Search Results for author:
Found 3 papers, 2 papers with code
Local Learning on Transformers via Feature Reconstruction
In this paper, we propose a new mechanism for each local module, where instead of reconstructing the entire image, we reconstruct its input features, generated from previous modules.
Fine-Grained Re-Identification
FGReID achieves state-of-the-art (SOTA) on MARS, iLIDS-VID, and PRID-2011 video person ReID benchmarks.
Ranked #2 on
Person Re-Identification
on PRID2011
Video Person Re-ID: Fantastic Techniques and Where to Find Them
The ability to identify the same person from multiple camera views without the explicit use of facial recognition is receiving commercial and academic interest.
Ranked #1 on
Person Re-Identification
on MARS
