Papers-2015.md

December 2015

• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction - [Arxiv] [QA]
• Deep Residual Learning for Image Recognition - [Arxiv] [QA]
• MovieQA: Understanding Stories in Movies through Question-Answering - [Arxiv] [QA]
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition - [Arxiv] [QA]

November 2015

• A Type Theory for Probabilistic and Bayesian Reasoning - [Arxiv] [QA]
• Sequence Level Training with Recurrent Neural Networks - [Arxiv] [QA]
• All you need is a good init - [Arxiv] [QA]
• Unsupervised Deep Embedding for Clustering Analysis - [Arxiv] [QA]

October 2015

• A Primer on Neural Network Models for Natural Language Processing - [Arxiv] [QA]

September 2015

• Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours - [Arxiv] [QA]
• Quantization based Fast Inner Product Search - [Arxiv] [QA]

June 2015

• Inverting Visual Representations with Convolutional Networks - [Arxiv] [QA]
• You Only Look Once: Unified, Real-Time Object Detection - [Arxiv] [QA]
• Visualizing and Understanding Recurrent Networks - [Arxiv] [QA]

May 2015

• A Critical Review of Recurrent Neural Networks for Sequence Learning - [Arxiv] [QA]
• Unsupervised Visual Representation Learning by Context Prediction - [Arxiv] [QA]
• Visual Semantic Role Labeling - [Arxiv] [QA]
• Contextual Action Recognition with R*CNN - [Arxiv] [QA]

April 2015

• Fast R-CNN - [Arxiv] [QA]

March 2015

• Label-Embedding for Image Classification - [Arxiv] [QA]
• LSTM: A Search Space Odyssey - [Arxiv] [QA]

February 2015

• Unsupervised Learning of Video Representations using LSTMs - [Arxiv] [QA]
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention - [Arxiv] [QA]

January 2015

• Transductive Multi-view Zero-Shot Learning - [Arxiv] [QA]
• A Dataset for Movie Description - [Arxiv] [QA]