Normal view MARC view ISBD view

Efficient posevit : (Record no. 35568)

MARC details
000 -LEADER
fixed length control field	03146nas a2200397 a 4500
005 - DATE AND TIME OF LATEST TRANSACTION
control field	20260818095404.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field	240223s2023 th u m tt 000 a eng d
035 ## - SYSTEM CONTROL NUMBER
System control number	.b12420591
099 ## - LOCAL FREE-TEXT CALL NUMBER (OCLC)
Classification number	AIT Thesis no.CS-23-05
100 1# - MAIN ENTRY--PERSONAL NAME
Personal name	Lamsal, Diwas
245 10 - TITLE STATEMENT
Title	Efficient posevit :
Remainder of title	exploring efficient vision transformers and training strategies for fast human pose estimation
260 ## - PUBLICATION, DISTRIBUTION, ETC.
Place of publication, distribution, etc.	Pathum Thani, Thailand :
Name of publisher, distributor, etc.	Asian Institute of Technology,
Date of publication, distribution, etc.	2023
300 ## - PHYSICAL DESCRIPTION
Extent	74 leaves :
Other physical details	ill.
490 1# - SERIES STATEMENT
Series statement	Thesis ;
Volume/sequential designation	no.CS-23-05
500 ## - GENERAL NOTE
General note	A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science
502 ## - DISSERTATION NOTE
Dissertation note	Thesis (M. Eng.) - Asian Institute of Technology, 2023
520 ## - SUMMARY, ETC.
Summary, etc.	Human pose estimation (HPE) serves as a critical component in various downstream applications, including activity recognition and human-computer interaction. However, it faces challenges such as occlusion, complex body poses, diverse clothing and environments, and low-quality images. State-of-the-art HPE methods adept at addressing these challenges often prove to be computationally expensive to run on low-cost edge devices. On the other hand, the efficient models designed to run on edge devices are not as accurate, especially when faced with occlusion. In this thesis, I explored the use of computationally efficient vision transformer (ViT) backbones for the task of HPE to produce an efficient model capable of running on edge devices while also addressing common HPE challenges. Specifically, I replaced the ViT encoder in ViTPose with effi cient ViT variants, and performed a comprehensive comparison. The findings indicate that the EdgeNeXt-Base model offers an optimal speed-accuracy trade-off among the evaluated models. Through knowledge distillation and multi-task training strategies, the resulting models exhibit improved performance, particularly in handling occlusion. Additionally, I produced a wheelchair-based human pose estimation and activity recognition dataset aimed at developing a system that effectively monitors the activities of people sitting in wheelchairs.
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element	Image analysis
650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element	Human-computer interaction
700 1# - ADDED ENTRY--PERSONAL NAME
Personal name	Dailey, Matthew N.,
Relator term	Chairperson
700 0# - ADDED ENTRY--PERSONAL NAME
Personal name	Mongkol Ekpanyapong,
Relator term	Examination Committee
700 0# - ADDED ENTRY--PERSONAL NAME
Personal name	Chaklam Silpasuwanchai,
Relator term	Examination Committee
710 2# - ADDED ENTRY--CORPORATE NAME
Corporate name or jurisdiction name as entry element	AIT Scholarships,
Relator term	Scholarship Donor
810 2# - SERIES ADDED ENTRY--CORPORATE NAME
Corporate name or jurisdiction name as entry element	Asian Institute of Technology.
Title of a work	Thesis :
Volume/sequential designation	no.CS-23-05
856 40 - ELECTRONIC LOCATION AND ACCESS
Materials specified	Full-Text
Uniform Resource Identifier	<a href="http://203.159.5.9/ait-thesis/Viewer/viewer.php?id=B20405">http://203.159.5.9/ait-thesis/Viewer/viewer.php?id=B20405</a>
907 ## - LOCAL DATA ELEMENT G, LDG (RLIN)
a	.b12420591
b	mnait
c	a
902 ## - LOCAL DATA ELEMENT B, LDB (RLIN)
a	250303
998 ## - LOCAL CONTROL INFORMATION (RLIN)
Operator's initials, OID (RLIN)	0
Cataloger's initials, CIN (RLIN)	240312
First date, FD (RLIN)	m
--	a
--	a
--	0
945 ## - LOCAL PROCESSING INFORMATION (OCLC)
l	mnarc
945 ## - LOCAL PROCESSING INFORMATION (OCLC)
l	mnarc
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type	67-Electronic Resource
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type	40-Archives
909 ## - LOCAL ITEMS USED
Barcode	Barcode : -
CREATED	CREATED : 2024-02-23
RECORD Id	RECORD # : i13486640
LPATRON	LPATRON : 0
LCHKIN	LCHKIN : -
RENEWALS	# RENEWALS : 0
--	# OVERDUE : 0
--	IUSE3 : 0
--	TOT CHKOUT : 0
--	TOT RENEW : 0
909 ## - LOCAL ITEMS USED
Barcode	Barcode : 30050120900476
CREATED	CREATED : 2025-03-03
RECORD Id	RECORD # : i13535183
LPATRON	LPATRON : 0
LCHKIN	LCHKIN : -
RENEWALS	# RENEWALS : 0
--	# OVERDUE : 0
--	IUSE3 : 0
--	TOT CHKOUT : 0
--	TOT RENEW : 0

Holdings
Withdrawn status	Lost status	Damaged status	Not for loan	Home library	Current library	Shelving location	Date acquired	Total checkouts	Full call number	Date last seen	Price effective from	Koha item type	Barcode	Copy number
			Available for Loans	Asian Institute of Technology Library	Asian Institute of Technology Library	Archives	18/08/2026		AIT Thesis no.CS-23-05	18/08/2026	18/08/2026	67-Electronic Resource
			Available for Loans	Asian Institute of Technology Library	Asian Institute of Technology Library	Archives	18/08/2026		AIT Thesis no.CS-23-05	18/08/2026	18/08/2026	40-Archives	30050120900476	1

Efficient posevit : (Record no. 35568)

AIT

Asian Institute of Technology Library