where is cross‑entropy for the primary classification, MSE encourages similar gating patterns for correlated modalities, and Θ denotes all trainable parameters. Hyper‑parameters are set to λ_cls = 1.0 , λ_att = 0.1 , λ_reg = 5 × 10⁻⁴ .
Proceedings of the 2026 International Conference on Computer Vision & Pattern Recognition (ICCV‑2026) fc2 3292343