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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
CURI: A Benchmark for Productive Concept Learning Under Uncertainty

Oct 06, 2020
Ramakrishna Vedantam, Arthur Szlam, Maximilian Nickel, Ari Morcos, Brenden Lake


  Access Paper or Ask Questions

Learning Optimal Representations with the Decodable Information Bottleneck

Sep 27, 2020
Yann Dubois, Douwe Kiela, David J. Schwab, Ramakrishna Vedantam

* Accepted at NeurIPS 2020 

  Access Paper or Ask Questions

Unsupervised Discovery of Decision States for Transfer in Reinforcement Learning

Aug 15, 2019
Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra, Ramakrishna Vedantam


  Access Paper or Ask Questions

Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering

Feb 21, 2019
Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, Devi Parikh

* 15 pages, 3 figures, 2 tables 

  Access Paper or Ask Questions

Generative Models of Visually Grounded Imagination

Feb 25, 2018
Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy

* International Conference on Learning Representations (ICLR), 2018 

  Access Paper or Ask Questions

Sound-Word2Vec: Learning Word Representations Grounded in Sounds

Aug 29, 2017
Ashwin K Vijayakumar, Ramakrishna Vedantam, Devi Parikh

* Accepted at EMNLP 2017. Contains 6 pages; 3 tables; 1 figure 

  Access Paper or Ask Questions

Context-aware Captions from Context-agnostic Supervision

Jul 31, 2017
Ramakrishna Vedantam, Samy Bengio, Kevin Murphy, Devi Parikh, Gal Chechik

* Accepted to CVPR 2017 (Spotlight) 

  Access Paper or Ask Questions

Counting Everyday Objects in Everyday Scenes

May 09, 2017
Prithvijit Chattopadhyay, Ramakrishna Vedantam, Ramprasaath R. Selvaraju, Dhruv Batra, Devi Parikh


  Access Paper or Ask Questions

Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization

Mar 21, 2017
Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra

* 24 pages, 22 figures. Adds bias experiments, and robustness to adversarial noise 

  Access Paper or Ask Questions

Grad-CAM: Why did you say that?

Jan 25, 2017
Ramprasaath R Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra

* Presented at NIPS 2016 Workshop on Interpretable Machine Learning in Complex Systems. This is an extended abstract version of arXiv:1610.02391 (CVPR format) 

  Access Paper or Ask Questions

Visual Word2Vec (vis-w2v): Learning Visually Grounded Word Embeddings Using Abstract Scenes

Jun 29, 2016
Satwik Kottur, Ramakrishna Vedantam, José M. F. Moura, Devi Parikh

* 15 pages, 11 figures 

  Access Paper or Ask Questions

CIDEr: Consensus-based Image Description Evaluation

Jun 03, 2015
Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh

* To appear in CVPR 2015 

  Access Paper or Ask Questions

Microsoft COCO Captions: Data Collection and Evaluation Server

Apr 03, 2015
Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Dollar, C. Lawrence Zitnick

* arXiv admin note: text overlap with arXiv:1411.4952 

  Access Paper or Ask Questions

Collecting Image Description Datasets using Crowdsourcing

Nov 12, 2014
Ramakrishna Vedantam, C. Lawrence Zitnick, Devi Parikh


  Access Paper or Ask Questions