Target Adaptive Context Aggregation for Video Scene Graph Generation
          Yao Teng1   Limin Wang1 B    Zhifeng Li2  Gangshan Wu1
       1
        State Key Laboratory for Novel Software Technology, Nanjing University, China
                   2
                    Tencent AI Lab, Shenzhen, China
     tengyao19980325@gmail.com, {lmwang, gswu}@nju.edu.cn, michaelzfli@tencent.com

             Abstract
  This paper deals with a challenging task of video scene
graph generation (VidSGG), which c ...