Tutorial : COGNITIVE VISION - Integrated Vision and AI for Embodied Perception and
Interaction
Abstract : The tutorial on "Cognitive Vision" addresses computational vision and perception at
the interface of language, logic, cognition, and artificial intelligence. The
principal emphasis of the tutorial is on the integration of vision and artificial
intelligence from the viewpoint of embodied (visual, visuo-spatial, visuo-
locomotive) perception, interaction, and autonomous control. Particular themes
addressed by the tutorial include:
- declarative representation and reasoning about spatio-temporal dynamics
- deep semantics and explainable visual computing (e.g., about space and motion)
- vision and computational models of narrative
- cognitive vision and multimodality (e.g., multimodal semantic interpretation)
- visual perception (e.g., high-level event perception, eye-tracking)
- methodological integrations between vision and AI
In addition to basic research questions, the tutorial addresses diverse application
areas where, for instance, the processing and semantic interpretation of
(potentially large volumes of) highly dynamic visuo-spatial imagery is central:
autonomous systems, cognitive robotics, self- driving vehicles, visuo-auditory
media design, and psychology & behavioural research domains where data-centred
analytical methods are gaining momentum. The tutorial will position an emerging
line of research that brings together a novel & unique combination of research
methodologies, academics and communities (e.g., AI, ML, Vision, Cognitive
Linguistics, Psychology, Visual Perception, Spatial Cognition).
Bio: Mehul Bhatt is Professor within the School of Science and Technology at
Örebro University (Sweden), where he is member of the Applied Autonomous Sensor
Systems (AASS) research environment; he is also consulting guest professor at the
Interaction Lab at the University of Skövde (Sweden). Mehul Bhatt directs CoDesign
Lab EU, an initiative aimed at addressing the confluence of Cognition, Artificial
Intelligence, Interaction, and Design Science for the development of human-centred
cognitive assistive technologies and interaction systems. He is director of the
research and consulting group DesignSpace, and pursues ongoing research in
Cognitive Vision and Spatial Representation and Reasoning. His research focuses on
visuospatial cognition and computation at the interface of AI, Cognitive Science,
HCI, and Design Science. His group develops human-centred technologies and
artefacts for application in contexts where human-centred engineering is crucial,
e.g., autonomous systems, architecture and built environment design, communications
and media design. Mehul?s research particularly emphasises the study of human-
behaviour (embodied multimodal interaction) in naturalistic settings as a principal
means of technology driven human-centred cognitive assistance in planning,
decision-making, and design situations that require an interplay of commonsense,
creative and specialist visuospatial thinking. Previously, Mehul Bhatt was
Professor within the Faculty of Mathematics and Informatics at the University of
Bremen (Germany) and Stiftungs Professor at the German Research Center for
Artificial Intelligence (DFKI Bremen).