1 code implementation • 2 May 2022 • Ekim Yurtsever, Emeç Erçelik, MingYu Liu, Zhijie Yang, Hanzhen Zhang, Pınar Topçam, Maximilian Listl, Yılmaz Kaan Çaylı, Alois Knoll
Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a supervised 3D detection head.
1 code implementation • 25 Apr 2021 • Emeç Erçelik, Ekim Yurtsever, Alois Knoll
Furthermore, ablation studies reinforce that the subject of improvement is temporal fusion and show the effects of different placements of TFM in the object detection pipeline.