AI RESEARCH
SHOE: Semantic HOI Open-Vocabulary Evaluation Metric
arXiv CS.CV
•
ArXi:2604.01586v1 Announce Type: new Open-vocabulary human-object interaction (HOI) detection is a step towards building scalable systems that generalize to unseen interactions in real-world scenarios and grounded multimodal systems that reason about human-object relationships. However, standard evaluation metrics, such as mean Average Precision (mAP), treat HOI classes as discrete categorical labels and fail to credit semantically valid but lexically different predictions (e.g., "lean on couch" vs.