본문

서브메뉴

상세정보

Visual Discovery from Spatio-Temporal Imagery- [electronic resource]
Visual Discovery from Spatio-Temporal Imagery - [electronic resource] / Utkarsh Kumar Mall
Visual Discovery from Spatio-Temporal Imagery- [electronic resource]

상세정보

자료유형  
 학위논문(국외)
자관 청구기호  
기본표목-개인명  
표제와 책임표시사항  
Visual Discovery from Spatio-Temporal Imagery - [electronic resource] / Utkarsh Kumar Mall
발행, 배포, 간사 사항  
[S.l.] : Cornell University. , 2023
    발행, 배포, 간사 사항  
    Ann Arbor : ProQuest Dissertations & Theses , 2023
      형태사항  
      1 online resource(p.301 )
      일반주기  
      Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
      일반주기  
      Advisor: Bala, Kavita;Hariharan, Bharath.
      학위논문주기  
      Thesis (Ph.D.)--Cornell University, 2023.
      이용제한주기  
      This item must not be sold to any third party vendors.
      요약 등 주기  
      요약From social media to street view and all the way to satellite images, we are capturing visual data at an unprecedented scale. These images tell a story about our planet. With advances in automatic recognition, we can build a collective understanding of world-scale events as recorded through visual media. Such insights have the potential to be useful for various experts in their domain such as cultural anthropologists and ecologists. However, discovering such rare yet interesting insights from the data is very challenging. First, it requires recognition models that have an expert-level understanding of such visual domains. Second, it requires tools that can leverage such models and large-scale spatio-temporal data and discover novel insights. In this dissertation, we first look at ways of building and improving automatic recognition models in such expert domains. More specifically we look at how we can efficiently learn a representation for such domains with either no supervision or with text or attribute-based supervision. We specifically work with domains that require expertise for understanding such as ornithology or remote sensing. These methods not only aim to make the recognition models more cost-efficient but also more practical to be used with experts. More specifically we present an unsupervised method to learn representation in the satellite image domain. Then we look at an attribute-based model for bird classification (and other attribute-based domains) and introduce ways to make it more practical and label-efficient to work with.We then present methods that can discover novel insights without any supervision by looking at large-scale spatio-temporal visual data. These methods make use of domain-specific vision models to make the discovery. More specifically, we use these methods to understand fashion trends and discover cultural phenomena and social events around the world by looking at fashion images from social media. Broadening our domain to include satellite imagery, we introduce completely unsupervised techniques to discover interesting change events across the planet from satellite images. This general framework can be potentially applied in different visual domains ranging from sustainability to online commerce to discover interesting phenomena in those domains.
      주제명부출표목-일반주제명  
      주제명부출표목-일반주제명  
      주제명부출표목-일반주제명  
      비통제 색인어  
      비통제 색인어  
      비통제 색인어  
      비통제 색인어  
      비통제 색인어  
      비통제 색인어  
      부출표목-단체명  
      Cornell University Computer Science
        기본자료저록  
        Dissertations Abstracts International. 85-03B.
        기본자료저록  
        Dissertation Abstract International
        전자적 위치 및 접속  
         원문정보보기
        소장사항  
        202402 2024

