We have witnessed impressive advances in computer vision based recognition and analysis of non-verbal behavioural cues such as gestures, posture, actions, joint attention and facial expressions. However, these cues are rarely analysed holistically and contextually to achieve a deeper understanding of social human behaviour.
The importance of socializing and its impact on decisions, thoughts, and the general wellbeing of individuals are widely recognized. Lack of social interactions is strongly correlated with depression, poor outcomes in stroke survivors, and dementia, for example. There has been increased interest in recent years in developing computer vision-based assistive technologies to monitor the social interactions of people affected by several disorders, and to improve the social interactions of visually impaired people and autistic children by relying on feedback provided by visual data. Development of systems that capture the complexities of human life, anticipate our intentions and adapt to accommodate our needs motivates us to build machines that better interpret our interactions and are capable of interacting with us at a social level.
This opens a new frontier for Social Behaviour Understanding, where major questions are how to capture the diversity and complexity of social life from image data and which image analysis and pattern recognition technologies are effective in this domain. We are organizing a workshop that aims at gathering research progress around those problems that require, in addition to performing an effective visual analysis of basic behavioral cues, to integrate and interpret them jointly.
|Session 1 (14:00 - 15:45)|
|14:00-14:05||Arrival and Welcome|
|14:05-14:50||Invited Talk 1: Physical Analytics with Body Cameras||Andrea Cavallaro (Queen Mary University of London, UK)|
|14:50-15:10||Tactile Logging for Understanding Plausible Tool Use Based on Human Demonstration||Shuichi Akizuki, Yoshimitsu Aoki|
|15:10-15:30||Unsupervised Speaker Cue Usage Detection in Public Speaking Videos||Anshul Gupta, Dinesh Babu Jayagopi|
|15:30-15:45||AHA-3D: A Labelled Dataset for Senior Fitness Exercise Recognition and Segmentation from 3D Skeletal Data||Joao Antunes, Alexandre Bernardino, Asim Smailagic, Daniel Siewiorek|
|Session 2 (16:00 - 18:00)|
|16:00-16:45||Invited Talk 2: Recognizing Human Emotions||Stefano Berretti (University of Florence, Italy)|
|16:45-17:05||Online Multiple Views Tracking: Targets Association Across Cameras||Quoc Cuong LE, Donatello Conte, Moncef Hidane|
|17:05-17:50||Invited Talk 3: Estimating Affect in-the-wild||Stefanos Zafeiriou (Imperial College London, UK)|
Stefano Berretti is an Associate Professor at the Media Integration and Communication Center (MICC) and at the Department of Information Engineering (DINFO) of the University of Florence (UNIFI), Florence, Italy, since 2002. In April 2017, he got the habilitation as full Professor in Computer Engineering from the Italian Ministery of Education, University and Research (MIUR). His research interests are in the areas of Computer Vision, Pattern Recognition and Multimedia, in particular, he worked on Image Retrieval, 3D Objects Retrieval and Partitioning, Face Biometrics, Facial Expression and Emotion Recognition, Human Action Recognition, 3D Surface Descriptors and Deep Learning for Face Recognition.
Andrea Cavallaro is Professor of Multimedia Signal Processing and Director of the Centre for Intelligent Sensing at Queen Mary University of London, UK. He received his Ph.D. in Electrical Engineering from the Swiss Federal Institute of Technology (EPFL), Lausanne, in 2002. He was a Research Fellow with British Telecommunications (BT) in 2004/2005 and was awarded the Royal Academy of Engineering teaching Prize in 2007. Prof. Cavallaro is Area Editor for the IEEE Signal Processing Magazine and Associate Editor for the IEEE Transactions on Image Processing. He is an elected member of the IEEE Signal Processing Society, Image, Video, and Multidimensional Signal Processing Technical Committee, and chair of its Awards committee. His research interests include Multi-camera Networks, Target Detection and Tracking, Multimodal Information Fusion, Behaviour and Identity Recognition, Robotic Perception, Underwater Imaging and Privacy.
Stefanos P. Zafeiriou (M’09) is currently a Reader in Machine Learning and Computer Vision with the Department of Computing, Imperial College London, London, U.K, and a Distinguishing Research Fellow with University of Oulu under Finish Distinguishing Professor Programme. He was a recipient of the Prestigious Junior Research Fellowships from Imperial College London in 2011 to start his own independent research group. He was the recipient of the President’s Medal for Excellence in Research Supervision for 2016. He has received various awards during his doctoral and post-doctoral studies. His research interests include Statistical Machine Learning/Pattern Recognition, Linear/Multilinear decompositions, Convex Optimization, Detection and Estimation Theory, Object Alignment and Tracking, Facial Biometrics, Facial Expression Recognition, Human Behavioral Analysis, Behavioral Biometrics.
Stephen J. McKenna
Chair of Computer Vision and Head of Research (Computing)
Computer Vision and Image Processing (CVIP) group
University of Dundee, Dundee, UK
Fernando De la Torre
Research Scientist Manager
Facebook AI Research, USA
Researcher at the University of Barcelona and Computer Vision Center
Research Associate (former Erasmus Mundus Fellow)
Surgical Robot Vision Group (WEISS)
University College London, UK