CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Eyiokur, Fevziye Irem, Yaman, Dogucan, Ekenel, Hazım Kemal, Waibel, Alexander
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.21888