Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language Models
Yvon Apedo, Martyna Poreba, Michal Szczepanski +1
Vision-Language Models (VLMs) have revolutionized multi-modal learning by jointly processing visual and textual information. Yet, they face significant challenges due to the high c…
cs.CV2024
DH-PTAM: A Deep Hybrid Stereo Events-Frames Parallel Tracking And Mapping System
Abanob Soliman, Fabien Bonardi, Désiré Sidibé +1
This paper presents a robust approach for a visual parallel tracking and mapping (PTAM) system that excels in challenging environments. Our proposed method combines the strengths o…