- Expressing an Image Stream with a Sequence of Natural Sentences
- Cesc Park, Seoul National University; Gunhee Kim*, Seoul National University
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [Paper]
- Shaoqing Ren, USTC; Kaiming He*, Microsoft Research Asia; Ross Girshick, Microsoft Research; Jian Sun, Microsoft Research Asia
- Space-Time Local Embeddings
- Ke SUN*, University of Geneva; Jun Wang, Expedia, Geneva; Alexandros Kalousis, ; Stephane Marchand-Maillet, University of Geneva
- Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning
- Jiajun Wu*, MIT; Ilker Yildirim, MIT; William Freeman, MIT; Josh Tenenbaum, MIT
- Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets [Paper]
- Armand Joulin*, Facebook AI research; Tomas Mikolov, Facebook AI Research
- Where are they looking?
- Adria Recasens*, MIT; Aditya Khosla, MIT; Carl Vondrick, MIT; Antonio Torralba, MIT
- Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution
- Yan Huang*, CRIPAC, CASIA; Wei Wang, NLPR,CASIA; Liang Wang,
- Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks [Paper]
- Leon Gatys*, University of Tübingen; Alexander Ecker, University of Tuebingen; Matthias Bethge, CIN, University Tübingen
- Learning visual biases from human imagination [Project Page] [Prev Paper]
- Carl Vondrick*, MIT; Hamed Pirsiavash, MIT; Aude Oliva, MIT; Antonio Torralba, MIT
- Deeply Learning the Messages in Message Passing Inference [Paper]
- Guosheng Lin*, The University of Adelaide; Chunhua Shen, ; Ian Reid, University of Adelaide; Anton Van Den Hengel, University of Adelaide
- 3D Object Proposals for Accurate Object Class Detection
- Xiaozhi Chen, Tsinghua University; Kaustav Kundu, University of Toronto; Yukun Zhu, University of Toronto; Andrew Berneshawi, University of Toronto; Huimin Ma, Tsinghua University; Sanja Fidler, University of Toronto; Raquel Urtasun*, University of Toronto
- Deep Knowledge Tracing [Paper]
- Chris Piech*, Stanford; Jonathan Bassen, stanford.edu; Jonathan Huang, google.com; Surya Ganguli, stanford.edu; Mehran Sahami, stanford.edu; Leonidas Guibas, stanford.edu; Jascha Sohl-Dickstein, stanford.edu
- Learning Theory and Algorithms for Forecasting Non-stationary Time Series
- Vitaly Kuznetsov*, Courant Institute; Mehryar Mohri, Courant Institute and Google
- Attention-Based Models for Speech Recognition [Paper]
- Jan Chorowski*, University of Wroclaw; Dzmitry Bahdanau, Jacobs University, Germany; Dmitriy Serdyuk, Université de Montréal; Kyunghyun Cho, NYU; Yoshua Bengio, U. Montreal
- Character-level Convolutional Networks for Text Classification [Paper]
- Xiang Zhang*, New York University; Junbo Zhao, New York University; Yann LeCun, New York University
- Deep learning with Elastic Averaging SGD [Paper]
- Sixin Zhang*, New York University; Anna Choromanska, Courant Institute, NYU; Yann LeCun, New York University
- Online Learning for Adversaries with Memory: Price of Past Mistakes
- Oren Anava*, Technion; Elad Hazan, Princeton University; Shie Mannor, Technion
- Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting [Paper]
- Xingjian Shi*, HKUST; Zhourong Chen, The Hong Kong University of Science and Technology; Hao Wang, HKUST; Dit Yan Yeung, HKUST; Wai-kin Wong, ; Wang-chun WOO,
- Bidirectional Recurrent Neural Networks as Generative Models [Paper]
- Mathias Berglund*, Aalto University; Tapani Raiko, Aalto University; Mikko Honkala, Nokia Labs; Leo Kärkkäinen, Nokia Labs; Akos Vetek, Nokia Labs; Juha Karhunen, Aalto University
- Hessian-Free Optimization For Learning Deep Multidimensional Recurrent Neural Networks
- Minhyung Cho*, Gracenote; Jaehyung Lee, Gracenote; Chandra Dhir, Gracenote
- Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling
- Ming Liang, Tsinghua University; Xiaolin Hu*, Tsinghua University; Bo Zhang, Tsinghua University
- Unsupervised Learning by Program Synthesis
- Kevin Ellis*, MIT; Josh Tenenbaum, MIT; Armando Solar-Lezama, MIT
- Human Memory Search as Initial-Visit Emitting Random Walk
- Kwang-Sung Jun*, University of Wisconsin-Madiso; Xiaojin Zhu, University of Wisconsin-Madison; Timothy Rogers, University of Wisconsin-Madison; Zhuoran Yang, Tsinghua University; ming yuan, University of Wisconsin - Madison
- Learning to Rotate 3D Objects with Recurrent Convolutional Encoder-Decoder Networks
- Jimei Yang*, UC Merced; Scott Reed, University of Michigan; Ming-Hsuan Yang, UC Merced; Honglak Lee, U. Michigan
- Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets [Paper]
- Pascal Vincent*, U. Montreal; Alexandre de Brébisson, Université de Montréal; Xavier Bouthillier, Universit de Montréal
- Backpropagation for Energy-Efficient Neuromorphic Computing
- Steve Esser*, IBM Research-Almaden; Rathinakumar Appuswamy, IBM Research-Almaden; Paul Merolla, IBM Research-Almaden; John Arthur, IBM Research-Almaden; Dharmendra Modha, IBM Research-Almaden
- Learning both Weights and Connections for Efficient Neural Network [Paper]
- Song Han*, Stanford University; Jeff Pool, ; John Tran, ; Bill Dally , Stanford University
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks [Paper]
- Samy Bengio*, Google Research; Oriol Vinyals, Google; Navdeep Jaitly, Google; Noam Shazeer, Google
- Learning to Linearize Under Uncertainty [Paper]
- Ross Goroshin*, New York University; Michael Mathieu, New York University; Yann LeCun, New York University
- Deep Visual Analogy-Making
- Scott Reed*, University of Michigan; Yi Zhang, University of Michigan; Yuting Zhang, University of Michigan; Honglak Lee, U. Michigan
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks [Paper]
- Emily Denton*, New York University; Rob Fergus, Facebook AI Research; Arthur Szlam, Facebook; Soumith Chintala, Facebook AI Research
- Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation [Paper]
- Seunghoon Hong*, POSTECH; Hyeonwoo Noh, POSTECH; Bohyung Han, Postech
- Teaching Machines to Read and Comprehend [Paper]
- Karl Moritz Hermann*, Google DeepMind; Tomas Kocisky, Oxford University; Edward Grefenstette, Google DeepMind; Lasse Espeholt, Google DeepMind; Will Kay, Google DeepMind; Mustafa Suleyman, Google DeepMind; Phil Blunsom, Google DeepMind
- Max-Margin Deep Generative Models [Paper]
- Chongxuan Li*, Tsinghua University; Jun Zhu, Tsinghua University; Tianlin Shi, Tsinghua University; Bo Zhang, Tsinghua University
- Visalogy: Answering Visual Analogy Questions
- Fereshteh Sadeghi*, University of Washington; Ross Girshick, Microsoft Research; Larry Zitnick, Microsoft Research; Ali Farhadi, University of Washington
- Generative Image Modeling Using Spatial LSTMs [Paper]
- Lucas Theis*, U.Tuebingen; Matthias Bethge, CIN, University Tübingen
- Learning to Segment Object Candidates [Paper]
- Pedro Pinheiro*, EPFL; Ronan Collobert, Facebook; Piotr Dollar, Facebook AI Research
- Spatial Transformer Networks [Paper]
- Max Jaderberg*, Google; Karen Simonyan, Google DeepMind; Andrew Zisserman, Google; Koray Kavukcuoglu, Google DeepMind
- Natural Neural Networks [Paper]
- Guillaume Desjardins*, Google DeepMind; Karen Simonyan, Google DeepMind; Razvan Pascanu, Google DeepMind; Koray Kavukcuoglu, Google DeepMind
- Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction
- Been Kim, MIT; Julie Shah, MIT; Finale Doshi-Velez*, Harvard
- Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question [Paper]
