 phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image CaptioningAsian Conference on Computer Vision (ACCV), 2016 |
 RETAIN: An Interpretable Predictive Model for Healthcare using Reverse
Time Attention MechanismNeural Information Processing Systems (NeurIPS), 2016 |
 Modeling Human Reading with Neural AttentionConference on Empirical Methods in Natural Language Processing (EMNLP), 2016 |
 HeMIS: Hetero-Modal Image SegmentationInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2016 |
 Weakly Supervised Learning of Heterogeneous Concepts in VideosEuropean Conference on Computer Vision (ECCV), 2016 |
 VideoLSTM Convolves, Attends and Flows for Action RecognitionComputer Vision and Image Understanding (CVIU), 2016 |
 "Show me the cup": Reference with Continuous RepresentationsConference on Intelligent Text Processing and Computational Linguistics (CICLing), 2016 |
 Diversified Visual Attention Networks for Fine-Grained Object
ClassificationIEEE transactions on multimedia (TMM), 2016 |
 Sequence-Level Knowledge DistillationConference on Empirical Methods in Natural Language Processing (EMNLP), 2016 |
 CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation
TasksConference on Machine Translation (WMT), 2016 |
 |
 Conditional Generation and Snapshot Learning in Neural Dialogue SystemsConference on Empirical Methods in Natural Language Processing (EMNLP), 2016 |
 Sequence-to-Sequence Learning as Beam-Search OptimizationConference on Empirical Methods in Natural Language Processing (EMNLP), 2016 |
 SE3-Nets: Learning Rigid Body Motion using Deep Neural NetworksIEEE International Conference on Robotics and Automation (ICRA), 2016 |
 Multimodal Compact Bilinear Pooling for Visual Question Answering and
Visual GroundingConference on Empirical Methods in Natural Language Processing (EMNLP), 2016 |
 Attention Correctness in Neural Image CaptioningAAAI Conference on Artificial Intelligence (AAAI), 2016 |
