文献类型：期刊文献

英文题名：Improved Lightweight Multi-Target Recognition Model for Live Streaming Scenes

作者：Li, Zongwei[1];Qiao, Kai[1];Chen, Jianing[1];Li, Zhenyu[2];Zhang, Yanhui[3]

机构：[1]Shanghai Inst Technol, Sch Econ & Management, Shanghai 200235, Peoples R China;[2]Shanghai Univ, Sch Cultural Heritage & Informat Management, Shanghai 200444, Peoples R China;[3]East China Univ Sci & Technol, Sch Business, Shanghai 200237, Peoples R China

年份：2023

卷号：13

期号：18

外文期刊名：APPLIED SCIENCES-BASEL

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001138027600001)】；

基金：This research was funded by the National Natural Science Foundation of China, Study on the mechanism and spatial and temporal effects of international learning on the internationalization speed of manufacturing enterprises, grant number 71974130.

语种：英文

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

摘要：Nowadays, the commercial potential of live e-commerce is being continuously explored, and machine vision algorithms are gradually attracting the attention of marketers and researchers. During live streaming, the visuals can be effectively captured by algorithms, thereby providing additional data support. This paper aims to consider the diversity of live streaming devices and proposes an extremely lightweight and high-precision model to meet different requirements in live streaming scenarios. Building upon yolov5s, we incorporate the MobileNetV3 module and the CA attention mechanism to optimize the model. Furthermore, we construct a multi-object dataset specific to live streaming scenarios, including anchor facial expressions and commodities. A series of experiments have demonstrated that our model realized a 0.4% improvement in accuracy compared to the original model, while reducing its weight to 10.52%.