Talks

A list of talks, lectures, presentations and posters.

2019

07.10.2019 / Datamod 2019 - Porto, Portugal

Oral presentation of the paper “How to look next? A data-driven approach for scanpath prediction” during the 8th International Symposium From Data to Models and Back (DataMod). Current visual attention models mostly rely, when considering static stimuli, on the following procedure. Given an image, a saliency map is computed, which, in turn, might serve the purpose of predicting a sequence of gaze shifts, namely a scanpath instantiating the dynamics of visual attention deployment. The temporal pattern of attention unfolding is thus confined to the scanpath generation stage, whilst salience is conceived as a static map, at best conflating a number of factors (bottom-up information, top-down, spatial biases, etc.). In this paper we propose a novel sequential scheme that consists of a three-stage processing relying on a center-bias model, a context/layout model, and an object-based model, respectively. Each stage contributes, at different times, to the sequential sampling of the final scanpath. We compare the method against classic scanpath generation that exploits state-of-the-art static saliency model. Results show that accounting for the structure of the temporal unfolding leads to gaze dynamics close to human gaze behaviour (presentation)

12.09.2019 / ICIAP 2019 - Trento, Italy

Spotlight (15% acceptance rate) and poster presentation of the paper “Problems with Saliency Maps” during the 20th International Conference on Image Analysis and Processing (ICIAP). Despite the popularity that saliency models have gained in the computer vision community, they are most often conceived, exploited and benchmarked without taking heed of a number of problems and subtle issues they bring about. When saliency maps are used as proxies for the likelihood of fixating a location in a viewed scene, one such issue is the temporal dimension of visual attention deployment. Through a simple simulation it is shown how neglecting this dimension leads to results that at best cast shadows on the predictive performance of a model and its assessment via benchmarking procedures. (spotlight, poster)

24.08.2019 / ICIG 2019 - Beijing, China

Poster presentation (34% acceptance rate) of the paper “OpenFACS : an open source FACS-based 3D face animation system” during the 10th International Conference on Image and Graphics (ICIG). OpenFACS is a software that allows the simulation of realistic facial expressions through the manipulation of specific action units as defined in the Facial Action Coding System. OpenFACS has been developed together with an API which is suitable to generate real-time dynamic facial expressions for a three-dimensional character. It can be easily embedded in existing systems without any prior experience in computer graphics. In this note, we discuss the adopted face model, the implemented architecture and provide additional details of model dynamics. Finally, a validation experiment is proposed to assess the effectiveness of the model. (poster)

18.03.2019 / Ital-IA 2019 - Rome, Italy

Flash presentation of a contribution submitted to the Workshop AI for Health and Medicine during the 1st CINI National Meeting on Artificial Intelligence. (presentation)

12.02.2019 / Domus Academy - Milan, Italy

Invited lecture on “Affective computing” as part of the Workshop of Tangible Interaction held by the Master in Interaction Design of Domus Academy, NABA. (presentation)

14.01.2019 / Universitätsklinikum - Freiburg, Germany

Invited workshop on “A probabilistic approach to the construction of a multimodal affect space” held at the Universitätsklinikum of Freiburg. (presentation)

2018

01.10.2018 / Domus Academy - Milan, Italy

Invited lecture on “Affective computing” as part of the Workshop of Tangible Interaction held by the Master in Interaction Design of Domus Academy, NABA.

30/31.08.2018 / CVPL 2018 - Vico Equense (NA), Italy

Presentation of my PhD thesis and the activities done in the Perceptual computing and Human Sensing Lab during the biennal meeting of the Italian Association for Computer Vision, Pattern Recognition and Machine Learning (CVPL). (presentation)

25.06.2018 / Datamod 2018 - Toulouse, France

Oral presentation of the paper “Personality gaze patterns unveiled via automatic relevance determination” during the 7th International Symposium - From Data to Models and Back (DataMod). In this paper we aim at understanding how the human gaze behaviour in social context, as along a face-to-face interaction, is correlated with personality traits. We propose a different analysis perspective based on novel data-mining techniques and a probabilistic classification method that relies on Gaussian Processes exploiting Automatic Relevance Determination (ARD) kernel. (presentation)

2017

15.11.2017 / ICMI 2017 - Glasgow, UK

Poster presentation (44% acceptance rate) of the paper “AMHUSE: A Multimodal dataset for HUmour SEnsing” during the 19th ACM International Conference on Multimodal Interaction. In this paper we present A Multimodal dataset for HUmour SEnsing along with a novel web-based annotation tool named DANTE (Dimensional ANnotation Tool for Emotions). The dataset is the result of an experiment concerning amusement elicitation. Gathered data include RGB video and depth sequences along with physiological responses (electrodermal activity, blood volume pulse, temperature). The videos were later annotated by 4 experts in terms of valence and arousal continuous dimensions. Both the dataset and the annotation tool are made publicly available for research purposes. (poster)

15.09.2017 / ICIAP 2017 - Catania, Italy

Oral presentation (10% acceptance rate) of the paper “Virtual EMG via facial video analysis” during the 19th International Conference on Image Analysis and Processing. In this paper we propose a method that uses the framework of Gaussian Process regression to predict the facial electromyographic signal from videos where people display non-posed affective expressions. The paper won the Best Paper Award. (presentation)

11.09.2017 / W3AS 2017 - Catania, Italy

Oral presentation of the paper “A note on modelling a somatic motor space for affective facial expressions” during the 1st Automatic Affect Analysis and Synthesis Workshop. We discuss modelling issues related to the design of a somatic facial motor space. The variants proposed are conceived to be part of a larger system for dealing with simulation-based face emotion analysis along dual interactions. (slides)

14.02.2017 / Domus Academy - Milan, Italy

Invited lecture on “Affective computing” as part of the Workshop of Tangible Interaction held by the Master in Interaction Design of Domus Academy.

2016

09.11.2016 / Opendot - Milan, Italy

Invited speaker at the opentalk “Machine Learning tra etica, arte e legge”, organised by opendot. (slides)

2015

09.09.2015 / ICIAP 2015 - Genova, Italy

Poster presentation (55% acceptance rate) of the paper “The color of smiling: computational synaesthesia of facial expressions” during the 18th International Conference on Image Analysis and Processing. This note gives a preliminary account of the transcoding or rechanneling problem between different stimuli as it is of interest for the natural interaction or affective computing fields. By the consideration of a simple example, namely the color response of an affective lamp to a sensed facial expression, we frame the problem within an information-theoretic perspective. (poster)

2014

11.12.2014 / EUVIP 2014 - Paris, France

Poster presentation of the paper “Using sparse coding for landmark localization in facial expressions” during the 5th European Workshop on Visual Information Processing. In this article we address the issue of adopting a local sparse coding representation (Histogram of Sparse Codes), in a part-based framework for inferring the locations of facial landmarks. The rationale behind this approach is that unsupervised learning of sparse code dictionaries from face data can be an effective approach to cope with such a challenging problem. (poster)