Idiap Research Institute

research

∙ 05/02/2019

Full-Jacobian Representation of Neural Networks

Non-linear functions such as neural networks can be locally approximated...

Suraj Srinivas, et al. ∙

research

∙ 02/08/2020

Multi-task Reinforcement Learning with a Planning Quasi-Metric

We introduce a new reinforcement learning approach combining a planning ...

Vincent Micheli, et al. ∙

research

∙ 07/09/2020

Fast Transformers with Clustered Attention

Transformers have been proven a successful model for a variety of tasks ...

Apoorv Vyas, et al. ∙

research

∙ 11/16/2019

Unsupervised Representation Learning for Gaze Estimation

Although automatic gaze estimation is very important to a large variety ...

Yu Yu, et al. ∙

research

∙ 06/16/2020

Gradient Alignment in Deep Neural Networks

One cornerstone of interpretable deep learning is the high degree of vis...

Suraj Srinivas, et al. ∙

research

∙ 12/02/2019

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

Achieving robust multi-person 2D body landmark localization and pose est...

Angel Martínez-González, et al. ∙

research

∙ 05/12/2022

Robot Cooking with Stir-fry: Bimanual Non-prehensile Manipulation of Semi-fluid Objects

This letter describes an approach to achieve well-known Chinese cooking ...

Junjia Liu, et al. ∙

research

∙ 12/05/2019

Smartphone Multi-modal Biometric Authentication: Database and Evaluation

Biometric-based verification is widely employed on the smartphones for v...

Raghavendra Ramachandra, et al. ∙

research

∙ 05/03/2022

Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI

A fundamental research goal for Explainable AI (XAI) is to build models ...

Marco Valentino, et al. ∙

research

∙ 06/05/2018

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

End-to-end deep-learning networks recently demonstrated extremely good p...

Stepan Tulyakov, et al. ∙

research

∙ 09/19/2019

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

Face recognition is a mainstream biometric authentication method. Howeve...

Anjith George, et al. ∙

research

∙ 09/14/2021

On the Language-specificity of Multilingual BERT and the Impact of Fine-tuning

Recent work has shown evidence that the knowledge acquired by multilingu...

Marc Tanti, et al. ∙

research

∙ 08/02/2021

An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning

Humans effortlessly solve pushing tasks in everyday life but unlocking t...

Marco Ewerton, et al. ∙

research

∙ 09/02/2021

Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning

Though language model text embeddings have revolutionized NLP research, ...

Christos Theodoropoulos, et al. ∙

research

∙ 08/08/2019

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...

Subhadeep Dey, et al. ∙

research

∙ 07/09/2019

Deep Pixel-wise Binary Supervision for Face Presentation Attack Detection

Face recognition has evolved as a prominent biometric authentication mod...

Anjith George, et al. ∙

research

∙ 06/07/2016

Multilingual Visual Sentiment Concept Matching

The impact of culture in visual emotion perception has recently captured...

Nikolaos Pappas, et al. ∙

research

∙ 11/30/2017

Deep Neural Networks for Multiple Speaker Detection and Localization

We propose to use neural networks (NNs) for simultaneous detection and l...

Weipeng He, et al. ∙

research

∙ 09/04/2017

A Reproducible Study on Remote Heart Rate Measurement

This paper studies the problem of reproducible research in remote photop...

Guillaume Heusch, et al. ∙

research

∙ 12/22/2014

Learning linearly separable features for speech recognition using convolutional neural networks

Automatic speech recognition systems usually rely on spectral-based feat...

Dimitri Palaz, et al. ∙

research

∙ 07/10/2017

Improving speaker turn embedding by crossmodal transfer learning from face embedding

Learning speaker turn embeddings has shown considerable improvement in s...

Nam Le, et al. ∙

research

∙ 07/03/2017

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...

Stepan Tulyakov, et al. ∙

research

∙ 12/07/2013

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

Most phoneme recognition state-of-the-art systems rely on a classical ne...

Dimitri Palaz, et al. ∙

research

∙ 08/03/2016

A supermartingale approach to Gaussian process based sequential design of experiments

Gaussian process (GP) models have become a well-established frameworkfor...

