Kao P.-YLei Y.-JChang C.-HChen C.-SLee M.-SYI-PING HUNG2023-06-092023-06-09202010514651https://www.scopus.com/inward/record.uri?eid=2-s2.0-85110484950&doi=10.1109%2fICPR48806.2021.9412330&partnerID=40&md5=32c36c338722fa087a1d459b8057a86bhttps://scholars.lib.ntu.edu.tw/handle/123456789/632255First-person-view (FPV) cameras are finding wide use in daily life to record activities and sports. In this paper, we propose a succinct and robust 3D convolutional neural network (CNN) architecture accompanied with an ensemble-learning network for activity recognition with FPV videos. The proposed 3D CNN is trained on low-resolution (32 ? 32) sparse optical flows using FPV video datasets consisting of daily activities. According to the experimental results, our network achieves an average accuracy of 90%. © 2020 IEEE[SDGs]SDG11Cameras; Convolutional neural networks; Optical flows; Activity recognition; Daily activity; Daily lives; Ensemble learning; First person; Low resolution; Video datasets; Pattern recognitionconference paper10.1109/ICPR48806.2021.94123302-s2.0-85110484950