서브메뉴
검색
Controllable Content Based Image Synthesis and Image Retrieval
Controllable Content Based Image Synthesis and Image Retrieval
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105538
- ISBN
- 9798263390662
- DDC
- 006
- 서명/저자
- Controllable Content Based Image Synthesis and Image Retrieval
- 발행사항
- [Sl] : Georgia Institute of Technology, 2022
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2022
- 형태사항
- 162 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
- 주기사항
- Advisor: Hays, James.
- 학위논문주기
- Thesis (Ph.D.)--Georgia Institute of Technology, 2022.
- 초록/해제
- 요약In this thesis, we address the problem of returning target images that match user queries in image retrieval and image synthesis. We investigate line drawing sketch as the main query, and explore several additional signals from the users that can helps clarify the type of images they are looking for. These additional queries may be expressed in one of the following two convenient forms:1. visual content (sketch, scribble, texture patch);2. language content.For image retrieval, we first look at the problem of sketch based image retrieval. We construct cross-domain networks that embed a user query and a target image into a shared feature space. We collected Sketchy Database; a large-scale dataset of matching sketch and image pairs that can be used as training data. The dataset has been made publicly available, and has become one of the few standard benchmarks for sketch-based image retrieval.To incorporate both sketch and language content as a queries, we propose a late-fusion dual-encoder approach, similar to CLIP; a recent successful work on vision and language representation learning. We also collected the dataset of 5,000 hand drawn sketch, which can be combined with existing COCO caption annotation to evaluate the task of image retrieval with sketch and language.For image synthesis, we present a general framework that allows users to interactively control the generated images based on specification of visual features (e.g., shape, color, texture).
- 일반주제명
- Deep learning
- 일반주제명
- Image retrieval
- 일반주제명
- Colorization
- 일반주제명
- Benchmarks
- 일반주제명
- Computer science
- 기본자료저록
- Dissertations Abstracts International. 87-05B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2022 us c eng d■001000017360506
■00520260202105538
■006m o d
■007cr#unu||||||||
■020 ▼a9798263390662
■035 ▼a(MiAaPQ)AAI32314919
■035 ▼a(MiAaPQ)GeorgiaTech66630
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a006
■1001 ▼aSangkloy, Patsorn.
■24510▼aControllable Content Based Image Synthesis and Image Retrieval
■260 ▼a[Sl]▼bGeorgia Institute of Technology▼c2022
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2022
■300 ▼a162 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-05, Section: B.
■500 ▼aAdvisor: Hays, James.
■5021 ▼aThesis (Ph.D.)--Georgia Institute of Technology, 2022.
■520 ▼aIn this thesis, we address the problem of returning target images that match user queries in image retrieval and image synthesis. We investigate line drawing sketch as the main query, and explore several additional signals from the users that can helps clarify the type of images they are looking for. These additional queries may be expressed in one of the following two convenient forms:1. visual content (sketch, scribble, texture patch);2. language content.For image retrieval, we first look at the problem of sketch based image retrieval. We construct cross-domain networks that embed a user query and a target image into a shared feature space. We collected Sketchy Database; a large-scale dataset of matching sketch and image pairs that can be used as training data. The dataset has been made publicly available, and has become one of the few standard benchmarks for sketch-based image retrieval.To incorporate both sketch and language content as a queries, we propose a late-fusion dual-encoder approach, similar to CLIP; a recent successful work on vision and language representation learning. We also collected the dataset of 5,000 hand drawn sketch, which can be combined with existing COCO caption annotation to evaluate the task of image retrieval with sketch and language.For image synthesis, we present a general framework that allows users to interactively control the generated images based on specification of visual features (e.g., shape, color, texture).
■590 ▼aSchool code: 0078.
■650 4▼aDeep learning
■650 4▼aImage retrieval
■650 4▼aColorization
■650 4▼aBenchmarks
■650 4▼aComputer science
■690 ▼a0800
■690 ▼a0984
■71020▼aGeorgia Institute of Technology.
■7730 ▼tDissertations Abstracts International▼g87-05B.
■790 ▼a0078
■791 ▼aPh.D.
■792 ▼a2022
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17360506▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
