文献类型：期刊文献

英文题名：Research on efficient feature extraction: Improving YOLOv5 backbone for facial expression detection in live streaming scenes

作者：Li, Zongwei[1];Song, Jia[1];Qiao, Kai[1];Li, Chenghai[2];Zhang, Yanhui[3];Li, Zhenyu[1]

机构：[1]Shanghai Inst Technol, Sch Econ & Management, Shanghai, Peoples R China;[2]Anhui Univ Technol, Sch Management Sci & Engn, Maanshan, Peoples R China;[3]East China Univ Sci & Technol, Business Sch, Shanghai, Peoples R China

年份：2022

卷号：16

外文期刊名：FRONTIERS IN COMPUTATIONAL NEUROSCIENCE

收录：;EI(收录号：20223512647054);WOS:【SCI-EXPANDED(收录号:WOS:000844006500001)】；

基金：Funding This research was supported by the National Natural Science Foundation of China (No. 71974130) and the National Social Science Fund of China (No. 18BGL093).

语种：英文

外文关键词：model optimization; object detection; attention mechanism; cascade classifier; live streaming

摘要：Facial expressions, whether simple or complex, convey pheromones that can affect others. Plentiful sensory input delivered by marketing anchors' facial expressions to audiences can stimulate consumers' identification and influence decision-making, especially in live streaming media marketing. This paper proposes an efficient feature extraction network based on the YOLOv5 model for detecting anchors' facial expressions. First, a two-step cascade classifier and recycler is established to filter invalid video frames to generate a facial expression dataset of anchors. Second, GhostNet and coordinate attention are fused in YOLOv5 to eliminate latency and improve accuracy. YOLOv5 modified with the proposed efficient feature extraction structure outperforms the original YOLOv5 on our self-built dataset in both speed and accuracy.