Open-Vocabulary Video Visual Relationship Detection
🎥 Demo
This demo showcases our end to end model across various open-vocabulary scenarios.
📢 News
Nov 2025 We introduced VaM-VidVRD, the first multi-modal benchmark for Open-vocabulary Video Visual Relationship Detection featuring synchronized audio, text, and 3D data, in our paper "Multi-modal Open-vocabulary Video Visual Relationship Detection".
Apr 2025 Our paper "METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection" was accepted by IJCAI 2025.
Apr 2025 Our paper "End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting" was accepted by IEEE TPAMI.
Dec 2023 Our paper "Multi-Modal Prompting for Open-Vocabulary Video Visual Relationship Detection" was accepted by AAAI 2024.