Search Results for author:
Found 2 papers, 1 papers with code
Short-term anchor linking and long-term self-guided attention for video object detection
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
Spatio-temporal Tubelet Feature Aggregation and Object Linking in Videos
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
