Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition

Multimodal Intention Recognition (MIR) plays a critical role in applications such as intelligent assistants, service robots, and autonomous systems. However, in realworld scenarios, different modalities often vary significantly in informativeness, reliability, and noise levels. This leads to modality imbalance, where models tend to over-rely on dominant modalities, thereby limiting generalization and robustness. Although existing methods address this issue at either the sample or model level, they generally fail to account for its multi-level nature. To address this, we propose Adaptive Re-calibration Learning (ARL), a novel dual-path framework that models modality importance from both sample-wise and structural perspectives. ARL incorporates two key mechanisms: Contribution-Inverse Sample Calibration (CISC), which dynamically masks overly dominant modalities at the sample level to encourage attention to underutilized ones; and Weighted Encoder Calibration (WEC), which adjusts encoder weights based on global modality contributions to prevent overfitting. Experimental results on multiple MIR benchmarks demonstrate that ARL significantly outperforms existing methods in both accuracy and robustness, particularly under noisy or modality-degraded conditions.