SUPPLEMENTARY MATERIAL FOR THE ICIP PAPER: OBJECT-INFORMED STATE CLASSIFICATION

Object State Classification (OSC) is a critical task in computer vision, enabling systems to understand the functional state of objects (e.g., ``open'', ``closed''). In this work, we propose a novel end-to-end architecture for OSC that leverages the inherent relationship between object classification and state recognition. Our approach first classifies the object and then uses object-specific attention mechanisms to focus on relevant features for state classification. This two-stage design allows the model to effectively capture object-state dependencies while maintaining modularity and flexibility. We conduct an extensive ablation study to analyze the impact of key parameters, such as attention mechanisms and loss weighting, and evaluate our method against five baselines across four benchmark datasets. Experimental results demonstrate that our approach outperforms competing methods by a significant margin, achieving state-of-the-art performance.