GenEARL: A Training-Free Generative Framework for Multimodal Event Argument Role Labeling

arXiv:2404.04763v1 Announce Type: new
Abstract: Multimodal event argument role labeling (EARL), a task that assigns a role for each event participant (object) in an image is a complex challenge. It requires reasoning over the entire image, the depicted event, and the interactions between various objects participating in the event. Existing models heavily rely on high-quality event-annotated training data to understand the event semantics and structures, and they fail to generalize to new event types and domains. In this paper, we …

abstract arxiv challenge cs.ai cs.cv event framework free generative image interactions labeling multimodal object objects reasoning role training type