D. MG, V. S. Multi-Modal Deepfake Detection via Spatial, Temporal, and Audio-Visual Fusion with Vision Transformers. J. Soft Comput. Paradigm [Internet]. 2026 Jun. 30 [cited 2026 Nov. 1];8(3):219-38. Available from: https://irojournals.com/jscp/article/view/2297