Search Results for author:
Found 2 papers, 1 papers with code
Divide and Conquer: Hybrid Pre-training for Person Search
To the best of our knowledge, this is the first work that investigates how to support full-task pre-training using sub-task data.
Grouped Adaptive Loss Weighting for Person Search
A straightforward solution is to manually assign different weights to different tasks, compensating for the diverse convergence rates.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
