03528nam 2200865z- 450 991061946580332120231214133638.03-0365-5200-6(CKB)5670000000391616(oapen)https://directory.doabooks.org/handle/20.500.12854/93210(EXLCZ)99567000000039161620202210d2022 |y 0engurmn|---annantxtrdacontentcrdamediacrrdacarrierDeep Learning-Based Action RecognitionMDPI - Multidisciplinary Digital Publishing Institute20221 electronic resource (240 p.)3-0365-5199-9 The classification of human action or behavior patterns is very important for analyzing situations in the field and maintaining social safety. This book focuses on recent research findings on recognizing human action patterns. Technology for the recognition of human action pattern includes the processing technology of human behavior data for learning, technology of expressing feature values ​​of images, technology of extracting spatiotemporal information of images, technology of recognizing human posture, and technology of gesture recognition. Research on these technologies has recently been conducted using general deep learning network modeling of artificial intelligence technology, and excellent research results have been included in this edition.Technology: general issuesbicsscHistory of engineering & technologybicsschuman action recognitiongraph convolutionhigh-order featurespatio-temporal featurefeature fusiondynamic gesture recognitionmulti-modalities networkclass regularization3D-CNNspatiotemporal activationsclass-specific featuresDynamic Hand Gesture Recognitionhuman-computer interactionhand shape featurespose estimationstacked hourglass networkdeep learningconvolutional receptive fieldhand gesture recognitionhuman-machine interfaceartificial intelligencefeedforward neural networksspatio-temporal image formationhuman activity recognitionfusion strategiestransfer learningactivity recognitiondata augmentationmulti-person pose estimationpartitioned centerpose networkpartition pose representationcontinuous hand gesture recognitiongesture spottinggesture classificationmulti-modal features3D skeletalCNNspatiotemporal featureembedded systemreal-timeaction recognitionLong Short-Term Memoryspatio-temporal differentialTechnology: general issuesHistory of engineering & technologyLee Hyo Jongedt1320374Lee Hyo JongothBOOK9910619465803321Deep Learning-Based Action Recognition3034204UNINA