Julien Bect, et al. ∙

research

∙ 02/09/2016

Nested Mini-Batch K-Means

A new algorithm is proposed which accelerates the mini-batch k-means alg...

James Newling, et al. ∙

research

∙ 01/22/2016

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...

Pranay Dighe, et al. ∙

research

∙ 10/13/2016

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

We investigate how a residual network can learn to predict the dynamics ...

François Fleuret, et al. ∙

research

∙ 11/12/2015

When Naïve Bayes Nearest Neighbours Meet Convolutional Neural Networks

Since Convolutional Neural Networks (CNNs) have become the leading learn...

Ilja Kuzborskij, et al. ∙

research

∙ 08/06/2014

Scalable Greedy Algorithms for Transfer Learning

In this paper we consider the binary transfer learning problem, focusing...

Ilja Kuzborskij, et al. ∙

research

∙ 10/06/2017

Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics

Lexical entailment, such as hyponymy, is a fundamental issue in the sema...

James Henderson, et al. ∙

research

∙ 09/30/2017

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

Vector-space models, from word embeddings to neural network parsers, hav...

Diana Nicoleta Popa, et al. ∙

research

∙ 09/14/2017

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

Neural sequence-to-sequence models achieve remarkable performance not on...

Lesly Miculicich Werlen, et al. ∙

research

∙ 07/04/2017

Multilingual Hierarchical Attention Networks for Document Classification

Hierarchical attention networks have recently achieved remarkable perfor...

Nikolaos Pappas, et al. ∙

research

∙ 10/19/2016

A Bayesian Approach to Estimation of Speaker Normalization Parameters

In this work, a Bayesian approach to speaker normalization is proposed t...

Dhananjay Ram, et al. ∙

research

∙ 08/16/2015

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

Every culture and language is unique. Our work expressly focuses on the ...

Brendan Jou, et al. ∙

research

∙ 11/27/2017

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

Phoneme-based multilingual training and different cross-lingual adaptati...

Sibo Tong, et al. ∙

research

∙ 06/16/2018

Joint Input-Label Embedding for Neural Text Classification

Neural text classification methods typically treat output classes as cat...

Nikolaos Pappas, et al. ∙

research

∙ 06/22/2018

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

The quest for comprehensive generative models of intonation that link li...

Branislav Gerazov, et al. ∙

research

∙ 08/31/2018

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...

Nikolaos Pappas, et al. ∙

research

∙ 09/05/2018

Document-Level Neural Machine Translation with Hierarchical Attention Networks

Neural Machine Translation (NMT) can be improved by including document-l...

Lesly Miculicich, et al. ∙

research

∙ 10/05/2018

Integrating Weakly Supervised Word Sense Disambiguation into Neural Machine Translation

This paper demonstrates that word sense disambiguation (WSD) can improve...

Xiao Pu, et al. ∙

research

∙ 10/11/2018

VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking

In this paper, we present a novel system that separates the voice of a t...

Quan Wang, et al. ∙

research

∙ 11/09/2018

Multilingual and Unsupervised Subword Modeling for Zero-Resource Languages

Unsupervised subword modeling aims to learn low-level representations of...

Enno Hermann, et al. ∙

research

∙ 11/27/2018

Geometry-aware Manipulability Transfer

Body posture influences human and robots performance in manipulation tas...

Noémie Jaquier, et al. ∙

research

∙ 12/20/2018

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

It is becoming increasingly easy to automatically replace a face of one ...

Pavel Korshunov, et al. ∙

research

∙ 12/13/2018

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

Recent advances in word embedding provide significant benefit to various...

Navid Rekabsaz, et al. ∙

research

∙ 12/25/2018

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

In recent years, Long Short-Term Memory (LSTM) has become a popular choi...

Suman Samui, et al. ∙

research

∙ 02/18/2019

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 ...

Florian Mai, et al. ∙

research

∙ 02/28/2019

Tensor-variate Mixture of Experts

When data are organized in matrices or arrays of higher dimensions (tens...

Noémie Jaquier, et al. ∙

research

∙ 04/09/2019

Hierarchical Planning of Dynamic Movements without Scheduled Contact Sequences

Most animal and human locomotion behaviors for solving complex tasks inv...

Carlos Mastalli, et al. ∙

Idiap Research Institute

Featured Researchers