56 Results
October 10, 2016
Learning to Refine Object Segments
European Conference on Computer Vision
In this work we propose to augment feedforward nets for object segmentation with a novel top-down refinement approach.
By: Pedro O. Pinheiro, Tsung-Yi Lin, Ronan Collobert, Piotr Dollar
Artificial Intelligence 
Computer Vision 
Facebook AI Research (FAIR) September 18, 2016
A MultiPath Network for Object Detection
BMVC
We test three modifications to the standard Fast R-CNN object detector to determine if they can overcome the object detection challenges in a COCO object detection dataset.
By: Sergey Zagoruyko, Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala, Piotr DollarAugust 16, 2016
Synergy of Monotonic Rules
JMLR
This article describes a method for constructing a special rule (we call it synergy rule) that uses as its input information the outputs (scores) of several monotonic rules which solve the same pattern recognition problem.
By: Vladimir Vapnik, Rauf IzmailovAugust 11, 2016
Semi-Supervised Convolutional Networks for Translation Adaptation with Tiny Amount of In-domain Data
Conference on Natural Language Learning
We propose a method which uses semi-supervised convolutional neural networks (CNNs) to select in-domain training data for statistical machine translation.
By: Boxing Chen, Fei Huang
Natural Language Processing & Speech June 26, 2016
End-to-End Voxel-to-Voxel Prediction
Conference on Computer Vision and Pattern Recognition (CVPR)
Over the last few years deep learning methods have emerged as one of the most prominent approaches for video analysis with most successful applications having been in the area of video classification and detection. In this paper we challenge these views by presenting a deep 3D convolutional architecture trained end to end to perform voxel-level prediction, i.e., to output a variable at every voxel of the video.
By: Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri
Machine Learning June 8, 2016
Key-Value Memory Networks for Directly Reading Documents
EMNLP 2016
This paper introduces a new method, Key-Value Memory Networks, that makes reading documents more viable by utilizing different encodings in the addressing and output stages of the memory read operation.
By: Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, Jason WestonMay 2, 2016
Deep Multi-Scale Video Prediction Beyond Mean Square Error
ICLR 2016
The paper is about predicting future frames in video sequences given the previous frames.
By: Michael Mathieu, Camille Couprie, Yann LeCunMay 2, 2016
Metric Learning with Adaptive Density Discrimination
ICLR
Distance metric learning approaches learn a transformation to a representation space in which distance is in correspondence with a predefined notion of similarity.
By: Oren Rippel, Manohar Paluri, Piotr Dollar, Lubomir BourdevSeptember 17, 2015
Improved Arabic Dialect Classification with Social Media Data
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Arabic dialect classification has been an important and challenging problem for Arabic language processing, especially for social media text analysis and machine translation. In this paper we propose an approach to improving Arabic dialect classification with semi-supervised learning: multiple classifiers are trained with weakly supervised, strongly supervised, and unsupervised data. Their combination yields significant and consistent improvement on two different test sets.
By: Fei HuangJune 12, 2015
Web-Scale Training for Face Identification
The IEEE Conference on Computer Vision and Pattern Recognition
We study face recognition and show that three distinct properties have surprising effects on the transferability of deep convolutional networks (CNN)
By: Yaniv Taigman, Ming Yang, Marc'Aurelio Ranzato, Lior Wolf