Deep Learning

Mapping Instructions and Visual Observations to Actions with Reinforcement Learning EMNLP 2017 MarrNet: 3D Shape Reconstruction via 2.5D Sketches NeurIPS 2017 MaskRNN: Instance Level Video Object Segmentation NeurIPS 2017 Massive Exploration of Neural Machine Translation Architectures EMNLP 2017 MAT: A Multimodal Attentive Translator for Image Captioning IJCAI 2017 Matching neural paths: transfer from recognition to correspondence search NeurIPS 2017 Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification NeurIPS 2017 Maximum Margin Reward Networks for Learning from Explicit and Implicit Supervision EMNLP 2017 May I take your order? A Neural Model for Extracting Structured Information from Conversations EACL 2017 MDNet: A Semantically and Visually Interpretable Medical Image Diagnosis Network CVPR 2017 Mean Field Residual Networks: On the Edge of Chaos NeurIPS 2017 Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results NeurIPS 2017 MEC: Memory-efficient Convolution for Deep Neural Network ICML 2017 Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search CVPR 2017 Memory-augmented Neural Machine Translation EMNLP 2017 Memory Augmented Neural Networks for Natural Language Processing EMNLP 2017 Mention Recommendation for Twitter with End-to-end Memory Network IJCAI 2017 meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting ICML 2017 Methodical Evaluation of Arabic Word Embeddings ACL 2017 Microblog Sentiment Classification via Recurrent Random Walk Network Learning IJCAI 2017 Mimicking Very Efficient Network for Object Detection CVPR 2017 Mimicking Word Embeddings using Subword RNNs EMNLP 2017 MIML-FCN+: Multi-Instance Multi-Label Learning via Fully Convolutional Networks With Privileged Information CVPR 2017 Minimum Semantic Error Cost Training of Deep Long Short-Term Memory Networks for Topic Spotting on Conversational Speech Interspeech 2017 Mining Object Parts From CNNs via Active Question-Answering CVPR 2017