Matches in SemOpenAlex for { <https://semopenalex.org/work/W1514447604> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W1514447604 abstract "Automatic recognition of events in video is an immensly challenging problem. If solved, the number of potential domains in which such a system could be deployed isvast and growing; including traffic monitoring, surveillance, security, elderly care and semantic video search to name but a few. Much prior research in the area has focused on producing a solution that is tailored towards one of these applications, applying methodswhich are most appropriate given the constraints of the target domain. For the moment, this remains to some extent the only practical way to approach the problem. The aim inthis thesis is to build a high-level framework for event recognition which is in the main generic and widely transferrable, yet allows domain-appropriate elements to be incorporated.A detector is constructed for low-level events which is based on dense extraction of Histograms of Optical Flow. This descriptor has only recently been adopted by the eventdetection community, and as such there are aspects of the features which have not been optimized. This thesis performs extensive experimentation on normalization scheme and finds that the strategy most widely in use is suboptimal compared to one of the alternatives proposed. The detector is then trained on a challenging real world domain to run in a sliding window fashion on continuous video input.A high level model which exploits temporal relations between different event types is constructed. The model is designed with transferrability and computational tractability in mind. Several methods are benchmarked for learning the distributions over time differences between pairs of events. Three different connection strategies are proposed and evaluated for creating a tree structured prior that permits fast, exact inference. An efficient iterative optimization scheme is presented for handling scenarios which contain unknown numbers of event instances. Finally, the model is extended in a Conditional Random Field framework that allows weights to be learned to balance the response from independent detectors with the pairwise temporal relationships." @default.
- W1514447604 created "2016-06-24" @default.
- W1514447604 creator A5007091975 @default.
- W1514447604 date "2012-06-01" @default.
- W1514447604 modified "2023-09-27" @default.
- W1514447604 title "High-level activity learning and recognition in structured environments" @default.
- W1514447604 hasPublicationYear "2012" @default.
- W1514447604 type Work @default.
- W1514447604 sameAs 1514447604 @default.
- W1514447604 citedByCount "0" @default.
- W1514447604 crossrefType "dissertation" @default.
- W1514447604 hasAuthorship W1514447604A5007091975 @default.
- W1514447604 hasConcept C102392041 @default.
- W1514447604 hasConcept C111919701 @default.
- W1514447604 hasConcept C119857082 @default.
- W1514447604 hasConcept C121332964 @default.
- W1514447604 hasConcept C124101348 @default.
- W1514447604 hasConcept C134306372 @default.
- W1514447604 hasConcept C136886441 @default.
- W1514447604 hasConcept C144024400 @default.
- W1514447604 hasConcept C154945302 @default.
- W1514447604 hasConcept C165696696 @default.
- W1514447604 hasConcept C19165224 @default.
- W1514447604 hasConcept C2778751112 @default.
- W1514447604 hasConcept C2779662365 @default.
- W1514447604 hasConcept C33923547 @default.
- W1514447604 hasConcept C36503486 @default.
- W1514447604 hasConcept C38652104 @default.
- W1514447604 hasConcept C41008148 @default.
- W1514447604 hasConcept C62520636 @default.
- W1514447604 hasConcept C76155785 @default.
- W1514447604 hasConcept C94915269 @default.
- W1514447604 hasConceptScore W1514447604C102392041 @default.
- W1514447604 hasConceptScore W1514447604C111919701 @default.
- W1514447604 hasConceptScore W1514447604C119857082 @default.
- W1514447604 hasConceptScore W1514447604C121332964 @default.
- W1514447604 hasConceptScore W1514447604C124101348 @default.
- W1514447604 hasConceptScore W1514447604C134306372 @default.
- W1514447604 hasConceptScore W1514447604C136886441 @default.
- W1514447604 hasConceptScore W1514447604C144024400 @default.
- W1514447604 hasConceptScore W1514447604C154945302 @default.
- W1514447604 hasConceptScore W1514447604C165696696 @default.
- W1514447604 hasConceptScore W1514447604C19165224 @default.
- W1514447604 hasConceptScore W1514447604C2778751112 @default.
- W1514447604 hasConceptScore W1514447604C2779662365 @default.
- W1514447604 hasConceptScore W1514447604C33923547 @default.
- W1514447604 hasConceptScore W1514447604C36503486 @default.
- W1514447604 hasConceptScore W1514447604C38652104 @default.
- W1514447604 hasConceptScore W1514447604C41008148 @default.
- W1514447604 hasConceptScore W1514447604C62520636 @default.
- W1514447604 hasConceptScore W1514447604C76155785 @default.
- W1514447604 hasConceptScore W1514447604C94915269 @default.
- W1514447604 hasLocation W15144476041 @default.
- W1514447604 hasOpenAccess W1514447604 @default.
- W1514447604 hasPrimaryLocation W15144476041 @default.
- W1514447604 hasRelatedWork W1002460645 @default.
- W1514447604 hasRelatedWork W1567589860 @default.
- W1514447604 hasRelatedWork W2008989859 @default.
- W1514447604 hasRelatedWork W2107021927 @default.
- W1514447604 hasRelatedWork W2108599331 @default.
- W1514447604 hasRelatedWork W2469401779 @default.
- W1514447604 hasRelatedWork W2604476911 @default.
- W1514447604 hasRelatedWork W2740218432 @default.
- W1514447604 hasRelatedWork W2935569394 @default.
- W1514447604 hasRelatedWork W2949876623 @default.
- W1514447604 hasRelatedWork W3005290865 @default.
- W1514447604 hasRelatedWork W3005469290 @default.
- W1514447604 hasRelatedWork W3092500685 @default.
- W1514447604 hasRelatedWork W3108639298 @default.
- W1514447604 hasRelatedWork W3134606731 @default.
- W1514447604 hasRelatedWork W3174998861 @default.
- W1514447604 hasRelatedWork W3178212073 @default.
- W1514447604 hasRelatedWork W3206354642 @default.
- W1514447604 hasRelatedWork W3213100082 @default.
- W1514447604 hasRelatedWork W823458229 @default.
- W1514447604 isParatext "false" @default.
- W1514447604 isRetracted "false" @default.
- W1514447604 magId "1514447604" @default.
- W1514447604 workType "dissertation" @default.