Idiap Research Institute

∙ Martigny , Switzerland ∙ 0 followers

Artificial Intelligence for Society. The Idiap Research Institute is an independent, nonprofit research foundation affiliated with the Ecole Polytechnique Fédérale de Lausanne (EPFL). Its activities encompass basic research, training (graduate and post...

Full-Jacobian Representation of Neural Networks

Non-linear functions such as neural networks can be locally approximated...
05/02/2019 ∙ by Suraj Srinivas, et al. ∙ 70 ∙ share

read it
Multi-task Reinforcement Learning with a Planning Quasi-Metric

We introduce a new reinforcement learning approach combining a planning ...
02/08/2020 ∙ by Vincent Micheli, et al. ∙ 55 ∙ share

read it
Fast Transformers with Clustered Attention

Transformers have been proven a successful model for a variety of tasks ...
07/09/2020 ∙ by Apoorv Vyas, et al. ∙ 34 ∙ share

read it
Unsupervised Representation Learning for Gaze Estimation

Although automatic gaze estimation is very important to a large variety ...
11/16/2019 ∙ by Yu Yu, et al. ∙ 30 ∙ share

read it
Gradient Alignment in Deep Neural Networks

One cornerstone of interpretable deep learning is the high degree of vis...
06/16/2020 ∙ by Suraj Srinivas, et al. ∙ 17 ∙ share

read it
Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation

Achieving robust multi-person 2D body landmark localization and pose est...
12/02/2019 ∙ by Angel Martínez-González, et al. ∙ 16 ∙ share

read it
Smartphone Multi-modal Biometric Authentication: Database and Evaluation

Biometric-based verification is widely employed on the smartphones for v...
12/05/2019 ∙ by Raghavendra Ramachandra, et al. ∙ 12 ∙ share

read it
Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

End-to-end deep-learning networks recently demonstrated extremely good p...
06/05/2018 ∙ by Stepan Tulyakov, et al. ∙ 10 ∙ share

read it
Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Network

Face recognition is a mainstream biometric authentication method. Howeve...
09/19/2019 ∙ by Anjith George, et al. ∙ 9 ∙ share

read it
Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition

In this paper, we explore various approaches for semi supervised learnin...
08/08/2019 ∙ by Subhadeep Dey, et al. ∙ 3 ∙ share

read it
Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection

Face recognition has evolved as a prominent biometric authentication mod...
07/09/2019 ∙ by Anjith George, et al. ∙ 2 ∙ share

read it
Multilingual Visual Sentiment Concept Matching

The impact of culture in visual emotion perception has recently captured...
06/07/2016 ∙ by Nikolaos Pappas, et al. ∙ 0 ∙ share

read it
Deep Neural Networks for Multiple Speaker Detection and Localization

We propose to use neural networks (NNs) for simultaneous detection and l...
11/30/2017 ∙ by Weipeng He, et al. ∙ 0 ∙ share

read it
A Reproducible Study on Remote Heart Rate Measurement

This paper studies the problem of reproducible research in remote photop...
09/04/2017 ∙ by Guillaume Heusch, et al. ∙ 0 ∙ share

read it
Learning linearly separable features for speech recognition using convolutional neural networks

Automatic speech recognition systems usually rely on spectral-based feat...
12/22/2014 ∙ by Dimitri Palaz, et al. ∙ 0 ∙ share

read it
Improving speaker turn embedding by crossmodal transfer learning from face embedding

Learning speaker turn embeddings has shown considerable improvement in s...
07/10/2017 ∙ by Nam Le, et al. ∙ 0 ∙ share

read it
Geometric calibration of Colour and Stereo Surface Imaging System of ESA's Trace Gas Orbiter

There are many geometric calibration methods for "standard" cameras. The...
07/03/2017 ∙ by Stepan Tulyakov, et al. ∙ 0 ∙ share

read it
End-to-end Phoneme Sequence Recognition using Convolutional Neural Networks

Most phoneme recognition state-of-the-art systems rely on a classical ne...
12/07/2013 ∙ by Dimitri Palaz, et al. ∙ 0 ∙ share

read it
A supermartingale approach to Gaussian process based sequential design of experiments

Gaussian process (GP) models have become a well-established frameworkfor...
08/03/2016 ∙ by Julien Bect, et al. ∙ 0 ∙ share

read it
Nested Mini-Batch K-Means

A new algorithm is proposed which accelerates the mini-batch k-means alg...
02/09/2016 ∙ by James Newling, et al. ∙ 0 ∙ share

read it
Exploiting Low-dimensional Structures to Enhance DNN Based Acoustic Modeling in Speech Recognition

We propose to model the acoustic space of deep neural network (DNN) clas...
01/22/2016 ∙ by Pranay Dighe, et al. ∙ 0 ∙ share

read it
Predicting the dynamics of 2d objects with a deep residual network

We investigate how a residual network can learn to predict the dynamics ...
10/13/2016 ∙ by François Fleuret, et al. ∙ 0 ∙ share

read it
When Naïve Bayes Nearest Neighbours Meet Convolutional Neural Networks

Since Convolutional Neural Networks (CNNs) have become the leading learn...
11/12/2015 ∙ by Ilja Kuzborskij, et al. ∙ 0 ∙ share

read it
Scalable Greedy Algorithms for Transfer Learning

In this paper we consider the binary transfer learning problem, focusing...
08/06/2014 ∙ by Ilja Kuzborskij, et al. ∙ 0 ∙ share

read it
Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics

Lexical entailment, such as hyponymy, is a fundamental issue in the sema...
10/06/2017 ∙ by James Henderson, et al. ∙ 0 ∙ share

read it
Bag-of-Vector Embeddings of Dependency Graphs for Semantic Induction

Vector-space models, from word embeddings to neural network parsers, hav...
09/30/2017 ∙ by Diana Nicoleta Popa, et al. ∙ 0 ∙ share

read it
Global-Context Neural Machine Translation through Target-Side Attentive Residual Connections

