Sanjib Kumar Swain

TE-CUME: Uncertainty-Aware Tri-Modal Video Retrieval Representation Learning

UAT-InfoNCE is proposed, a precision-weighted contrastive objective that adaptively modulates gradient contributions by the model’s own confidence, together with pairwise cross-modal disagreement terms that serve as zero-shot diagnostics for broadcast failure modes such as A/V desynchronisation, dubbed content, and adv...