Zeyad Khalifa

Papers

Total Citations

H-Index

About

Zeyad Khalifa is a rising researcher in computer vision and robotics, whose work centers on visual affordance understanding—the ability of machines to perceive how objects can be used or interacted with. His major contributions include the creation of a large-scale, multi-view RGBD visual affordance learning dataset, which provides rich, annotated data to train deep neural networks for recognizing object functionalities beyond mere physical attributes. This dataset, introduced in his 2023 paper, has already garnered 5 citations, underscoring its foundational role in the field. Khalifa further advanced the domain with a hierarchical transformer architecture designed for affordance understanding, leveraging his dataset to improve how robots interpret visual cues for intelligent interaction. This work, also from 2023, has received 3 citations, highlighting its impact on bridging perception and action. By addressing the gap between object recognition and practical utility, Khalifa’s research paves the way for more autonomous and context-aware robotic systems, making him a notable contributor to the intersection of computer vision and embodied AI.