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 Thao Minh Le

Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering


Jun 25, 2021
Long Hoang Dang, Thao Minh Le, Vuong Le, Truyen Tran

* Accepted by IJCAI 2021 

  Access Paper or Ask Questions

Object-Centric Representation Learning for Video Question Answering


Apr 13, 2021
Long Hoang Dang, Thao Minh Le, Vuong Le, Truyen Tran

* 8 pages 

  Access Paper or Ask Questions

Hierarchical Conditional Relation Networks for Multimodal Video Question Answering


Oct 18, 2020
Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran

* 18 pages. arXiv admin note: substantial text overlap with arXiv:2002.10698 

  Access Paper or Ask Questions

GEFA: Early Fusion Approach in Drug-Target Affinity Prediction


Sep 28, 2020
Tri Minh Nguyen, Thin Nguyen, Thao Minh Le, Truyen Tran


  Access Paper or Ask Questions

Dynamic Language Binding in Relational Visual Reasoning


Apr 30, 2020
Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran

* Early version accepted by IJCAI20 

  Access Paper or Ask Questions

Hierarchical Conditional Relation Networks for Video Question Answering


Mar 17, 2020
Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran

* CVPR 2020, Oral 
* Check out our code on GitHub at https://github.com/thaolmk54/hcrn-videoqa 

  Access Paper or Ask Questions

Learning to Reason with Relational Video Representation for Question Answering


Jul 10, 2019
Thao Minh Le, Vuong Le, Svetha Venkatesh, Truyen Tran


  Access Paper or Ask Questions

Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances


Sep 12, 2018
Thao Minh Le, Nobuyuki Shimizu, Takashi Miyazaki, Koichi Shinoda

* Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence Main track. Pages 1546-1553 

  Access Paper or Ask Questions

A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition


Aug 18, 2018
Thao Minh Le, Nakamasa Inoue, Koichi Shinoda

* Camera-ready manuscript for BMVC2018 

  Access Paper or Ask Questions