• Publications
  • Influence
Learning to rank using gradient descent
TLDR
RankNet is introduced, an implementation of these ideas using a neural network to model the underlying ranking function, and test results on toy data and on data from a commercial internet search engine are presented. Expand
MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
TLDR
MCTest is presented, a freely available set of stories and associated questions intended for research on the machine comprehension of text that requires machines to answer multiple-choice reading comprehension questions about fictional stories, directly tackling the high-level goal of open-domain machine comprehension. Expand
Full body gait analysis with Kinect
TLDR
This work presents an accurate gait analysis system that is economical and non-intrusive, based on the Kinect sensor and thus can extract comprehensive gait information from all parts of the body, and suggests that the proposed technique can be used for continuous gait tracking at home. Expand
Automatic Discovery of Personal Topics to Organize Email
TLDR
This paper presents a procedure to automatically discover a user s personal topics by clustering their emails using appropriate keywords and demonstrates these keywords by creating an email/ document browser which makes use of these keywords as standing queries to create virtual folders that help organize, index and retrieve email efficiently. Expand
A foreground-background separation algorithm for image compression
TLDR
The SLIm system for separating text and line drawing from background images, in order to compress both more effectively is proposed and results show that the SLIm compression performance is attractive for many applications. Expand
Animacy Detection with Voting Models
TLDR
This work presents a state-of-the-art system which uses a number of simple classifiers with heterogeneous data sources in a voting scheme and shows how this framework can give direct insight into the behavior of the system, allowing us to more easily diagnose sources of error. Expand
Using audio fingerprinting for duplicate detection and thumbnail generation
TLDR
Two new applications of audio fingerprinting are presented: duplicate detection, whose goal is to identify duplicate audio clips in a set, even if they differ in compression quality or duration, and thumbnail generation, which aims to provide a representative short clip of a music track. Expand
DUPLICATE DETECTION AND AUDIO THUMBNAILS WITH AUDIO FINGERPRINTING
TLDR
This paper presents two new applications: duplicate detection, whose goal is to identify duplicate audio clips in a set, even if they differ in compression quality or duration, and thumbnail generation, which aims at providing a representative short clip of a music track. Expand
Selective Classifiers for Part-of-Speech Tagging
TLDR
It is shown that a selective classifier that is constructed as an abstaining committee of two off-the-shelf POS taggers can indeed achieve very high accuracies with modest drops in coverage, and the overall accuracy is computed. Expand
Human Gait Identification using Depth Gradient Histogram Energy Image
Earlier work where we evaluated how traditional Gait Energy Image (GEI) can be used to identify human gait and eventually human ID. However, we also witnessed how inaccurate segmentation (due toExpand
...
1
2
...