Neural sequence-to-sequence models achieve remarkable performance not on...
09/14/2017 ∙ by Lesly Miculicich Werlen, et al. ∙ 0 ∙ share

read it
Multilingual Hierarchical Attention Networks for Document Classification

Hierarchical attention networks have recently achieved remarkable perfor...
07/04/2017 ∙ by Nikolaos Pappas, et al. ∙ 0 ∙ share

read it
A Bayesian Approach to Estimation of Speaker Normalization Parameters

In this work, a Bayesian approach to speaker normalization is proposed t...
10/19/2016 ∙ by Dhananjay Ram, et al. ∙ 0 ∙ share

read it
Visual Affect Around the World: A Large-scale Multilingual Visual Sentiment Ontology

Every culture and language is unique. Our work expressly focuses on the ...
08/16/2015 ∙ by Brendan Jou, et al. ∙ 0 ∙ share

read it
Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model

Phoneme-based multilingual training and different cross-lingual adaptati...
11/27/2017 ∙ by Sibo Tong, et al. ∙ 0 ∙ share

read it
Joint Input-Label Embedding for Neural Text Classification

Neural text classification methods typically treat output classes as cat...
06/16/2018 ∙ by Nikolaos Pappas, et al. ∙ 0 ∙ share

read it
A Variational Prosody Model for the decomposition and synthesis of speech prosody

The quest for comprehensive generative models of intonation that link li...
06/22/2018 ∙ by Branislav Gerazov, et al. ∙ 0 ∙ share

read it
Beyond Weight Tying: Learning Joint Input-Output Embeddings for Neural Machine Translation

Tying the weights of the target word embeddings with the target word cla...
08/31/2018 ∙ by Nikolaos Pappas, et al. ∙ 0 ∙ share

read it
Document-Level Neural Machine Translation with Hierarchical Attention Networks

Neural Machine Translation (NMT) can be improved by including document-l...
09/05/2018 ∙ by Lesly Miculicich, et al. ∙ 0 ∙ share

read it
Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation

This paper demonstrates that word sense disambiguation (WSD) can improve...
10/05/2018 ∙ by Xiao Pu, et al. ∙ 0 ∙ share

read it
VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking

In this paper, we present a novel system that separates the voice of a t...
10/11/2018 ∙ by Quan Wang, et al. ∙ 0 ∙ share

read it
Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages

Unsupervised subword modeling aims to learn low-level representations of...
11/09/2018 ∙ by Enno Hermann, et al. ∙ 0 ∙ share

read it
Geometry-aware Manipulability Transfer

Body posture influences human and robots performance in manipulation tas...
11/27/2018 ∙ by Noémie Jaquier, et al. ∙ 0 ∙ share

read it
DeepFakes: a New Threat to Face Recognition? Assessment and Detection

It is becoming increasingly easy to automatically replace a face of one ...
12/20/2018 ∙ by Pavel Korshunov, et al. ∙ 0 ∙ share

read it
An Unbiased Approach to Quantification of Gender Inclination using Interpretable Word Representations

Recent advances in word embedding provide significant benefit to various...
12/13/2018 ∙ by Navid Rekabsaz, et al. ∙ 0 ∙ share

read it
Tensor-Train Long Short-Term Memory for Monaural Speech Enhancement

In recent years, Long Short-Term Memory (LSTM) has become a popular choi...
12/25/2018 ∙ by Suman Samui, et al. ∙ 0 ∙ share

read it
CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model

Continuous Bag of Words (CBOW) is a powerful text embedding method. Due ...
02/18/2019 ∙ by Florian Mai, et al. ∙ 0 ∙ share

read it
Tensor-variate Mixture of Experts

When data are organized in matrices or arrays of higher dimensions (tens...
02/28/2019 ∙ by Noémie Jaquier, et al. ∙ 0 ∙ share

read it
Hierarchical Planning of Dynamic Movements without Scheduled Contact Sequences

Most animal and human locomotion behaviors for solving complex tasks inv...
04/09/2019 ∙ by Carlos Mastalli, et al. ∙ 0 ∙ share

read it
Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis

As an indicator of human attention gaze is a subtle behavioral cue which...
04/24/2019 ∙ by Yu Yu, et al. ∙ 0 ∙ share

read it
Speech Emotion Recognition Using Multi-Hop Attention Mechanism

In this paper, we are interested in exploiting textual and acoustic data...
04/23/2019 ∙ by Seunghyun Yoon, et al. ∙ 0 ∙ share

read it
Bayesian Gaussian mixture model for robotic policy imitation

A common approach to learn robotic skills is to imitate a policy demonst...
04/24/2019 ∙ by Emmanuel Pignat, et al. ∙ 0 ∙ share

read it
On the Effect of Low-Frequency Terms on Neural-IR Models

Low-frequency terms are a recurring challenge for information retrieval ...
04/29/2019 ∙ by Hofstätter, et al. ∙ 0 ∙ share

read it
Nullspace Structure in Model Predictive Control

Robotic tasks can be accomplished by exploiting different forms of redun...
05/23/2019 ∙ by Hakan Girgin, et al. ∙ 0 ∙ share

read it

Idiap Research Institute

Featured Researchers