detection with Language Priors


Jul 31, 2016
Cewu Lu, Ranjay Krishna, Michael Bernstein, Li Fei-Fei

Figure 1 for Visual Relationship Detection with Language Priors
Figure 2 for Visual Relationship Detection with Language Priors
Figure 3 for Visual Relationship Detection with Language Priors
Figure 4 for Visual Relationship Detection with Language Priors
* ECCV 2016 Oral 
  Access Paper or Ask Questions

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations


Feb 23, 2016
Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A. Shamma, Michael S. Bernstein, Fei-Fei Li

Figure 1 for Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Figure 2 for Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Figure 3 for Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Figure 4 for Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
* 44 pages, 37 figures 
  Access Paper or Ask Questions

Embracing Error to Enable Rapid Crowdsourcing


Feb 14, 2016
Ranjay Krishna, Kenji Hata, Stephanie Chen, Joshua Kravitz, David A. Shamma, Li Fei-Fei, Michael S. Bernstein

Figure 1 for Embracing Error to Enable Rapid Crowdsourcing
Figure 2 for Embracing Error to Enable Rapid Crowdsourcing
Figure 3 for Embracing Error to Enable Rapid Crowdsourcing
Figure 4 for Embracing Error to Enable Rapid Crowdsourcing
* 10 pages, 7 figures, CHI '16, CHI: ACM Conference on Human Factors in Computing Systems (2016) 
  Access Paper or Ask Questions