1 code implementation • 18 Apr 2021 • Daniel Cores, Víctor M Brea, Manuel Mucientes
This module takes advantage of geometrical features in the long-term for the first time in the video object detection domain.
Ranked #1 on Video Object Detection on USC-GRAD-STDdb
no code implementations • 1 Apr 2020 • Daniel Cores, Víctor M. Brea, Manuel Mucientes
Then, we aggregate RoI pooled deep features through the tubelet using a temporal pooling operator that summarizes the information with a fixed size output independent of the number of input frames.