Deep Learning-based Gesture Recognition and In-Sensor Motion Perception Systems, Wearable Artificial Intelligence and Aesthetic Self-Monitoring Devices, and Beauty Filter and Visual Sentiment Algorithms for Problematic Body Image
Deep Learning-based Gesture Recognition and In-Sensor Motion Perception Systems, Wearable Artificial Intelligence and Aesthetic Self-Monitoring Devices, and Beauty Filter and Visual Sentiment Algorithms for Problematic Body Image

Summary/Abstract: The aim of this systematic review is to synthesize and analyze artificial intelligence-generated hyper-realistic body-inclusive avatars, augmented reality makeup try-on and facial emotion recognition technologies, and emotion analytics and visual sentiment algorithms. With increasing evidence of scene representation and classification tools, virtual beauty try-ons, and speech emotion recognition and neurobiological computation technologies, there is an essential demand for comprehending whether 3D object recognition and path planning tools, synthetic image data augmentation, and virtual makeup try-ons are instrumental in toxic body image ideals. A quantitative literature review of ProQuest, Scopus, and the Web of Science was carried out throughout July 2024, with search terms including “problematic body image” + “deep learning-based gesture recognition and in-sensor motion perception systems,” “wearable artificial intelligence and aesthetic self-monitoring devices,” and “beauty filter and visual sentiment algorithms.” As research published between 2017 and 2024 was inspected, only 174 articles satisfied the eligibility criteria, and 31 mainly empirical sources were selected. Data visualization tools: Dimensions (bibliometric mapping) and VOSviewer (layout algorithms). Reporting quality assessment tool: PRISMA. Methodological quality assessment tools include: Citationchaser, DistillerSR, METAGEAR package for R, Nested Knowledge, SluRp, and SWIFT-Active Screener.

• Details
• Contents