03753nam a22005295i 4500001001800000003000900018005001700027007001500044008004100059020003700100024003500137050001800172072001600190072002300206072001500229100008000244245009700324250001800421264006900439300005300508336002600561337002600587338003600613347002400649490003400673505035400707520153301061650002302594650002302617650002102640650003102661650004202692650004102734650002102775650004302796700008402839710003402923773002602957776003602983776003603019776003603055830004103091856004603132912001403178912001403192999001703206978-3-031-57679-9DE-He21320251030112702.0cr nn 008mamaa240801s2024    sz |    s    |||| 0|eng d  a97830315767999978-3-031-57679-97 a10.1007/978-3-031-57679-92doi 4aTK5101-5105.9 7aTJK2bicssc 7aTEC0410002bisacsh 7aTJK2thema1 aWu, Zuxuan.eauthor.4aut4http://id.loc.gov/vocabulary/relators/aut98165810aDeep Learning for Video Understandingh[electronic resource] /cby Zuxuan Wu, Yu-Gang Jiang.  a1st ed. 2024. 1aCham :bSpringer Nature Switzerland :bImprint: Springer,c2024.  aIX, 188 p. 99 illus. in color.bonline resource.  atextbtxt2rdacontent  acomputerbc2rdamedia  aonline resourcebcr2rdacarrier  atext filebPDF2rda1 aWireless Networks,x2366-14450 aIntroduction -- 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.  aThis 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. 0aTelecommunication. 0aSignal processing. 0aComputer vision. 0aMultimedia systems.96556914aCommunications Engineering, Networks.24aSignal, Speech and Image Processing.24aComputer Vision.24aMultimedia Information Systems.9655721 aJiang, Yu-Gang.eauthor.4aut4http://id.loc.gov/vocabulary/relators/aut9816592 aSpringerLink (Online service)0 tSpringer Nature eBook08iPrinted edition:z978303157678208iPrinted edition:z978303157680508iPrinted edition:z9783031576812 0aWireless Networks,x2366-144596749740uhttps://doi.org/10.1007/978-3-031-57679-9  aZDB-2-ENG  aZDB-2-SXE  c62107d62107