Search Results for author: Mehul Bhatt

Found 22 papers, 0 papers with code

Multi3Generation: Multitask, Multilingual, Multimodal Language Generation

no code implementations EAMT 2022 Anabela Barreiro, José GC de Souza, Albert Gatt, Mehul Bhatt, Elena Lloret, Aykut Erdem, Dimitra Gkatzia, Helena Moniz, Irene Russo, Fabio Kepler, Iacer Calixto, Marcin Paprzycki, François Portet, Isabelle Augenstein, Mirela Alhasani

This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generation (CA18231), an interdisciplinary network of research groups working on different aspects of language generation.

Text Generation

Commonsense Visual Sensemaking for Autonomous Driving: On Generalised Neurosymbolic Online Abduction Integrating Vision and Semantics

no code implementations28 Dec 2020 Jakob Suchan, Mehul Bhatt, Srikrishna Varadarajan

The method integrates state of the art in visual computing, and is developed as a modular framework that is generally usable within hybrid architectures for realtime perception and control.

Autonomous Driving Question Answering

Towards a Human-Centred Cognitive Model of Visuospatial Complexity in Everyday Driving

no code implementations29 May 2020 Vasiliki Kondyli, Mehul Bhatt, Jakob Suchan

We develop a human-centred, cognitive model of visuospatial complexity in everyday, naturalistic driving conditions.

Benchmarking

Out of Sight But Not Out of Mind: An Answer Set Programming Based Online Abduction Framework for Visual Sensemaking in Autonomous Driving

no code implementations31 May 2019 Jakob Suchan, Mehul Bhatt, Srikrishna Varadarajan

We demonstrate the need and potential of systematically integrated vision and semantics} solutions for visual sensemaking (in the backdrop of autonomous driving).

Autonomous Driving Question Answering

Semantic Analysis of (Reflectional) Visual Symmetry: A Human-Centred Computational Model for Declarative Explainability

no code implementations31 May 2018 Jakob Suchan, Mehul Bhatt, Srikrishna Vardarajan, Seyed Ali Amirshahi, Stella Yu

Key features include a human-centred representation, and a declarative, explainable interpretation model supporting deep semantic question-answering founded on an integration of methods in knowledge representation and deep learning based computer vision.

Question Answering

Answer Set Programming Modulo `Space-Time'

no code implementations17 May 2018 Carl Schultz, Mehul Bhatt, Jakob Suchan, Przemysław Wałęga

We present ASP Modulo `Space-Time', a declarative representational and computational framework to perform commonsense reasoning about regions with both spatial and temporal components.

Visual Explanation by High-Level Abduction: On Answer-Set Programming Driven Reasoning about Moving Objects

no code implementations3 Dec 2017 Jakob Suchan, Mehul Bhatt, Przemysław Wałęga, Carl Schultz

We present the formal framework, its general implementation as a (declarative) method in answer set programming, and an example application and evaluation based on two diverse video datasets: the MOTChallenge benchmark developed by the vision community, and a recently developed Movie Dataset.

Object Tracking

Deep Semantic Abstractions of Everyday Human Activities: On Commonsense Representations of Human Interactions

no code implementations10 Oct 2017 Jakob Suchan, Mehul Bhatt

We propose a deep semantic characterization of space and motion categorically from the viewpoint of grounding embodied human-object interactions.

Human-Object Interaction Detection Object +1

Commonsense Scene Semantics for Cognitive Robotics: Towards Grounding Embodied Visuo-Locomotive Interactions

no code implementations15 Sep 2017 Jakob Suchan, Mehul Bhatt

We present a commonsense, qualitative model for the semantic grounding of embodied visuo-spatial and locomotive interactions.

Deeply Semantic Inductive Spatio-Temporal Learning

no code implementations9 Aug 2016 Jakob Suchan, Mehul Bhatt, Carl Schultz

We present an inductive spatio-temporal learning framework rooted in inductive logic programming.

Inductive logic programming

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction

no code implementations26 Jul 2016 Michael Spranger, Jakob Suchan, Mehul Bhatt, Manfred Eppe

This paper presents a computational model of the processing of dynamic spatial relations occurring in an embodied robotic interaction setup.

