서브메뉴
검색
Modeling Social Interactions From Multimodal Signals.
Modeling Social Interactions From Multimodal Signals.
- 자료유형
- 학위논문
- Control Number
- 0017161671
- International Standard Book Number
- 9798384448846
- Dewey Decimal Classification Number
- 004
- Main Entry-Personal Name
- Ng, Evonne.
- Publication, Distribution, etc. (Imprint
- [S.l.] : University of California, Berkeley., 2024
- Publication, Distribution, etc. (Imprint
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- Physical Description
- 101 p.
- General Note
- Source: Dissertations Abstracts International, Volume: 86-03, Section: A.
- General Note
- Advisor: Darrell, Trevor;Kanazawa, Angjoo.
- Dissertation Note
- Thesis (Ph.D.)--University of California, Berkeley, 2024.
- Summary, Etc.
- 요약As social agents, humans have social intelligence that enables them to engage with others through complex signals such as facial expressions, body motion, and speech, among other communication modalities. Building systems that can perceive and model these fine-grain interaction dynamics is therefore essential for advancing human-machine interactions in everyday life. This thesis explores a few fundamental building blocks towards building such systems that can understand and exhibit appropriate gestural motion in conversational settings. The first work explores patterns in dyadic interactions by modeling the nonverbal conversational dynamics between the facial expressions of a speaker and a listener. The second builds upon this prior work, expanding the investigation towards modeling full-body dynamics. Finally the last work takes a step towards incorporating higher-level syntactic understanding by leveraging large language models to model listener-speaker dynamics.
- Subject Added Entry-Topical Term
- Computer science.
- Subject Added Entry-Topical Term
- Engineering.
- Subject Added Entry-Topical Term
- Communication.
- Subject Added Entry-Topical Term
- Information technology.
- Index Term-Uncontrolled
- Animation
- Index Term-Uncontrolled
- Computer vision
- Index Term-Uncontrolled
- Conversational AI
- Index Term-Uncontrolled
- Deep learning
- Index Term-Uncontrolled
- Gesture generation
- Index Term-Uncontrolled
- Conversational settings
- Added Entry-Corporate Name
- University of California, Berkeley Electrical Engineering & Computer Sciences
- Host Item Entry
- Dissertations Abstracts International. 86-03A.
- Electronic Location and Access
- 로그인을 한후 보실 수 있는 자료입니다.
- Control Number
- joongbu:654059
ค้นหาข้อมูลรายละเอียด
- จองห้องพัก
- 캠퍼스간 도서대출
- 서가에 없는 책 신고
- โฟลเดอร์ของฉัน