Accurate and reliable localization of mobile robots in complex indoor environments presents significant challenges for visual-inertial odometry (VIO) systems. To address the limitations of conventional approaches—including their dependency on precise calibration, susceptibility to dynamic disturbances, and inadequate cross-modal feature integration—this paper proposes a deep learning-enhanced adaptive VIO framework. Our solution, the CAT-SC-VIO algorithm, introduces three key innovations: (1) a self-calibrating sensor adaptation module, (2) dynamic scene robustness enhancement, and (3) a novel cross-modal feature fusion architecture. Comprehensive evaluations demonstrate that the proposed system achieves a 17.8% improvement in translational accuracy over the baseline CAT-VIO method while maintaining exceptional robustness against sensor data degradation. The framework particularly excels in handling challenging scenarios involving occlusions, illumination variations, and moving objects in indoor environments.