        MARC

         008240306s2023        s  |          s        0000c|  eng  d
        ■001000016934634
        ■00520240214101636
        ■006m          o    d                
        ■007cr
        ■020    ▼a9798380316040
        ■035    ▼a(MiAaPQ)AAI30631748
        ■040    ▼aMiAaPQ▼cMiAaPQ
        ■08204▼a004
        ■090    ▼a전자도서(박사논문)
        ■1001  ▼aMall,  Utkarsh  Kumar.▼0(orcid)0009-0002-5302-0657
        ■24510▼aVisual  Discovery  from  Spatio-Temporal  Imagery▼h[electronic  resource]▼cUtkarsh  Kumar  Mall
        ■260    ▼a[S.l.]▼bCornell  University.  ▼c2023
        ■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2023
        ■300    ▼a1  online  resource(p.301  )
        ■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-03,  Section:  B.
        ■500    ▼aAdvisor:  Bala,  Kavita;Hariharan,  Bharath.
        ■5021  ▼aThesis  (Ph.D.)--Cornell  University,  2023.
        ■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
        ■520    ▼aFrom  social  media  to  street  view  and  all  the  way  to  satellite  images,  we  are  capturing  visual  data  at  an  unprecedented  scale.  These  images  tell  a  story  about  our  planet.  With  advances  in  automatic  recognition,  we  can  build  a  collective  understanding  of  world-scale  events  as  recorded  through  visual  media.  Such  insights  have  the  potential  to  be  useful  for  various  experts  in  their  domain  such  as  cultural  anthropologists  and  ecologists.  However,  discovering  such  rare  yet  interesting  insights  from  the  data  is  very  challenging.  First,  it  requires  recognition  models  that  have  an  expert-level  understanding  of  such  visual  domains.  Second,  it  requires  tools  that  can  leverage  such  models  and  large-scale  spatio-temporal  data  and  discover  novel  insights.  In  this  dissertation,  we  first  look  at  ways  of  building  and  improving  automatic  recognition  models  in  such  expert  domains.  More  specifically  we  look  at  how  we  can  efficiently  learn  a  representation  for  such  domains  with  either  no  supervision  or  with  text  or  attribute-based  supervision.  We  specifically  work  with  domains  that  require  expertise  for  understanding  such  as  ornithology  or  remote  sensing.  These  methods  not  only  aim  to  make  the  recognition  models  more  cost-efficient  but  also  more  practical  to  be  used  with  experts.  More  specifically  we  present  an  unsupervised  method  to  learn  representation  in  the  satellite  image  domain.  Then  we  look  at  an  attribute-based  model  for  bird  classification  (and  other  attribute-based  domains)  and  introduce  ways  to  make  it  more  practical  and  label-efficient  to  work  with.We  then  present  methods  that  can  discover  novel  insights  without  any  supervision  by  looking  at  large-scale  spatio-temporal  visual  data.  These  methods  make  use  of  domain-specific  vision  models  to  make  the  discovery.  More  specifically,  we  use  these  methods  to  understand  fashion  trends  and  discover  cultural  phenomena  and  social  events  around  the  world  by  looking  at  fashion  images  from  social  media.  Broadening  our  domain  to  include  satellite  imagery,  we  introduce  completely  unsupervised  techniques  to  discover  interesting  change  events  across  the  planet  from  satellite  images.  This  general  framework  can  be  potentially  applied  in  different  visual  domains  ranging  from  sustainability  to  online  commerce  to  discover  interesting  phenomena  in  those  domains.
        ■590    ▼aSchool  code:  0058.
        ■650  4▼aComputer  science.
        ■650  4▼aComputer  engineering.
        ■650  4▼aRemote  sensing.
        ■653    ▼aComputer  vision
        ■653    ▼aDiscovery
        ■653    ▼aMachine  learning
        ■653    ▼aUnsupervised  learning
        ■653    ▼aSocial  media
        ■653    ▼aSatellite  images
        ■690    ▼a0984
        ■690    ▼a0464
        ■690    ▼a0800
        ■690    ▼a0799
        ■71020▼aCornell  University▼bComputer  Science.
        ■7730  ▼tDissertations  Abstracts  International▼g85-03B.
        ■773    ▼tDissertation  Abstract  International
        ■790    ▼a0058
        ■791    ▼aPh.D.
        ■792    ▼a2023
        ■793    ▼aEnglish
        ■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16934634▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
        ■980    ▼a202402▼f2024

        미리보기

        내보내기

        chatGPT토론

        Ai 추천 관련 도서


          신착도서 더보기
          관련도서 더보기
          최근 3년간 통계입니다.
          SMS 발송 간략정보 이동 상세정보출력

          소장정보

          • 예약
          • 서가에 없는 책 신고
          • 자료배달서비스
          • 나의폴더
          • 우선정리요청
          소장자료
          등록번호 청구기호 소장처 대출가능여부 대출정보
          EM163464 TD  전자도서(박사논문) 연속간행물실(2층) 온라인이용가능 온라인이용가능
          마이폴더

          * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

          해당 도서를 다른 이용자가 함께 대출한 도서

          관련도서

          관련 인기도서

          서평쓰기

          도서위치

          AiBot !!
          CH