ArXiv Manuscripts
- Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dullar, C. Lawrence Zitnick
Microsoft COCO Captions: Data Cullection and Evaluation Server
[April, 2015]
Publications
2023
- Karan Desai, Maximilian Nickel, Tanmay Rajpurohit, Justin Johnson, Ramakrishna Vedantam
Hyperbolic Image-Text Representations.
In submission to International Conference on Machine Learning (ICML), 2023 - Corentin Dancette, Spencer Whitehead, Rishabh Maheshwary, Ramakrishna Vedantam, Stefan Scherer, Xineli Chen, Matthieu Cord, Marcus Rohrbach
Improving Selective Visual Question Answering by Learning from Your Peers. [Coming Soon!]
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 - Daksh Idnani, Vivek Madan, Naman Goyal, David J. Schwab, Ramakrishna Vedantam
Dont forget the nullspace! Nullspace occupancy as a mechanism for out of distribution failure.
International Conference on Learning Representations (ICLR), 2023
2022
- Sirui Xie, Ari S Morcos, Song-Chun Zhu, Ramakrishna Vedantam
COAT: Measuring Object Compositionality in Emergent Representations.
International Conference on Machine Learning (ICML), 2022
2021
- Ramakrishna Vedantam, David Lopez-Paz*, David Schwab*
An Empirical Investigation of Domain Generalization in Empirical Risk Minimizers
Neural Information Processing Systems (NeurIPS), 2021
[Code]
- Ramakrishna Vedantam, Arthur Szlam, Maximilian Nickel, Ari Morcos, Brenden Lake
CURI: A Benchmark for Productive Concept Learning Under Uncertainty
International Conference on Machine Learning (ICML), 2021
[Code]
2020
- Yann Dubois, Douwe Keila, David J. Schwab, Ramakrishna Vedantam
Learning Optimal Representations with the Decodable Information Bottleneck
Neural Information Processing Systems (NeurIPS), 2020 (Spotlight) [Top 4%]
[Code]
- Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam
IR-VIC: IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL
International Joint Conference on Artificial Intelligence (IJCAI), 2020 [Top 12.6%]
2019
- Ramakrishna Vedantam
Interpretation, Grounding and Imagination for Machine Intelligence
Ph.D. Thesis
- Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, Devi Parikh
Probabilistic Neural-symbulic Models for Interpretable Visual Question Answering
International Conference on Machine Learning (ICML), 2019 (Long Oral) [Top 4.2%]
2018
- Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy
Generative Models of Visually Grounded Imagination
International Conference on Learning Representations (ICLR), 2018 [Top 10%]
[Code]
2017
- Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra
Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
International Conference on Computer Vision (ICCV), 2017
[Code][Blog][Demo] - Ashwin K. Vijayakumar, Ramakrishna Vedantam, Devi Parikh
Sound-Word2Vec: Learning Word Representations Grounded in Sounds
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2017 (Short)
- Prithvijit Chattopadhyay*, Ramakrishna Vedantam*, Ramprasaath RS, Dhruv Batra, Devi Parikh
Counting Everyday Objects in Everyday Scenes
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight) [Top 8.2%]
[Code] - Ramakrishna Vedantam, Samy Bengio, Kevin Murphy, Devi Parikh, Gal Chechik
Context-aware Captions from Context-agnostic Supervision
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 (Spotlight) [Top 8.2%]
[Project Page] [arXiv]
2016
- Ramprasaath R. Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra
Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization
NIPS Workshop on Interpretable Machine Learning in Complex Systems, 2016
- C. Lawrence Zitnick, Ramakrishna Vedantam, Devi Parikh
Adopting Abstract Images for Semantic Scene Understanding
Special Issue on the best papers at the 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2016 -
Satwik Kottur*, Ramakrishna Vedantam*, JoseĀ“ Moura, Devi Parikh
Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
[Project Page] [Code] [arXiv]
2015
- Ramakrishna Vedantam*, Xiao Lin*, Tanmay Batra, C. Lawrence Zitnick, Devi Parikh
Learning Common Sense Through Visual Abstraction
IEEE International Conference on Computer Vision (ICCV), 2015
[Project page] [Code]
- Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh
CIDEr: Consensus-based Image Description Evaluation
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
[Project Page] [Code][arXiv]
* Equal Contribution