Joint learning of video scene detection and annotation via multi-modal adaptive context network

Yifei Xu, Litong Pan, Weiguang Sang, Hailun Luo, Li Li, Pingping Wei, Li Zhu

Abstract: Highlights•Scene detection and annotation are solved from window view to avoid propagation errors.•Our method jointly learns scene detection and annotation.•Our method outperforms other methods on two public datasets.