Chen, T.-W.T.-W.ChenChen, Y.-L.Y.-L.ChenCheng, T.-Y.T.-Y.ChengTang, C.-S.C.-S.TangTsung, P.-K.P.-K.TsungChuang, T.-D.T.-D.ChuangLIANG-GEE CHENSHAO-YI CHIEN2018-09-102018-09-10201001936530https://www.scopus.com/inward/record.uri?eid=2-s2.0-77952184606&doi=10.1109%2fISSCC.2010.5433887&partnerID=40&md5=bfa8c9926bca7d521848fa3086b82af6http://scholars.lib.ntu.edu.tw/handle/123456789/358152Advances in semiconductors and developments in machine learning [1] have led to versatile multimedia applications with semantic processing abilities. Realtime applications, such as face detection, facial-expression recognition, scene analysis [2] and object recognition [3], have become indispensable functionality for Consumer Electronic (CE) products. To deal with complicated video-processing algorithms for multimedia content analysis, many powerful processors have been reported [2-5]. Although these processors can speed up video-processing tasks with massively parallel processing elements, they only focus on the feature-extraction parts, and there is no specialized hardware to support different kinds of advanced machine-learning algorithms, which require extensive computations. In this paper, a Semantic Analysis SoC (SASoC) that accelerates video processing and machine learning simultaneously, is developed to meet the demands of the near future. ©2010 IEEE.[SDGs]SDG7Expression recognition; Face Detection; Machine learning algorithms; Machine-learning; Massively parallel processing; Multimedia applications; Multimedia content analysis; Multimedia semantics; Real-time application; Scene analysis; Semantic analysis; Semantic processing; Specialized hardware; Speed-ups; Video processing; Video-processing algorithms; Face recognition; Feature extraction; Learning systems; Semantics; Learning algorithmsconference paper10.1109/ISSCC.2010.54338872-s2.0-77952184606