Impact of Missing Data Imputation Strategies on Multimodal Fusion versus Unimodal Baseline Robustness

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion methods and VLMs in the field of robot vision. For semantic scene understanding tasks, we categorize fusion approaches into encoder-decoder frameworks, attention-based architectures, and graph neural networks. Meanwhile, we also analyze the architectural characteristics and practical implementations of these fusion strategies in key tasks such as simultaneous l

Research goal: What is the impact of different missing data imputation strategies on the robustness of multimodal fusion models versus unimodal baselines?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.3/10.