Bart Ons

Followers

Following

Public Views

Interests

Uploads

Papers by Bart Ons

A geometrical description of visual sensation II

Kragujevac journal of mathematics, 2010

Plateau's irradiation phenomenon in particular describes what one sees when observing a brighter ... more Plateau's irradiation phenomenon in particular describes what one sees when observing a brighter object on a darker background and a physically congruent darker object on a brighter background: the brighter object is seen as being larger. This phenomenon occurs in many optical visual illusions and it involves some fundamental aspects of human vision. We present a general geometrical model of human visual sensation and perception, hereby taking into account the law of Fechner in addition to the anisotropic smoothing that was introduced in [1], and explicitly illustrate its meaning for irradiation illusions of Helmholtz and Kitaoka.

Download

The influence of categorisation on perceived shape similarity within natural object categories

Perception, 2006

Previous studies have found effects of categorisation on perceived shape similarity with artifici... more Previous studies have found effects of categorisation on perceived shape similarity with artificial shapes. Here we ask to what extent similar effects are present with objects from natural categories. We trained sixteen subjects on a perceptual categorisation task (PCT). For each of four categories (birds, cars, fishes, and vases), we started from four extremes in a measured two-dimensional similarity space and created horizontal and vertical morph lines between them. Each subject learned to categorise two of these shape-spaces ...

The self-taught vocal interface

Eurasip Journal on Audio, Speech, and Music Processing, Dec 1, 2014

Speech technology is firmly rooted in daily life, most notably in command-and-control (C&C) appli... more Speech technology is firmly rooted in daily life, most notably in command-and-control (C&C) applications. C&C usability downgrades quickly, however, when used by people with non-standard speech. We pursue a fully adaptive vocal user interface (VUI) which can learn both vocabulary and grammar directly from interaction examples, achieving robustness against non-standard speech by building up models from scratch. This approach raises feasibility concerns on the amount of training material required to yield an acceptable recognition accuracy. In a previous work, we proposed a VUI based on non-negative matrix factorisation (NMF) to find recurrent acoustic and semantic patterns comprising spoken commands and device-specific actions, and showed its effectiveness on unimpaired speech. In this work, we evaluate the feasibility of a self-taught VUI on a new database called DOMOTICA-3, which contains dysarthric speech with typical commands in a home automation setting. Additionally, we compare our NMF-based system with a system based on Gaussian mixtures. The evaluation favours our NMF-based approach, yielding feasible recognition accuracies for people with dysarthric speech after a few learning examples. Finally, we propose the use of a multi-layered semantic frame structure and demonstrate its effectiveness in boosting overall performance.

Download

The effect of category learning on the representation of shape: dimensions can be biased but not differentiated

Journal of experimental psychology. General, 2003

Recent studies have suggested a profound influence of category learning on visual perception, res... more Recent studies have suggested a profound influence of category learning on visual perception, resulting in independent processing of previously integral dimensions. The authors reinvestigate this issue for shape dimensions. They first extend previous findings that some shape dimensions (aspect ratio and curvature) are processed in a separable way, whereas others (radial frequency components) are not. They then show that a category-learning phase improved the discrimination of a relevant with respect to an irrelevant dimension, but only for separable dimensions. No similar effect was found on the relative sensitivity for integral shape dimensions. Thus, category learning is capable of biasing separable shape dimensions but does not alter the status of dimensions in the visual system as either separable or integral.

Download

Effective weakly supervised semantic frame induction using expression sharing in hierarchical hidden Markov models

arXiv (Cornell University), Jan 30, 2019

We present a framework for the induction of semantic frames from utterances in the context of an ... more We present a framework for the induction of semantic frames from utterances in the context of an adaptive command-and-control interface. The system is trained on an individual user's utterances and the corresponding semantic frames representing controls. During training, no prior information on the alignment between utterance segments and frame slots and values is available. In addition, semantic frames in the training data can contain information that is not expressed in the utterances. To tackle this weakly supervised classification task, we propose a framework based on Hidden Markov Models (HMMs). Structural modifications, resulting in a hierarchical HMM, and an extension called expression sharing are introduced to minimize the amount of training time and effort required for the user. The dataset used for the present study is patcor, which contains commands uttered in the context of a vocally guided card game, Patience. Experiments were carried out on orthographic and phonetic transcriptions of commands, segmented on different levels of n-gram granularity. The experimental results show positive effects of all the studied system extensions, with some effect differences between the different input representations. Moreover, evaluation experiments on held-out data with the optimal system configuration show that the extended system is able to achieve high accuracies with relatively small amounts of training data.

