1 code implementation • 19 Feb 2024 • Keyang Xuan, Li Yi, Fan Yang, Ruochen Wu, Yi R. Fung, Heng Ji
In this paper, we first investigate the potential of LVLM on multimodal misinformation detection.
no code implementations • 14 Oct 2022 • Praveen Ravirathinam, Rahul Ghosh, Ke Wang, Keyang Xuan, Ankush Khandelwal, Hilary Dugan, Paul Hanson, Vipin Kumar
Using this large unlabelled dataset, we first show how a spatiotemporal representation is better compared to just spatial or temporal representation.