Search Results for author: Daniel Cores

Found 2 papers, 1 papers with code

Short-term anchor linking and long-term self-guided attention for video object detection

1 code implementation18 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.

Object object-detection +1

Spatio-temporal Tubelet Feature Aggregation and Object Linking in Videos

no code implementations1 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.

Object object-detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.