國立虎尾科技大學 |

Deep learning for video understanding

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Deep learning for video understanding/ by Zuxuan Wu, Yu-Gang Jiang.
作者:	Wu, Zuxuan.
其他作者:	Jiang, Yu-Gang.
出版者:	Cham :Springer Nature Switzerland : : 2024.,
面頁冊數:	ix, 188 p. :ill. (chiefly col.), digital ; : 24 cm.;
Contained By:	Springer Nature eBook
標題:	Multimedia Information Systems. -
電子資源:	https://doi.org/10.1007/978-3-031-57679-9
ISBN:	9783031576799

Deep learning for video understanding
Wu, Zuxuan.

Deep learning for video understanding[electronic resource] /by Zuxuan Wu, Yu-Gang Jiang. - Cham :Springer Nature Switzerland :2024. - ix, 188 p. :ill. (chiefly col.), digital ;24 cm. - Wireless networks,2366-1445. - Wireless networks..

Introduction -- Overview of Video Understanding -- Deep Learning Basics for Video Understanding -- Deep Learning for Action Recognition -- Deep Learning for Action Localization -- Deep Learning for Video Captioning -- Unsupervised Feature Learning for Video Understanding -- Efficient Video Understanding -- Future Research Directions -- Conclusion.

This book presents deep learning techniques for video understanding. For deep learning basics, the authors cover machine learning pipelines and notations, 2D and 3D Convolutional Neural Networks for spatial and temporal feature learning. For action recognition, the authors introduce classical frameworks for image classification, and then elaborate both image-based and clip-based 2D/3D CNN networks for action recognition. For action detection, the authors elaborate sliding windows, proposal-based detection methods, single stage and two stage approaches, spatial and temporal action localization, followed by datasets introduction. For video captioning, the authors present language-based models and how to perform sequence to sequence learning for video captioning. For unsupervised feature learning, the authors discuss the necessity of shifting from supervised learning to unsupervised learning and then introduce how to design better surrogate training tasks to learn video representations. Finally, the book introduces recent self-training pipelines like contrastive learning and masked image/video modeling with transformers. The book provides promising directions, with an aim to promote future research outcomes in the field of video understanding with deep learning. Presents an overview of deep learning techniques for video understanding; Covers important topics like action recognition, action localization, video captioning, and more; Introduces cutting-edge and state-of-the-art video understanding techniques.

ISBN: 9783031576799

Standard No.: 10.1007/978-3-031-57679-9doiSubjects--Topical Terms:

669810
Multimedia Information Systems.

LC Class. No.: Q325.73

Dewey Class. No.: 006.31

Deep learning for video understanding
LDR:02887nam a2200337 a 4500 001 1134068
003 DE-He213
005 20240801130618.0
006 m d
007 cr nn 008maaau
008 241213s2024 sz s 0 eng d
020 $a 9783031576799 $q (electronic bk.)
020 $a 9783031576782 $q (paper)
024 7 $a 10.1007/978-3-031-57679-9 $2 doi
035 $a 978-3-031-57679-9
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.73
072 7 $a TJK $2 bicssc
072 7 $a TEC041000 $2 bisacsh
072 7 $a TJK $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.73 $b .W959 2024
100 1 $a Wu, Zuxuan. $3 1455381
245 1 0 $a Deep learning for video understanding $h [electronic resource] / $c by Zuxuan Wu, Yu-Gang Jiang.
260 $a Cham : $c 2024. $b Springer Nature Switzerland : $b Imprint: Springer,
300 $a ix, 188 p. : $b ill. (chiefly col.), digital ; $c 24 cm.
490 1 $a Wireless networks, $x 2366-1445
505 0 $a Introduction -- Overview of Video Understanding -- Deep Learning Basics for Video Understanding -- Deep Learning for Action Recognition -- Deep Learning for Action Localization -- Deep Learning for Video Captioning -- Unsupervised Feature Learning for Video Understanding -- Efficient Video Understanding -- Future Research Directions -- Conclusion.
520 $a This book presents deep learning techniques for video understanding. For deep learning basics, the authors cover machine learning pipelines and notations, 2D and 3D Convolutional Neural Networks for spatial and temporal feature learning. For action recognition, the authors introduce classical frameworks for image classification, and then elaborate both image-based and clip-based 2D/3D CNN networks for action recognition. For action detection, the authors elaborate sliding windows, proposal-based detection methods, single stage and two stage approaches, spatial and temporal action localization, followed by datasets introduction. For video captioning, the authors present language-based models and how to perform sequence to sequence learning for video captioning. For unsupervised feature learning, the authors discuss the necessity of shifting from supervised learning to unsupervised learning and then introduce how to design better surrogate training tasks to learn video representations. Finally, the book introduces recent self-training pipelines like contrastive learning and masked image/video modeling with transformers. The book provides promising directions, with an aim to promote future research outcomes in the field of video understanding with deep learning. Presents an overview of deep learning techniques for video understanding; Covers important topics like action recognition, action localization, video captioning, and more; Introduces cutting-edge and state-of-the-art video understanding techniques.
650 2 4 $a Multimedia Information Systems. $3 669810
650 2 4 $a Computer Vision. $3 1127422
650 2 4 $a Signal, Speech and Image Processing. $3 1414819
650 1 4 $a Communications Engineering, Networks. $3 669809
650 0 $a Deep learning (Machine learning) $3 1381171
700 1 $a Jiang, Yu-Gang. $3 1455382
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
830 0 $a Wireless networks. $3 1069216
856 4 0 $u https://doi.org/10.1007/978-3-031-57679-9
950 $a Engineering (SpringerNature-11647)