no code implementations • 30 Mar 2022 • Vineet Garg, Ognjen Rudovic, Pranay Dighe, Ahmed H. Abdelaziz, Erik Marchi, Saurabh Adya, Chandra Dhir, Ahmed Tewfik
We also show that the ensemble of the LatticeRNN and acoustic-distilled models brings further accuracy improvement of 20%.
no code implementations • 9 Oct 2021 • Ognjen Rudovic, Akanksha Bindal, Vineet Garg, Pramod Simha, Pranay Dighe, Sachin Kajarekar
When interacting with smart devices such as mobile phones or wearables, the user typically invokes a virtual assistant (VA) by saying a keyword or by pressing a button on the device.
1 code implementation • 12 Jan 2021 • Ognjen Rudovic, Nicolas Tobis, Sebastian Kaltwang, Björn Schuller, Daniel Rueckert, Jeffrey F. Cohn, Rosalind W. Picard
A potential approach to tackling this is Federated Learning (FL), which enables multiple parties to collaboratively learn a shared prediction model by using parameters of locally trained models while keeping raw training data locally.
no code implementations • 26 Sep 2019 • Mihee Lee, Ognjen Rudovic, Vladimir Pavlovic, Maja Pantic
In this paper, we propose a deep learning approach for facial AU detection that can easily and in a fast manner adapt to a new AU or target subject by leveraging only a few labeled samples from the new task (either an AU or subject).
no code implementations • 7 Jun 2019 • Ognjen Rudovic, Meiru Zhang, Bjorn Schuller, Rosalind W. Picard
Human behavior expression and experience are inherently multi-modal, and characterized by vast individual and contextual heterogeneity.
no code implementations • 19 Apr 2019 • Ognjen Rudovic, Yuria Utsumi, Ricardo Guerrero, Kelly Peterson, Daniel Rueckert, Rosalind W. Picard
We introduce a novel personalized Gaussian Process Experts (pGPE) model for predicting per-subject ADAS-Cog13 cognitive scores -- a significant predictor of Alzheimer's Disease (AD) in the cognitive domain -- over the future 6, 12, 18, and 24 months.
no code implementations • ICLR 2019 • Behnam Gholami, Pritish Sahu, Ognjen Rudovic, Konstantinos Bousmalis, Vladimir Pavlovic
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain.
no code implementations • 1 Mar 2018 • Adria Ruiz, Ognjen Rudovic, Xavier Binefa, Maja Pantic
In this framework, we treat instance-labels as temporally-dependent latent variables in an Undirected Graphical Model.
1 code implementation • 22 Feb 2018 • Yuria Utsumi, Ognjen Rudovic, Kelly Peterson, Ricardo Guerrero, Rosalind W. Picard
In this paper, we introduce the use of a personalized Gaussian Process model (pGP) to predict per-patient changes in ADAS-Cog13 -- a significant predictor of Alzheimer's Disease (AD) in the cognitive domain -- using data from each patient's previous visits, and testing on future (held-out) data.
no code implementations • 4 Feb 2018 • Ognjen Rudovic, Jaeryoung Lee, Miles Dai, Bjorn Schuller, Rosalind Picard
To tackle the heterogeneity in behavioral cues of children with autism, we use the latest advances in deep learning to formulate a personalized machine learning (ML) framework for automatic perception of the childrens affective states and engagement during robot-assisted autism therapy.
1 code implementation • 1 Dec 2017 • Kelly Peterson, Ognjen Rudovic, Ricardo Guerrero, Rosalind W. Picard
In this paper, we introduce the use of a personalized Gaussian Process model (pGP) to predict the key metrics of Alzheimer's Disease progression (MMSE, ADAS-Cog13, CDRSB and CS) based on each patient's previous visits.
no code implementations • 10 Nov 2017 • Daniel Lopez-Martinez, Ognjen Rudovic, Rosalind Picard
Pain is a subjective experience commonly measured through patient's self report.
no code implementations • 29 Sep 2017 • Cuong D. Tran, Ognjen Rudovic, Vladimir Pavlovic
We study the task of unsupervised domain adaptation, where no labeled data from the target domain is provided during training time.
no code implementations • 22 Jun 2017 • Daniel Lopez Martinez, Ognjen Rudovic, Rosalind Picard
To the best of our knowledge, this is the first approach to automatically estimate VAS from face images.
no code implementations • ICCV 2017 • Dieu Linh Tran, Robert Walecki, Ognjen Rudovic, Stefanos Eleftheriadis, Bjørn Schuller, Maja Pantic
Potentially, this makes VAEs a suitable approach for learning facial features for AU intensity estimation.
no code implementations • 6 Sep 2016 • Adria Ruiz, Ognjen Rudovic, Xavier Binefa, Maja Pantic
In this paper, we address the Multi-Instance-Learning (MIL) problem when bag labels are naturally represented as ordinal variables (Multi--Instance--Ordinal Regression).
no code implementations • 16 Aug 2016 • Stefanos Eleftheriadis, Ognjen Rudovic, Marc P. Deisenroth, Maja Pantic
In particular, we introduce GP encoders to project multiple observed features onto a latent space, while GP decoders are responsible for reconstructing the original features.
no code implementations • CVPR 2016 • Robert Walecki, Ognjen Rudovic, Vladimir Pavlovic, Maja Pantic
Joint modeling of the intensity of facial action units (AUs) from face images is challenging due to the large number of AUs (30+) and their intensity levels (6).
no code implementations • 11 Apr 2016 • Stefanos Eleftheriadis, Ognjen Rudovic, Marc P. Deisenroth, Maja Pantic
The adaptation of the classifier is facilitated in probabilistic fashion by conditioning the target expert on multiple source experts.
no code implementations • ICCV 2015 • Stefanos Eleftheriadis, Ognjen Rudovic, Maja Pantic
We propose a novel multi-conditional latent variable model for simultaneous facial feature fusion and detection of facial action units.
no code implementations • 13 Oct 2015 • Robert Walecki, Ognjen Rudovic, Vladimir Pavlovic, Maja Pantic
For instance, in the case of AU detection, the goal is to discriminate between the segments of an image sequence in which this AU is active or inactive.
no code implementations • 22 Jan 2013 • Ognjen Rudovic, Maja Pantic, Vladimir Pavlovic
We propose a novel method for automatic pain intensity estimation from facial images based on the framework of kernel Conditional Ordinal Random Fields (KCORF).