- Haoyuan Gao, Baidu; Junhua Mao, UCLA; Jie Zhou, Baidu; Zhiheng Huang, Baidu; Lei Wang, Baidu; Wei Xu*, Baidu
- Training Very Deep Networks [Paper]
- Rupesh Srivastava*, IDSIA; Klaus Greff, IDSIA; J?rgen Schmidhuber,
- End-To-End Memory Networks [Paper]
- Sainbayar Sukhbaatar*, New York University; Arthur Szlam, Facebook; Jason Weston, Facebook AI Research; Rob Fergus, Facebook AI Research
- Spectral Representations for Convolutional Neural Networks [Paper]
- Oren Rippel*, MIT; Jasper Snoek, Harvard; Ryan Adams, Harvard
- Deep Temporal Sigmoid Belief Networks for Sequence Modeling
- Zhe Gan*, Duke University; Chunyuan Li, Duke University; Ricardo Henao, Duke University; David Carlson, ; Lawrence Carin, Duke University
- Deep Convolutional Inverse Graphics Network [Paper]
- Pushmeet Kohli, Microsoft Research; Will Whitney, MIT; Tejas Kulkarni*, MIT; Josh Tenenbaum, MIT
- Learning Wake-Sleep Recurrent Attention Models
- Jimmy Ba*, University of Toronto; Ruslan Salakhutdinov, University of Toronto; Roger Grosse, University of Toronto; Brendan Frey, U. Toronto
- Super-Resolution Off the Grid
- Qingqing Huang, MIT; Sham Kakade*, University of Washington
- The Return of the Gating Network: combining generative models and discriminative training in natural image priors.
- Dan Rosenbaum*, The Hebrew University; Yair Weiss, Hebrew University
- Pointer Networks [Paper]
- Oriol Vinyals*, Google; Meire Fortunato, ; Navdeep Jaitly, Google
- Grammar as a Foreign Language [Paper]
- Oriol Vinyals*, Google; Lukasz Kaiser, Google; Terry Koo, Google; Slav Petrov, Google; Ilya Sutskever, Google; Geoffrey Hinton, Google
- The Human Kernel
- Andrew Wilson*, Carnegie Mellon University; Christoph Dann, CMU; Chris Lucas, University of Edinburgh; Eric Xing, Carnegie Mellon University
- Exploring Models and Data for Image Question Answering [Paper]
- Mengye Ren*, University of Toronto; Ryan Kiros, U. Toronto; Richard Zemel, University of Toronto
- A Recurrent Latent Variable Model for Sequential Data [Paper]
- Junyoung Chung*, University of Montreal; Kyle Kastner, Universite de Montreal; Viet Hanh Laurent Dinh, University of Montreal; Kratarth Goel, University of Montreal; Aaron Courville, U. Montreal; Yoshua Bengio, U. Montreal
- Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation [Paper]
- Marijn Stollenga*, IDSIA; Wonmin Byeon, TU Kaiserslautern; Marcus Liwicki, TU Kaiserslautern; J?rgen Schmidhuber,
- Unsupervised Sequence Learning
- Andrew Dai*, Google Inc; Quoc Le, Google
- Data Generation as Sequential Decision Making [Paper]
- Philip Bachman*, McGill University; Doina Precup, University of McGill
- Skip-Thought Vectors [Paper]
- Ryan Kiros*, U. Toronto; Yukun Zhu, University of Toronto; Ruslan Salakhutdinov, University of Toronto; Richard Zemel, University of Toronto; Raquel Urtasun, University of Toronto; Antonio Torralba, MIT; Sanja Fidler, University of Toronto
- Bayesian dark knowledge [Paper]
- Anoop Korattikara*, Google; Vivek Rathod, Google; Kevin Murphy, Google; Max Welling,
- Learning Structured Output Representation using Deep Conditional Generative Models
- Kihyuk Sohn*, University of Michigan; Honglak Lee, U. Michigan; Xinchen Yan, UMich
- Semi-supervised Learning with Ladder Network [Paper]
- Antti Rasmus*, Aalto University; Mathias Berglund, Aalto University; Mikko Honkala, Nokia Labs; Harri Valpola, ZenRobotics; Tapani Raiko, Aalto University
- Recursive 2D-3D Convolutional Networks for Neuronal Boundary Prediction [Paper]
- Kisuk Lee*, MIT; Aleksandar Zlateski, MIT; Vishwanathan Ashwin, Princeton University; H. Sebastian Seung, Princeton University