東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Human-Centric Perception With Limite...

Weng, Zhenzhen,

FindBook

Google Book

Amazon

博客來

Human-Centric Perception With Limited Supervision: Improving Generalizability in the Wild /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Human-Centric Perception With Limited Supervision: Improving Generalizability in the Wild // Zhenzhen Weng.
作者:	Weng, Zhenzhen,
面頁冊數:	1 electronic resource (214 pages)
附註:	Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
Contained By:	Dissertations Abstracts International86-05B.
標題:	Adaptation. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31520294
ISBN:	9798342114684

Human-Centric Perception With Limited Supervision: Improving Generalizability in the Wild /
Weng, Zhenzhen,

Human-Centric Perception With Limited Supervision: Improving Generalizability in the Wild /Zhenzhen Weng. - 1 electronic resource (214 pages)

Source: Dissertations Abstracts International, Volume: 86-05, Section: B.

Human-centric perception has numerous valuable applications in self-driving vehicles, AI-assisted healthcare, and content creation, where understanding human poses and behaviors enhances planning, intervention strategies, and visual e↵ects. However, challenges such as the high cost of data capture and annotation limit the availability of training data for 3D applications. This thesis addresses these challenges through various methods leveraging priors and pre-trained models to improve perception models with limited supervision.The first part of the thesis explores leveraging priors to enhance perception models. It introduces a method using common room layout knowledge to refine indoor human and scene reconstructions and a method that learns human body priors from unannotated LiDAR sensor data, reducing the need for annotated training data. This is particularly beneficial in self-driving, where large sensor data captures are common, but 3D annotation is complex.The second part presents a study that bootstraps synthetic data for training perception models using human pose priors. Incorporating diverse synthetic data results in more robust models that perform well in challenging scenarios. This method, applied to caregiver-child interaction videos, extracts human behavior aspects to facilitate behavioral and developmental research, enhancing perception models and providing insights into developmental processes.The third part discusses using pre-trained generative models to create realistic synthetic human training data. It introduces methods employing pre-trained generative and di↵usion models to enhance perception models, leveraging powerful 2D models to reduce dependence on high-quality 3D training data.Overall, this thesis demonstrates that data-driven methods for understanding human form and behavior significantly improve our ability to perceive and generate realistic human representations with high fidelity and accuracy.

English

ISBN: 9798342114684Subjects--Topical Terms:

3562958
Adaptation.

Human-Centric Perception With Limited Supervision: Improving Generalizability in the Wild /
LDR:03252nmm a22003733i 4500 001 2438658
005 20260727134406.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798342114684
035 $a (MiAaPQD)AAI31520294
035 $a (MiAaPQD)Stanfordnk873jd2198
035 $a AAI31520294
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Weng, Zhenzhen, $e author. $3 3830028
245 1 0 $a Human-Centric Perception With Limited Supervision: Improving Generalizability in the Wild / $c Zhenzhen Weng.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (214 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
500 $a Advisors: Yeung, Serena Committee members: Fatahalian, Kayvon; Fedkiw, Ron.
502 $b Ph.D. $c Stanford University $d 2024.
520 $a Human-centric perception has numerous valuable applications in self-driving vehicles, AI-assisted healthcare, and content creation, where understanding human poses and behaviors enhances planning, intervention strategies, and visual e↵ects. However, challenges such as the high cost of data capture and annotation limit the availability of training data for 3D applications. This thesis addresses these challenges through various methods leveraging priors and pre-trained models to improve perception models with limited supervision.The first part of the thesis explores leveraging priors to enhance perception models. It introduces a method using common room layout knowledge to refine indoor human and scene reconstructions and a method that learns human body priors from unannotated LiDAR sensor data, reducing the need for annotated training data. This is particularly beneficial in self-driving, where large sensor data captures are common, but 3D annotation is complex.The second part presents a study that bootstraps synthetic data for training perception models using human pose priors. Incorporating diverse synthetic data results in more robust models that perform well in challenging scenarios. This method, applied to caregiver-child interaction videos, extracts human behavior aspects to facilitate behavioral and developmental research, enhancing perception models and providing insights into developmental processes.The third part discusses using pre-trained generative models to create realistic synthetic human training data. It introduces methods employing pre-trained generative and di↵usion models to enhance perception models, leveraging powerful 2D models to reduce dependence on high-quality 3D training data.Overall, this thesis demonstrates that data-driven methods for understanding human form and behavior significantly improve our ability to perceive and generate realistic human representations with high fidelity and accuracy.
546 $a English
590 $a School code: 0212
650 4 $a Adaptation. $3 3562958
650 4 $a Caregivers. $3 580207
650 4 $a Geometry. $3 517251
650 4 $a Computer engineering. $3 621879
650 4 $a Applied mathematics. $3 2122814
690 $a 0464
690 $a 0364
710 2 $a Stanford University. $e degree granting institution. $3 3765820
720 1 $a Yeung, Serena $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-05B.
790 $a 0212
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31520294