B. Ankayarkanni, D. Usha Nandini, P. Sangeetha, R. Aroul Canessane, and Mary Livinsa Z., “MULTI-MODAL TRANSFORMER ARCHITECTURE WITH CROSS-ATTENTION FUSION FOR ROBUST AUDIO-VISUAL SENTIMENT ANALYSIS”, IJCISIM, vol. 18, no. 11s, pp. 1101–1112, Jul. 2026.