Matches in SemOpenAlex for { <https://semopenalex.org/work/W1594821797> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W1594821797 abstract "We present a method for unsupervised learning of event classes from videos in which multiple activities may occur simultaneously. Unsupervised discovery of event classesavoids the need to hand-crafted event classes and thereby makes it possible in principle to scale-up to the huge number of event classes that occur in the real world. Research into an unsupervised approach has important consequences for tasks such as video understandingand summarization, modelling usual and unusual behaviour and video indexing for retrieval. These tasks are becoming increasingly important for scenarios such as surveillance,video search, robotic vision and sports highlights extraction as a consequence of the increasing proliferation of videos.The proposed approach is underpinned by a generative probabilistic model for events and a graphical representation for the qualitative spatial relationships between objects and their temporal evolution. Given a set of tracks for the objects within a scene, a set of event classes is derived from the most likely decomposition of the ‘activity graph’ of spatio-temporal relationships between all pairs of objects into a set of labelled eventsinvolving subsets of these objects.The posterior probability of candidate solutions favours decompositions in which events of the same class have a similar relational structure, together with three other measures of well-formedness. A Markov Chain Monte Carlo (MCMC) procedure is used to efficiently search for the MAP solution. This search moves between possible decompositionsof the activity graph into sets of unlabelled events and at each move adds a close to optimal labellings (for this decomposition) using spectral clustering.Experiments on simulated and real data show that the discovered event classes are often semantically meaningful and correspond well with ground-truth event classes assignedby hand.Event Learning is followed by learning of functional object categories. Equivalence classes of objects are discovered on the basis of their similar functional role in multipleevent instantiations. Objects are represented in a multidimensional space that captures their functional role in all the events. Unsupervised learning in this space results in functional object-categories.Experiments in the domain of aircraft handling suggests that our spatio-temporal representation together with the learning techniques are a promising framework for learningfunctional object-categories from video." @default.
- W1594821797 created "2016-06-24" @default.
- W1594821797 creator A5074371620 @default.
- W1594821797 date "2010-12-01" @default.
- W1594821797 modified "2023-09-23" @default.
- W1594821797 title "Unsupervised learning of event and object classes from video" @default.
- W1594821797 hasPublicationYear "2010" @default.
- W1594821797 type Work @default.
- W1594821797 sameAs 1594821797 @default.
- W1594821797 citedByCount "3" @default.
- W1594821797 countsByYear W15948217972015 @default.
- W1594821797 crossrefType "dissertation" @default.
- W1594821797 hasAuthorship W1594821797A5074371620 @default.
- W1594821797 hasConcept C119857082 @default.
- W1594821797 hasConcept C121332964 @default.
- W1594821797 hasConcept C132525143 @default.
- W1594821797 hasConcept C153180895 @default.
- W1594821797 hasConcept C154945302 @default.
- W1594821797 hasConcept C167966045 @default.
- W1594821797 hasConcept C170858558 @default.
- W1594821797 hasConcept C177264268 @default.
- W1594821797 hasConcept C199360897 @default.
- W1594821797 hasConcept C23224414 @default.
- W1594821797 hasConcept C2777212361 @default.
- W1594821797 hasConcept C2779662365 @default.
- W1594821797 hasConcept C39890363 @default.
- W1594821797 hasConcept C41008148 @default.
- W1594821797 hasConcept C49937458 @default.
- W1594821797 hasConcept C62520636 @default.
- W1594821797 hasConcept C75165309 @default.
- W1594821797 hasConcept C8038995 @default.
- W1594821797 hasConcept C80444323 @default.
- W1594821797 hasConceptScore W1594821797C119857082 @default.
- W1594821797 hasConceptScore W1594821797C121332964 @default.
- W1594821797 hasConceptScore W1594821797C132525143 @default.
- W1594821797 hasConceptScore W1594821797C153180895 @default.
- W1594821797 hasConceptScore W1594821797C154945302 @default.
- W1594821797 hasConceptScore W1594821797C167966045 @default.
- W1594821797 hasConceptScore W1594821797C170858558 @default.
- W1594821797 hasConceptScore W1594821797C177264268 @default.
- W1594821797 hasConceptScore W1594821797C199360897 @default.
- W1594821797 hasConceptScore W1594821797C23224414 @default.
- W1594821797 hasConceptScore W1594821797C2777212361 @default.
- W1594821797 hasConceptScore W1594821797C2779662365 @default.
- W1594821797 hasConceptScore W1594821797C39890363 @default.
- W1594821797 hasConceptScore W1594821797C41008148 @default.
- W1594821797 hasConceptScore W1594821797C49937458 @default.
- W1594821797 hasConceptScore W1594821797C62520636 @default.
- W1594821797 hasConceptScore W1594821797C75165309 @default.
- W1594821797 hasConceptScore W1594821797C8038995 @default.
- W1594821797 hasConceptScore W1594821797C80444323 @default.
- W1594821797 hasLocation W15948217971 @default.
- W1594821797 hasOpenAccess W1594821797 @default.
- W1594821797 hasPrimaryLocation W15948217971 @default.
- W1594821797 hasRelatedWork W103521858 @default.
- W1594821797 hasRelatedWork W125749174 @default.
- W1594821797 hasRelatedWork W1544277926 @default.
- W1594821797 hasRelatedWork W1915501369 @default.
- W1594821797 hasRelatedWork W1969652666 @default.
- W1594821797 hasRelatedWork W1998312196 @default.
- W1594821797 hasRelatedWork W2119246739 @default.
- W1594821797 hasRelatedWork W2128358762 @default.
- W1594821797 hasRelatedWork W2153944708 @default.
- W1594821797 hasRelatedWork W2313667075 @default.
- W1594821797 hasRelatedWork W2558496198 @default.
- W1594821797 hasRelatedWork W2584471052 @default.
- W1594821797 hasRelatedWork W2755922031 @default.
- W1594821797 hasRelatedWork W2900279641 @default.
- W1594821797 hasRelatedWork W2951478746 @default.
- W1594821797 hasRelatedWork W2966998144 @default.
- W1594821797 hasRelatedWork W3000279895 @default.
- W1594821797 hasRelatedWork W3192607066 @default.
- W1594821797 hasRelatedWork W65642710 @default.
- W1594821797 hasRelatedWork W85699701 @default.
- W1594821797 isParatext "false" @default.
- W1594821797 isRetracted "false" @default.
- W1594821797 magId "1594821797" @default.
- W1594821797 workType "dissertation" @default.