Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805555398> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2805555398 abstract "Identifying suspects in surveillance footage is paramount in ensuring public safety, preventing crime, policing and forensic investigation. At present, finding an individual in real-world CCTV footage given only an eye-witness description is near impossible. The vast majority of contemporary research assumes coarse, expertly-defined categories to describe subjects, ineffective in dealing with unconstrained, low quality and obscured images. Such brittle representations hamper semantic image discrimination and the ability to learn robust predictors from challenging subject matter. This thesis explores human and machine centric techniques for representing and learning semantic human descriptions for suspect identification. By investigating the duality of human-machine communication, we enhance the capabilities of traditional attributes and soft biometric descriptors, expanding their versatility and applicability towards challenging images and large-scale surveillance datasets. We experiment with crowdsourcing human annotations using ordered and similarity comparisons, and estimating attributes from images employing a variety of state-of-the-art machine learning techniques. Our focus is on utilising a lean lexicon of global and body characteristics that are most pertinent when estimated from stand-alone surveillance footage. Significant improvements in suspect retrieval and identification performance are achieved by discovering enhanced soft biometric descriptions which represent visual trait characteristics with more precision and relevance. This work evolves the areas of soft biometrics and identity science, drawing ideas from contemporary image attribute recognition, semantic attribute discovery, pedestrian reidentification and perceptual psychology. Our findings indicate that increasing not only the volume, but the complexity of information conveyed between humans and machines is key in deploying soft biometrics ubiquitously." @default.
- W2805555398 created "2018-06-13" @default.
- W2805555398 creator A5049901038 @default.
- W2805555398 date "2018-03-01" @default.
- W2805555398 modified "2023-09-27" @default.
- W2805555398 title "Discovering human descriptions for ubiquitous visual identification" @default.
- W2805555398 hasPublicationYear "2018" @default.
- W2805555398 type Work @default.
- W2805555398 sameAs 2805555398 @default.
- W2805555398 citedByCount "0" @default.
- W2805555398 crossrefType "dissertation" @default.
- W2805555398 hasAuthorship W2805555398A5049901038 @default.
- W2805555398 hasConcept C107457646 @default.
- W2805555398 hasConcept C116834253 @default.
- W2805555398 hasConcept C119857082 @default.
- W2805555398 hasConcept C136197465 @default.
- W2805555398 hasConcept C136764020 @default.
- W2805555398 hasConcept C154945302 @default.
- W2805555398 hasConcept C15744967 @default.
- W2805555398 hasConcept C158154518 @default.
- W2805555398 hasConcept C17744445 @default.
- W2805555398 hasConcept C184297639 @default.
- W2805555398 hasConcept C199539241 @default.
- W2805555398 hasConcept C204321447 @default.
- W2805555398 hasConcept C2522767166 @default.
- W2805555398 hasConcept C2778223634 @default.
- W2805555398 hasConcept C41008148 @default.
- W2805555398 hasConcept C59822182 @default.
- W2805555398 hasConcept C62230096 @default.
- W2805555398 hasConcept C73484699 @default.
- W2805555398 hasConcept C86803240 @default.
- W2805555398 hasConceptScore W2805555398C107457646 @default.
- W2805555398 hasConceptScore W2805555398C116834253 @default.
- W2805555398 hasConceptScore W2805555398C119857082 @default.
- W2805555398 hasConceptScore W2805555398C136197465 @default.
- W2805555398 hasConceptScore W2805555398C136764020 @default.
- W2805555398 hasConceptScore W2805555398C154945302 @default.
- W2805555398 hasConceptScore W2805555398C15744967 @default.
- W2805555398 hasConceptScore W2805555398C158154518 @default.
- W2805555398 hasConceptScore W2805555398C17744445 @default.
- W2805555398 hasConceptScore W2805555398C184297639 @default.
- W2805555398 hasConceptScore W2805555398C199539241 @default.
- W2805555398 hasConceptScore W2805555398C204321447 @default.
- W2805555398 hasConceptScore W2805555398C2522767166 @default.
- W2805555398 hasConceptScore W2805555398C2778223634 @default.
- W2805555398 hasConceptScore W2805555398C41008148 @default.
- W2805555398 hasConceptScore W2805555398C59822182 @default.
- W2805555398 hasConceptScore W2805555398C62230096 @default.
- W2805555398 hasConceptScore W2805555398C73484699 @default.
- W2805555398 hasConceptScore W2805555398C86803240 @default.
- W2805555398 hasLocation W28055553981 @default.
- W2805555398 hasOpenAccess W2805555398 @default.
- W2805555398 hasPrimaryLocation W28055553981 @default.
- W2805555398 hasRelatedWork W115699299 @default.
- W2805555398 hasRelatedWork W2067816745 @default.
- W2805555398 hasRelatedWork W2584760857 @default.
- W2805555398 hasRelatedWork W2609077090 @default.
- W2805555398 hasRelatedWork W2895516219 @default.
- W2805555398 hasRelatedWork W2902450824 @default.
- W2805555398 hasRelatedWork W2963656477 @default.
- W2805555398 hasRelatedWork W2968570587 @default.
- W2805555398 hasRelatedWork W3002798153 @default.
- W2805555398 hasRelatedWork W3021152764 @default.
- W2805555398 hasRelatedWork W3025915648 @default.
- W2805555398 hasRelatedWork W3035227524 @default.
- W2805555398 hasRelatedWork W3044114958 @default.
- W2805555398 hasRelatedWork W3045097470 @default.
- W2805555398 hasRelatedWork W3046037264 @default.
- W2805555398 hasRelatedWork W3083805107 @default.
- W2805555398 hasRelatedWork W3093082837 @default.
- W2805555398 hasRelatedWork W3121972911 @default.
- W2805555398 hasRelatedWork W3126988965 @default.
- W2805555398 hasRelatedWork W3160710820 @default.
- W2805555398 isParatext "false" @default.
- W2805555398 isRetracted "false" @default.
- W2805555398 magId "2805555398" @default.
- W2805555398 workType "dissertation" @default.