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 Subhajit Chaudhury

Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents


Jun 09, 2021
Keerthiram Murugesan, Subhajit Chaudhury, Kartik Talamadupula


  Access Paper or Ask Questions

Reinforcement Learning with External Knowledge by using Logical Neural Networks


Mar 03, 2021
Daiki Kimura, Subhajit Chaudhury, Akifumi Wachi, Ryosuke Kohita, Asim Munawar, Michiaki Tatsubori, Alexander Gray

* KBRL Workshop at IJCAI-PRICAI 2020 

  Access Paper or Ask Questions

Image inpainting using frequency domain priors


Dec 03, 2020
Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki, Tatsuaki Hashimoto


  Access Paper or Ask Questions

VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning


Oct 26, 2020
Thomas Carta, Subhajit Chaudhury, Kartik Talamadupula, Michiaki Tatsubori

* Code is available at http://ibm.biz/VisualHints 

  Access Paper or Ask Questions

Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games


Sep 24, 2020
Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori, Asim Munawar, Ryuki Tachibana

* Accepted to EMNLP 2020 

  Access Paper or Ask Questions

Investigating Generalization in Neural Networks under Optimally Evolved Training Perturbations


Mar 14, 2020
Subhajit Chaudhury, Toshihiko Yamasaki

* Accepted at IEEE ICASSP 2020 

  Access Paper or Ask Questions

Unsupervised Temporal Feature Aggregation for Event Detection in Unstructured Sports Videos


Feb 19, 2020
Subhajit Chaudhury, Daiki Kimura, Phongtharin Vinayavekhin, Asim Munawar, Ryuki Tachibana, Koji Ito, Yuki Inaba, Minoru Matsumoto, Shuji Kidokoro, Hiroki Ozaki

* Accepted to IEEE International Symposium on Multimedia, 2019 

  Access Paper or Ask Questions

Lunar surface image restoration using U-net based deep neural networks


Apr 14, 2019
Hiya Roy, Subhajit Chaudhury, Toshihiko Yamasaki, Danielle DeLatte, Makiko Ohtake, Tatsuaki Hashimoto


  Access Paper or Ask Questions

Internal Model from Observations for Reward Shaping


Oct 14, 2018
Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana, Sakyasingha Dasgupta

* 7 pages, 6 figures, ICML workshop (ALA 2018) 

  Access Paper or Ask Questions

Video Imitation GAN: Learning control policies by imitating raw videos using generative adversarial reward estimation


Oct 02, 2018
Subhajit Chaudhury, Daiki Kimura, Tu-Hoa Pham, Asim Munawar, Ryuki Tachibana


  Access Paper or Ask Questions

Constrained Exploration and Recovery from Experience Shaping


Sep 21, 2018
Tu-Hoa Pham, Giovanni De Magistris, Don Joven Agravante, Subhajit Chaudhury, Asim Munawar, Ryuki Tachibana

* Code: https://github.com/IBM/constrained-rl 

  Access Paper or Ask Questions

Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection


Jul 04, 2018
Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta

* Copyright 2018 IEEE - Accepted at ICIP 2018, Athens, Greece, October 7-10, 2018. Video: https://youtu.be/30vji7nJibA. arXiv admin note: text overlap with arXiv:1709.06762 

  Access Paper or Ask Questions

Focusing on What is Relevant: Time-Series Learning and Understanding using Attention


Jun 22, 2018
Phongtharin Vinayavekhin, Subhajit Chaudhury, Asim Munawar, Don Joven Agravante, Giovanni De Magistris, Daiki Kimura, Ryuki Tachibana

* To appear in ICPR 2018 

  Access Paper or Ask Questions

Transfer learning from synthetic to real images using variational autoencoders for robotic applications


Sep 20, 2017
Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta

* video: https://youtu.be/Wd-1WU8emkw 

  Access Paper or Ask Questions

Conditional generation of multi-modal data using constrained embedding space mapping


Jul 26, 2017
Subhajit Chaudhury, Sakyasingha Dasgupta, Asim Munawar, Md. A. Salam Khan, Ryuki Tachibana

* 7 pages, 4 figures, ICML 2017 Workshop on Implicit Models 

  Access Paper or Ask Questions

Can fully convolutional networks perform well for general image restoration problems?


Apr 13, 2017
Subhajit Chaudhury, Hiya Roy

* Accepted at IAPR MVA 2017 

  Access Paper or Ask Questions