Download

Study on the effects of automation on road user behaviour and performance

The aim of this study is to provide strategic and practical advice to the European Commission Gen... more The aim of this study is to provide strategic and practical advice to the European Commission General Directorate DG MOVE on the policy-related actions required to address disruptive digital developments, particularly the transition to automated driving and its effects on driver behaviour and performance. Automated driving brings a number of changes to the traffic system. The topics addressed include the expected evolution of automated driving, changes in human-machine interfaces (in the vehicle and in interactions with road infrastructure), traffic rules, driving licences, and the training of professional drivers. It includes also a reflection on these topics towards the development of a code of conduct for the transition to automated mobility. Based on a broad literature review and the views of experts, different issues are discussed, and a number of policy-oriented recommendations are put forward

TransAID Deliverable 8.1: Stakeholder consultation report (final version)

Download

TransAID Deliverable 8.2: Meta-analysis of the results

Download

TransAID Deliverable 4.2 - Preliminary Simulation and Assessment of enhanced traffic management measures - iteration 2

TransAID Deliverable 6.2/2 - Assessment of Traffic Management Procedures in Transition Areas

Enhanced Traffic Management Procedures of Connected and Autonomous Vehicles in Transition Areas

In light of the increasing trend towards vehicle connectivity and automation, there will be areas... more In light of the increasing trend towards vehicle connectivity and automation, there will be areas and situations on the roads where high automation can be granted, and others where it is not allowed or not possible. These are termed ‘Transition Areas’. Without proper traffic management, such areas may lead to vehicles issuing take-over requests (TORs), which in turn can trigger transitions of control (ToCs), or even minimum-risk manoeuvres (MRMs). In this respect, the TransAID Horizon 2020 project develops and demonstrates traffic management procedures and protocols to enable smooth coexistence of automated, connected, andconventional vehicles, with the goal of avoiding ToCs and MRMs, or at least postponing/accommodating them. Our simulations confirmed that proper traffic management, taking the traffic mix into account, can prevent drops in traffic efficiency, which in turn leads to a more performant, safer, and cleaner traffic system, when taking the capabilities of connected and a...

Download

inferior temporal neurons Effects of category learning on the stimulus selectivity of macaque

TransAID D4.1 - Overview of Existing and Enhanced Traffic Management Procedures - iteration 2

TransAID D9.3 (reporting template)

Project Acronym TransAID Project Title Transition Areas for Infrastructure-Assisted Driving Proje... more Project Acronym TransAID Project Title Transition Areas for Infrastructure-Assisted Driving Project Number Horizon 2020 ART-05-2016 – GA Nr. 723390 Work Package WP3 Modelling and Impact Assessment of Automated Vehicles Lead Beneficiary CERTH HIT (CRT) Editor / Main Author Evangelos Mintsis CRT Reviewer Michele Rondinone HMETC Dissemination Level PU Contractual Delivery Date 29/02/2020 (M30) Actual Delivery Date 29/02/2020 Version V2.0

Download

The Self-taught Speech Interface

Alle rechten voorbehouden. Niets uit deze uitgave mag worden vermenigvuldigd en/of openbaar gemaa... more Alle rechten voorbehouden. Niets uit deze uitgave mag worden vermenigvuldigd en/of openbaar gemaakt worden door middel van druk, fotokopie, microfilm, elektronisch of op welke andere wĳze ook zonder voorafgaande schriftelĳke toestemming van de uitgever. All rights reserved. No part of the publication may be reproduced in any form by print, photoprint, microfilm, electronic or any other means without written permission from the publisher.

Download

TransAID Deliverable 4.3 - Translation of traffic management measures to iCS, scale-up, and wider deployment

Effects of category learning on the stimulus selectivity of macaque inferior temporal neurons

Learning & Memory, 2008

Primates can learn to categorize complex shapes, but as yet it is unclear how this categorization... more Primates can learn to categorize complex shapes, but as yet it is unclear how this categorization learning affects the representation of shape in visual cortex. Previous studies that have examined the effect of categorization learning on shape representation in the macaque inferior temporal (IT) cortex have produced diverse and conflicting results that are difficult to interpret owing to inadequacies in design. The present study overcomes these issues by recording IT responses before and after categorization learning. We used parameterized shapes that varied along two shape dimensions. Monkeys were extensively trained to categorize the shapes along one of the two dimensions. Unlike previous studies, our paradigm counterbalanced the relevant categorization dimension across animals. We found that categorization learning increased selectivity specifically for the category-relevant stimulus dimension (i.e., an expanded representation of the trained dimension), and that the ratio of with...

Download

A varying abstraction model for categorization

status: published

A model is proposed that elegantly unifies the traditional exemplar and prototype models. These t... more A model is proposed that elegantly unifies the traditional exemplar and prototype models. These two models are extreme cases of the proposed varying abstraction model. The unifying model further makes room for many new intermediate pseudo-exemplar models. A preliminary analysis using Medin and Schaffer's (1978) 5-4 structure pointed to such an intermediate model that outperformed the prototype and exemplar models.

Download

An anisotropic retouche of Koenderink and van Doorn's view on the nature of observation in accordance with the work of Milutin Borisavljevic on scientiflc aesthetics

A Geometrical Description of Visual Sensation II a Complemented Model for Visual Sensation Explicitly Taking Into Account the Law of Fechner, and Its Application to Plateau’s Irradiation

Plateau’s irradiation phenomenon in particular describes what one sees when observing a brighter ... more Plateau’s irradiation phenomenon in particular describes what one sees when observing a brighter object on a darker background and a physically congruent darker object on a brighter background: the brighter object is seen as being larger. This phenomenon occurs in many optical visual illusions and it involves some fundamental aspects of human vision. We present a general geometrical model of human visual sensation and perception, hereby taking into account the law of Fechner in addition to the anisotropic smoothing that was introduced in [1], and explicitly illustrate its meaning for irradiation illusions of Helmholtz and Kitaoka.

Download

Bart Ons

Uploads

Papers by Bart Ons

Log In