Project Pages

Grounded Visual Captions without Localization Supervision
3 Jun 2019 Kevin Chih-Yao Ma
The Regretful Navigation Agent for Vision-and-Language Navigation
25 Feb 2019 Kevin Chih-Yao Ma
Self-Monitoring Agent for Vision-and-Language Navigation
27 Sep 2018 Kevin Chih-Yao Ma
Object Interactions for Fine-grained Video Understanding
16 Nov 2017 Kevin Chih-Yao Ma
Activity Recognition with RNN and Temporal-ConvNet
30 Mar 2017 Kevin Chih-Yao Ma
NCTU-3DFixation Dataset
1 May 2015 Kevin Chih-Yao Ma