Concept

Classement automatique

Publications associées (608)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Information theoretic feature extraction for audio-visual speech recognition

Jean-Philippe Thiran, Mihai Gurban

The problem of feature selection has been thoroughly analyzed in the context of pattern classification, with the purpose of avoiding the curse of dimensionality. However, in the context of multimodal signal processing, this problem has been studied less. O ...

2009

A Comprehensive Stochastic Model of Window Usage: Theory and Validation

Darren Robinson, Frédéric Haldi

Based on almost seven years of continuous measurements we have analysed in detail the influence of occupancy patterns, indoor temperature and outdoor climate parameters (temperature, wind speed and direction, relative humidity and rainfall) on window openi ...

2009

Compact Signatures for High-speed Interest Point Description and Matching

Pascal Fua, Vincent Lepetit, Michael Calonder

Prominent feature point descriptors such as SIFT and SURF allow reliable real-time matching but at a computational cost that limits the number of points that can be handled on PCs, and even more on less powerful mobile devices. A recently proposed techniqu ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2009

Joint Pose Estimator and Feature Learning for Object Detection

Pascal Fua, François Fleuret, Karim Ali, David Hasler

A new learning strategy for object detection is presented. The proposed scheme forgoes the need to train a collection of detectors dedicated to homogeneous families of poses, and instead learns a single classifier that has the inherent ability to deform ba ...

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2009

Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space

Aude Billard, Sylvain Calinon

We present a probabilistic architecture for solving generically the problem of extracting the task constraints through a Programming by Demonstration (PbD) framework and for generalizing the acquired knowledge to various situations. In previous work, we pr ...

2009

Malicious Traffic Detection in Local Networks with Snort

Loïc Etienne

Snort is an open source Network Intrusion Detection System combining the benefits of signature, protocol and anomaly based inspection and is considered to be the most widely de- ployed IDS/IPS technology worldwide. However, Snort's deployment in a large co ...

2009

Improving biometric verification with class-independent quality information

Andrzej Drygajlo, Krzysztof Kryszczuk

Existing approaches to biometric classification with quality measures make a clear distinction between the single-modality applications and the multi-modal scenarios. This study bridges this gap with Q-stack, a stacking-based classifier ensemble, which use ...

2009

Interactions with window openings by office occupants

Darren Robinson, Frédéric Haldi

Based on almost seven years of continuous measurements, we have analysed in detail the influence of occupancy patterns, indoor temperature and outdoor climate parameters (temperature, wind speed and direction, relative humidity and rainfall) on window open ...

2009

A Large Margin Algorithm for Forced Alignment

We describe and analyze a discriminative algorithm for learning to align a phoneme sequence of a speech utterance with its acoustical signal counterpart by predicting a timing sequence representing the phoneme start times. In contrast to common HMM-based a ...

John Wiley and Sons2009

Support Vector Machines with a Reject Option

We consider the problem of binary classification where the classfier may abstain instead of classifying each observation. The Bayes decision rule for this setup, known as Chow’s rule, is deﬁned by two thresholds on posterior probabilities. From simple desi ...

Idiap2009