by Bhatt, Mehul and Suchan, Jakob
Abstract:
Semantic interpretation of dynamic visuospatial imagery calls for a general and systematic integration of methods in knowl- edge representation and computer vision. Towards this, we highlight research articulating & developing�deep semantics, characterised by the existence of declarative models ?e.g., pertaining�space and mo- tion? and corresponding formalisation and reasoning methods sup- porting capabilities such as semantic question-answering, relational visuospatial learning, and (non-monotonic) visuospatial explanation. We position a working model for deep semantics by highlighting se- lect recent / closely related works from IJCAI [8,�4], AAAI [10], ILP [7], and ACS [9]. We posit that human-centred, explainable visual sensemaking necessitates both high-level semantics and low-level vi- sual computing, with the highlighted works providing a model for systematic, modular integration of diverse multifaceted techniques developed in AI, ML, and Computer Vision.
Reference:
Cognitive Vision and Perception: Deep Semantics Integrating AI and Vision for Reasoning about Space, Motion, and Interaction (Bhatt, Mehul and Suchan, Jakob), In ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020), IOS Press, volume 325, 2020.
Bibtex Entry:
@inproceedings{BhattECAI20,
author = {Bhatt, Mehul and Suchan, Jakob},
booktitle = {ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020 - Including 10th Conference on Prestigious Applications of Artificial Intelligence (PAIS 2020)},
pages = {2881--2882},
publisher = {IOS Press},
title = {{Cognitive Vision and Perception: Deep Semantics Integrating AI and Vision for Reasoning about Space, Motion, and Interaction}},
series = {Frontiers in Artificial Intelligence and Applications},
volume = {325},
DOI = {10.3233/FAIA200434},
keywords = {Computational cognitive vision; Vision and AI; Visual Perception; Spatial Cognition and Artificial Intelligence},
abstract = {Semantic interpretation of dynamic visuospatial imagery calls for a general and systematic integration of methods in knowl- edge representation and computer vision. Towards this, we highlight research articulating & developing�deep semantics, characterised by the existence of declarative models ?e.g., pertaining�space and mo- tion? and corresponding formalisation and reasoning methods sup- porting capabilities such as semantic question-answering, relational visuospatial learning, and (non-monotonic) visuospatial explanation. We position a working model for deep semantics by highlighting se- lect recent / closely related works from IJCAI [8,�4], AAAI [10], ILP [7], and ACS [9]. We posit that human-centred, explainable visual sensemaking necessitates both high-level semantics and low-level vi- sual computing, with the highlighted works providing a model for systematic, modular integration of diverse multifaceted techniques developed in AI, ML, and Computer Vision. },
url = {pdfs/cognitive_vision/ECAI2020-cognitive_vision.pdf},
year = {2020}
}