 |
 |
 Recurrent 3D Attentional Networks for End-to-End Active Object
RecognitionComputational Visual Media (CVM), 2016 |
 Attention and Anticipation in Fast Visual-Inertial NavigationIEEE International Conference on Robotics and Automation (ICRA), 2016 |
 Latent Sequence DecompositionsInternational Conference on Learning Representations (ICLR), 2016 |
 End-to-end Concept Word Detection for Video Captioning, Retrieval, and
Question AnsweringComputer Vision and Pattern Recognition (CVPR), 2016 |
 Understanding intermediate layers using linear classifier probesInternational Conference on Learning Representations (ICLR), 2016 |
 Visual Question Answering: Datasets, Algorithms, and Future ChallengesComputer Vision and Image Understanding (CVIU), 2016 |
