Swarang Joshi

Swarang Joshi

CS + Computational Linguistics @ IIIT Hyderabad. NLP, VLMs, and AI Alignment.

Hyderabad, India · IIIT Hyderabad

SceneGraMMi: Scene Graph-boosted Hybrid-fusion for Multi-Modal Misinformation Veracity Prediction

Published in arXiv:2410.15517, 2024

SceneGraMMi introduces a hybrid-fusion architecture that leverages scene graphs to boost multi-modal misinformation veracity prediction, combining visual and textual evidence more effectively than late- or early-fusion baselines.

Read the paper on arXiv

Recommended citation: S. Joshi*, S. Mavani*, et al. (2024). "SceneGraMMi: Scene Graph-boosted Hybrid-fusion for Multi-Modal Misinformation Veracity Prediction." arXiv:2410.15517.
Download Paper