Robust Natural Language Processing - Combining Reasoning, Cognitive Semantics and Construction Grammar for Spatial Language

no code implementations20 Jul 2016 Michael Spranger, Jakob Suchan, Mehul Bhatt

We present a system for generating and understanding of dynamic and static spatial relations in robotic interaction setups.

Non-Monotonic Spatial Reasoning with Answer Set Programming Modulo Theories

no code implementations25 Jun 2016 Przemysław Andrzej Wałęga, Carl Schultz, Mehul Bhatt

We present ASPMT(QS), a novel approach and fully-implemented prototype for non-monotonic spatial reasoning -a crucial requirement within dynamic spatial systems- based on Answer Set Programming Modulo Theories (ASPMT).

Talking about the Moving Image: A Declarative Model for Image Schema Based Embodied Perception Grounding and Language Generation

no code implementations13 Aug 2015 Jakob Suchan, Mehul Bhatt, Harshita Jhavar

We present a general theory and corresponding declarative model for the embodied grounding and natural language based analytical summarisation of dynamic visuo-spatial imagery.

Text Generation

Spatial Symmetry Driven Pruning Strategies for Efficient Declarative Spatial Reasoning

no code implementations16 Jun 2015 Carl Schultz, Mehul Bhatt

Declarative spatial reasoning denotes the ability to (declaratively) specify and solve real-world problems related to geometric and qualitative spatial representation and reasoning within standard knowledge representation and reasoning (KR) based methods (e. g., logic programming and derivatives).

ASPMT(QS): Non-Monotonic Spatial Reasoning with Answer Set Programming Modulo Theories

no code implementations16 Jun 2015 Przemysław Andrzej Wałęga, Mehul Bhatt, Carl Schultz

We present ASPMT(QS), a novel approach and fully-implemented prototype for non-monotonic spatial reasoning ---a crucial requirement within dynamic spatial systems-- based on Answer Set Programming Modulo Theories (ASPMT).

Geospatial Narratives and their Spatio-Temporal Dynamics: Commonsense Reasoning for High-level Analyses in Geographic Information Systems

no code implementations9 Jul 2013 Mehul Bhatt, Jan Oliver Wallgruen

The modelling, analysis, and visualisation of dynamic geospatial phenomena has been identified as a key developmental challenge for next-generation Geographic Information Systems (GIS).

Data Integration

Cognitive Interpretation of Everyday Activities: Toward Perceptual Narrative Based Visuo-Spatial Scene Interpretation

no code implementations22 Jun 2013 Mehul Bhatt, Jakob Suchan, Carl Schultz

We position a narrative-centred computational model for high-level knowledge representation and reasoning in the context of a range of assistive technologies concerned with "visuo-spatial perception and cognition" tasks.

Position Scene Understanding

ROTUNDE - A Smart Meeting Cinematography Initiative: Tools, Datasets, and Benchmarks for Cognitive Interpretation and Control

no code implementations5 Jun 2013 Mehul Bhatt, Jakob Suchan, Christian Freksa

ROTUNDE, an instance of smart meeting cinematography concept, aims to: (a) develop functionality-driven benchmarks with respect to the interpretation and control capabilities of human-cinematographers, real-time video editors, surveillance personnel, and typical human performance in everyday situations; (b) Develop general tools for the commonsense cognitive interpretation of dynamic scenes from the viewpoint of visuo-spatial cognition centred perceptual narrativisation.

Narrative based Postdictive Reasoning for Cognitive Robotics

no code implementations4 Jun 2013 Manfred Eppe, Mehul Bhatt

Making sense of incomplete and conflicting narrative knowledge in the presence of abnormalities, unobservable processes, and other real world considerations is a challenge and crucial requirement for cognitive robotics systems.

Anomaly Detection Translation

h-approximation: History-Based Approximation of Possible World Semantics as ASP

no code implementations17 Apr 2013 Manfred Eppe, Mehul Bhatt, Frank Dylla

We propose an approximation of the Possible Worlds Semantics (PWS) for action planning.

Cannot find the paper you are looking for? You can Submit a new open access paper.