본문

서브메뉴

Enabling Semantically Richer Queries Over Unstructured Data
Enabling Semantically Richer Queries Over Unstructured Data
Enabling Semantically Richer Queries Over Unstructured Data

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202105504
ISBN  
9798263326302
DDC  
574
저자명  
Chunduri, Pramod.
서명/저자  
Enabling Semantically Richer Queries Over Unstructured Data
발행사항  
[Sl] : Georgia Institute of Technology, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
200 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
주기사항  
Advisor: Arulraj, Joy.
학위논문주기  
Thesis (Ph.D.)--Georgia Institute of Technology, 2025.
초록/해제  
요약Querying unstructured data such as video, audio, and text is critical for domains ranging from traffic surveillance to healthcare and finance. Modern AI models (e.g., vision and language models) unlock significant potential for extracting fine-grained information from such data. However, current data systems that leverage these models primarily focus on efficiently executing semantically simple queries.This thesis argues that enabling semantically rich queries over unstructured data requires rethinking both the query execution strategies and the query interfaces. To this end, we develop four systems that can efficiently and accurately process semantically rich queries over unstructured data.First, we present Zeus, a video analytics system that efficiently localizes complex actions in videos using a reinforcement learning (RL)-based query executor. By using accuracy-based rewards during query planning, Zeus substantially improves efficiency while meeting user-specified accuracy targets.Next, we propose Tracer, an adaptive query processing framework for multi-camera re-identification queries. Tracer uses a recurrent network with a probabilistic search model to optimally select camera feeds to process at each time step. Tracer significantly reduces the cost of re-identification queries on synthetically generated and real-world datasets.We then introduce SketchQL, a visual query interface that allows users to sketch complex video moments. SketchQL maps these sketches to fine-grained video moments using a transformer model trained on synthetically generated data. SketchQL greatly enhances the usability and accuracy of fine-grained video moment retrieval.Finally, we present Halo, a long-context question answering (QA) framework designed for domain-augmented queries. Halo incorporates domain knowledge into the QA pipeline via a Domain Hints interface, allowing users to specify structured suggestions that augment the original query. A three-stage execution pipeline applies these hints automatically and optimally, improving both the efficiency and accuracy of long-context QA.
일반주제명  
Adaptation
일반주제명  
User feedback
일반주제명  
Computer science
키워드  
Querying unstructured data
기타저자  
Georgia Institute of Technology.
기본자료저록  
Dissertations Abstracts International. 87-06B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017360309
■00520260202105504
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798263326302
■035    ▼a(MiAaPQ)AAI32308000
■035    ▼a(MiAaPQ)GeorgiaTech78732
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a574
■1001  ▼aChunduri,  Pramod.
■24510▼aEnabling  Semantically  Richer  Queries  Over  Unstructured  Data
■260    ▼a[Sl]▼bGeorgia  Institute  of  Technology▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a200  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-06,  Section:  B.
■500    ▼aAdvisor:  Arulraj,  Joy.
■5021  ▼aThesis  (Ph.D.)--Georgia  Institute  of  Technology,  2025.
■520    ▼aQuerying  unstructured  data  such  as  video,  audio,  and  text  is  critical  for  domains  ranging  from  traffic  surveillance  to  healthcare  and  finance.  Modern  AI  models  (e.g.,  vision  and  language  models)  unlock  significant  potential  for  extracting  fine-grained  information  from  such  data.  However,  current  data  systems  that  leverage  these  models  primarily  focus  on  efficiently  executing  semantically  simple  queries.This  thesis  argues  that  enabling  semantically  rich  queries  over  unstructured  data  requires  rethinking  both  the  query  execution  strategies  and  the  query  interfaces.  To  this  end,  we  develop  four  systems  that  can  efficiently  and  accurately  process  semantically  rich  queries  over  unstructured  data.First,  we  present  Zeus,  a  video  analytics  system  that  efficiently  localizes  complex  actions  in  videos  using  a  reinforcement  learning  (RL)-based  query  executor.  By  using  accuracy-based  rewards  during  query  planning,  Zeus  substantially  improves  efficiency  while  meeting  user-specified  accuracy  targets.Next,  we  propose  Tracer,  an  adaptive  query  processing  framework  for  multi-camera  re-identification  queries.  Tracer  uses  a  recurrent  network  with  a  probabilistic  search  model  to  optimally  select  camera  feeds  to  process  at  each  time  step.  Tracer  significantly  reduces  the  cost  of  re-identification  queries  on  synthetically  generated  and  real-world  datasets.We  then  introduce  SketchQL,  a  visual  query  interface  that  allows  users  to  sketch  complex  video  moments.  SketchQL  maps  these  sketches  to  fine-grained  video  moments  using  a  transformer  model  trained  on  synthetically  generated  data.  SketchQL  greatly  enhances  the  usability  and  accuracy  of  fine-grained  video  moment  retrieval.Finally,  we  present  Halo,  a  long-context  question  answering  (QA)  framework  designed  for  domain-augmented  queries.  Halo  incorporates  domain  knowledge  into  the  QA  pipeline  via  a  Domain  Hints  interface,  allowing  users  to  specify  structured  suggestions  that  augment  the  original  query.  A  three-stage  execution  pipeline  applies  these  hints  automatically  and  optimally,  improving  both  the  efficiency  and  accuracy  of  long-context  QA.
■590    ▼aSchool  code:  0078.
■650  4▼aAdaptation
■650  4▼aUser  feedback
■650  4▼aComputer  science
■653    ▼aQuerying  unstructured  data
■690    ▼a0984
■71020▼aGeorgia  Institute  of  Technology.
■7730  ▼tDissertations  Abstracts  International▼g87-06B.
■790    ▼a0078
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360309▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Info Détail de la recherche.

    • Réservation
    • n'existe pas
    • My Folder
    • Demande Première utilisation
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Matériel
    Reg No. Call No. emplacement Status Lend Info
    TF19120 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Les réservations sont disponibles dans le livre d'emprunt. Pour faire des réservations, S'il vous plaît cliquer sur le bouton de réservation

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.