AI RESEARCH
Ego-Grounding for Personalized Question-Answering in Egocentric Videos
arXiv CS.CV
•
ArXi:2604.01966v1 Announce Type: new We present the first systematic analysis of multimodal large language models (MLLMs) in personalized question-answering requiring ego-grounding - the ability to understand the camera-wearer in egocentric videos. To this end, we