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

回上頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Visual object tracking = an evaluation perspective /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Visual object tracking/ by Xin Zhao, Shiyu Hu, Xu-Cheng Yin.
其他題名:	an evaluation perspective /
作者:	Zhao, Xin.
其他作者:	Hu, Shiyu.
出版者:	Singapore :Springer Nature Singapore : : 2025.,
面頁冊數:	xv, 199 p. :ill. (chiefly color), digital ;24 cm.
內容註:	Task Introduction -- Experimental Environment -- Algorithms -- Humans -- Machine-to-Machine Comparisons -- Visual Turing Test: Machine-to-Machine Comparisons -- More Human-like Task Design -- More Realistic Data Environment -- More Human-like Executors -- More Intelligent Evaluation.
Contained By:	Springer Nature eBook
標題:	Computer vision. -
電子資源:	https://doi.org/10.1007/978-981-96-4558-9
ISBN:	9789819645589

Visual object tracking = an evaluation perspective /
Zhao, Xin.

Visual object trackingan evaluation perspective /[electronic resource] :by Xin Zhao, Shiyu Hu, Xu-Cheng Yin. - Singapore :Springer Nature Singapore :2025. - xv, 199 p. :ill. (chiefly color), digital ;24 cm. - Advances in computer vision and pattern recognition,2191-6594. - Advances in computer vision and pattern recognition..

Task Introduction -- Experimental Environment -- Algorithms -- Humans -- Machine-to-Machine Comparisons -- Visual Turing Test: Machine-to-Machine Comparisons -- More Human-like Task Design -- More Realistic Data Environment -- More Human-like Executors -- More Intelligent Evaluation.

This book delves into visual object tracking (VOT), a fundamental aspect of computer vision crucial for replicating human dynamic vision, with applications ranging from self-driving vehicles to surveillance systems. Despite significant strides propelled by deep learning, challenges such as target deformation and motion persist, exposing a disparity between cutting-edge VOT systems and human performance. This observation underscores the necessity to thoroughly scrutinize and enhance evaluation methodologies within VOT research. Hence, the primary objective of this book is to equip readers with essential insights into dynamic visual tasks encapsulated by VOT. Beginning with the elucidation of task definitions, it integrates interdisciplinary perspectives on evaluation techniques. The book is organized into five parts, tracing the evolution of VOT from perceptual to cognitive intelligence, exploring the experimental frameworks utilized in assessments, analyzing the various agents involved, including tracking algorithms and human visual tracking, and dissecting evaluation mechanisms through both machine-machine and human-machine comparisons. Furthermore, it examines the trend toward crafting more human-like task definitions and comprehensive evaluation frameworks to effectively gauge machine intelligence. This book serves as a roadmap for researchers aiming to grasp the bottlenecks in VOT capabilities and comprehend the gaps between current methodologies and human abilities, all geared toward advancing algorithmic intelligence. It also delves into the realm of data-centric AI, emphasizing the pivotal role of high-quality datasets and evaluation systems in the age of large language models (LLMs). Such systems are indispensable for training AI models while ensuring their safety and reliability. Utilizing VOT as a case study, the book offers detailed insights into these facets of data-centric AI research. Designed to cater to readers with foundational knowledge in computer vision, it employs diagrams and examples to facilitate comprehension, providing essential groundwork for understanding key technical components.

ISBN: 9789819645589

Standard No.: 10.1007/978-981-96-4558-9doiSubjects--Topical Terms:

540671
Computer vision.

LC Class. No.: TA1634

Dewey Class. No.: 006.37

Visual object tracking = an evaluation perspective /
LDR:03553nmm a2200349 a 4500 001 2413294
003 DE-He213
005 20250702130232.0
006 m d
007 cr nn 008maaau
008 260205s2025 si s 0 eng d
020 $a 9789819645589 $q (electronic bk.)
020 $a 9789819645572 $q (paper)
024 7 $a 10.1007/978-981-96-4558-9 $2 doi
035 $a 978-981-96-4558-9
040 $a GP $c GP
041 0 $a eng
050 4 $a TA1634
072 7 $a UYQV $2 bicssc
072 7 $a COM016000 $2 bisacsh
072 7 $a UYQV $2 thema
082 0 4 $a 006.37 $2 23
090 $a TA1634 $b .Z63 2025
100 1 $a Zhao, Xin. $3 1023944
245 1 0 $a Visual object tracking $h [electronic resource] : $b an evaluation perspective / $c by Xin Zhao, Shiyu Hu, Xu-Cheng Yin.
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2025.
300 $a xv, 199 p. : $b ill. (chiefly color), digital ; $c 24 cm.
338 $a online resource $b cr $2 rdacarrier
490 1 $a Advances in computer vision and pattern recognition, $x 2191-6594
505 0 $a Task Introduction -- Experimental Environment -- Algorithms -- Humans -- Machine-to-Machine Comparisons -- Visual Turing Test: Machine-to-Machine Comparisons -- More Human-like Task Design -- More Realistic Data Environment -- More Human-like Executors -- More Intelligent Evaluation.
520 $a This book delves into visual object tracking (VOT), a fundamental aspect of computer vision crucial for replicating human dynamic vision, with applications ranging from self-driving vehicles to surveillance systems. Despite significant strides propelled by deep learning, challenges such as target deformation and motion persist, exposing a disparity between cutting-edge VOT systems and human performance. This observation underscores the necessity to thoroughly scrutinize and enhance evaluation methodologies within VOT research. Hence, the primary objective of this book is to equip readers with essential insights into dynamic visual tasks encapsulated by VOT. Beginning with the elucidation of task definitions, it integrates interdisciplinary perspectives on evaluation techniques. The book is organized into five parts, tracing the evolution of VOT from perceptual to cognitive intelligence, exploring the experimental frameworks utilized in assessments, analyzing the various agents involved, including tracking algorithms and human visual tracking, and dissecting evaluation mechanisms through both machine-machine and human-machine comparisons. Furthermore, it examines the trend toward crafting more human-like task definitions and comprehensive evaluation frameworks to effectively gauge machine intelligence. This book serves as a roadmap for researchers aiming to grasp the bottlenecks in VOT capabilities and comprehend the gaps between current methodologies and human abilities, all geared toward advancing algorithmic intelligence. It also delves into the realm of data-centric AI, emphasizing the pivotal role of high-quality datasets and evaluation systems in the age of large language models (LLMs). Such systems are indispensable for training AI models while ensuring their safety and reliability. Utilizing VOT as a case study, the book offers detailed insights into these facets of data-centric AI research. Designed to cater to readers with foundational knowledge in computer vision, it employs diagrams and examples to facilitate comprehension, providing essential groundwork for understanding key technical components.
650 0 $a Computer vision. $3 540671
650 0 $a Tracking (Engineering) $3 2192932
650 1 4 $a Computer Vision. $3 3538524
650 2 4 $a Image Processing. $3 891209
650 2 4 $a Artificial Intelligence. $3 769149
650 2 4 $a Machine Learning. $3 3382522
650 2 4 $a Data Science. $3 3538937
650 2 4 $a System Performance and Evaluation. $3 891353
700 1 $a Hu, Shiyu. $3 3789242
700 1 $a Yin, Xu-Cheng. $3 3714556
710 2 $a SpringerLink (Online service) $3 836513
773 0 $t Springer Nature eBook
830 0 $a Advances in computer vision and pattern recognition. $3 1567575
856 4 0 $u https://doi.org/10.1007/978-981-96-4558-9
950 $a Computer Science (SpringerNature-11645)