Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/484262
Full metadata record
DC FieldValueLanguage
dc.coverage.spatial
dc.date.accessioned2023-05-18T12:17:04Z-
dc.date.available2023-05-18T12:17:04Z-
dc.identifier.urihttp://hdl.handle.net/10603/484262-
dc.description.abstractThis thesis targets the problem of surrogate approximations for similarity measures to improve their newlineperformance in various applications. We have presented surrogate approximations for popular dynamic newlinetime warping (DTW) distance, canonical correlation analysis (CCA), Intersection-over-Union (IoU), newlinePCP, and PCKh measures. For DTW and CCA, our surrogate approximations are based on their corresponding definitions. We presented a surrogate approximation using neural networks for IoU, PCP, and newlinePCKh measures. newlineFirst, we propose a linear approximation for the naïve DTW distance. We try to speed up the DTW newlinedistance computation by learning the optimal alignment from the training data. We propose a surrogate kernel approximation over CCA in our next contribution. It enables us to use CCA in the kernel newlineframework, further improving its performance. In our final contribution, we propose a surrogate approximation technique using neural networks to learn a surrogate loss function over IoU, PCP, and newlinePCKh measures. For IoU loss, we validated our method over semantic segmentation models. For PCP, newlineand PCKh loss, we validated over human pose estimation models. newline
dc.format.extent
dc.languageEnglish
dc.relation
dc.rightsuniversity
dc.titleSurrogate Approximations for Similarity Measures
dc.title.alternative
dc.creator.researcherNagendar G
dc.subject.keywordComputer Science
dc.subject.keywordComputer Science Artificial Intelligence
dc.subject.keywordEngineering and Technology
dc.description.note
dc.contributor.guideC V Jawahar
dc.publisher.placeHyderabad
dc.publisher.universityInternational Institute of Information Technology, Hyderabad
dc.publisher.institutionComputer Science and Engineering
dc.date.registered2010
dc.date.completed2023
dc.date.awarded2023
dc.format.dimensions
dc.format.accompanyingmaterialNone
dc.source.universityUniversity
dc.type.degreePh.D.
Appears in Departments:Computer Science and Engineering

Files in This Item:
File Description SizeFormat 
01_title.pdfAttached File67.44 kBAdobe PDFView/Open
02_prelim pages.pdf110.28 kBAdobe PDFView/Open
03_content.pdf80.21 kBAdobe PDFView/Open
04_abstract.pdf40.34 kBAdobe PDFView/Open
05_chapter 1.pdf354.49 kBAdobe PDFView/Open
06_chapter 2.pdf748.13 kBAdobe PDFView/Open
07_chapter 3.pdf355.73 kBAdobe PDFView/Open
08_chapter 4.pdf387.8 kBAdobe PDFView/Open
10_chapter 6.pdf1.65 MBAdobe PDFView/Open
11_annexures.pdf88.05 kBAdobe PDFView/Open
80_recommendation.pdf82.46 kBAdobe PDFView/Open


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: