Interleaved Inductive-Abductive Reasoning for Learning Complex Event Models

Dubba, Krishna; Bhatt, Mehul; Dylla, Frank; Hogg, David C.; Cohn, Anthony G.

doi:10.1007/978-3-642-31951-8_14

Cited by 13 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the spatial reasoning system used in this paper has much more capabilities then employed for the purpose of this paper. The system can be used for abductive reasoning and explain missing or faulty observations [9]. In case of the robot scenario presented in this paper, this can be used to generate or interpret descriptions where only partial information are available.…”

Section: Discussion and Future Workmentioning

confidence: 99%

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction

Spranger

Suchan

Bhatt

et al. 2014

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents a computational model of the processing of dynamic spatial relations occurring in an embodied robotic interaction setup. A complete system is introduced that allows autonomous robots to produce and interpret dynamic spatial phrases (in English) given an environment of moving objects. The model unites two separate research strands: computational cognitive semantics and on commonsense spatial representation and reasoning. The model for the first time demonstrates an integration of these different strands.

show abstract

Section: Discussion and Future Workmentioning

confidence: 99%

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction

Spranger

Suchan

Bhatt

et al. 2014

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…As the number of rules for a concept increases, this may result in many false positives when the rules are used for classification/recognition in test examples. In order to avoid learning from corrupt examples, the framework identifies examples as being corrupted by explaining them through abduction using the already induced model and the background theory (Dubba et al, 2012).…”

Section: Iia Algorithmmentioning

confidence: 99%

Learning Relational Event Models from Video

Dubba

Cohn

Hogg

et al. 2015

jair

Self Cite

View full text Add to dashboard Cite

Event models obtained automatically from video can be used in applications ranging from abnormal event detection to content based video retrieval. When multiple agents are involved in the events, characterizing events naturally suggests encoding interactions as relations. Learning event models from this kind of relational spatio-temporal data using relational learning techniques such as Inductive Logic Programming (ILP) hold promise, but have not been successfully applied to very large datasets which result from video data. In this paper, we present a novel framework remind (Relational Event Model INDuction) for supervised relational learning of event models from large video datasets using ILP. Efficiency is achieved through the learning from interpretations setting and using a typing system that exploits the type hierarchy of objects in a domain. The use of types also helps prevent over generalization. Furthermore, we also present a type-refining operator and prove that it is optimal. The learned models can be used for recognizing events from previously unseen videos. We also present an extension to the framework by integrating an abduction step that improves the learning performance when there is noise in the input data. The experimental results on several hours of video data from two challenging real world domains (an airport domain and a physical action verbs domain) suggest that the techniques are suitable to real world scenarios.

show abstract

“…This translates to the need to explicitly represent and reason about dynamic spatial configurations or scenes and, for real world problems, integrated reasoning about perceptual narratives of space, actions, and change [Bhatt, 2012]. With these modelling primitives, the ability to perform predictive and explanatory analyses on the basis of sensory data is crucial for creating a useful intelligent function within such environments [Dubba et al, 2011].…”

Section: Perceptual Narrative Generation For Activity Interpretationmentioning

confidence: 99%

“…The interpretation of narrative knowledge in this paper is based on these characterisations, especially in regard to the commonsense representation and reasoning tasks that accrue whilst modelling and reasoning about the perceptually grounded, narrativised epistemic state of an autonomous agent pertaining to space, actions, events, and change [Bhatt, 2012]. In particular, this encompasses a range of inference patterns such as: (a) spatiotemporal abduction for scenario and narrative completion [Bhatt and Flanagan, 2010]; (b) integrated inductive-abductive reasoning with narrative knowledge [Dubba et al, 2011]; (c) narrative-based postdiction for abnormality detection and planning [Eppe and Bhatt, 2013]. Perceptual Narratives.…”

Section: Introduction: Cognitive Interpretation By Narrativisationmentioning

confidence: 99%

“…The long-term vision is to benchmark with respect to the capabilities of human-cinematographers, real-time video editors, surveillance personnel to record and semantically annotate individual and group activity (e.g., for summarisation, story-book format digital media and promo generation). ] interpretation, robotic plan generation, semantic model generation from video, ambient intelligence and smart environments (e.g., see narrative based models in [Hajishirzi et al, 2012, Hajishirzi and Mueller, 2011, Mueller, 2007, Bhatt and Flanagan, 2010, Dubba et al, 2011, Eppe and Bhatt, 2013).…”

Section: Introduction: Cognitive Interpretation By Narrativisationmentioning

confidence: 99%

See 1 more Smart Citation

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

Bhatt¹,

Suchan²,

Schultz³

2013

Preprint

Self Cite

View full text Add to dashboard Cite

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. Our proposed narrative model encompasses aspects such as space, events, actions, change, and interaction from the viewpoint of commonsense reasoning and learning in large-scale cognitive systems. The broad focus of this paper is on the domain of human-activity interpretation in smart environments, ambient intelligence etc. In the backdrop of a smart meeting cinematography domain, we position the proposed narrative model, preliminary work on perceptual narrativisation, and the immediate outlook on constructing general-purpose open-source tools for perceptual narrativisation.

show abstract

Interleaved Inductive-Abductive Reasoning for Learning Complex Event Models

Cited by 13 publications

References 16 publications

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction

Grounding Dynamic Spatial Relations for Embodied (Robot) Interaction

Learning Relational Event Models from Video

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

Contact Info

Product

Resources

About