Human-object interaction detection

Abstract

Human-object interaction (HOI) detection has been a trending topic in computer vision and image understanding domain. The state-of-the-art algorithms perform high accuracy on popular benchmark data sets. However, some of them lose the adaptability and significance of the general images, leading to the misalignment with the original motivation of HOI detection. Therefore, in this dissertation, the refined framework is introduced to directly conduct detection on usual images taking advantage of the current state-of-the-art, achieving satisfying performance close to that on benchmarks. Experiments and ablation studies are illustrated and analyzed to provide guidance and empirical information for practitioners to better apply the algorithm in certain scenes. In the end, some potential solutions for improvements are described for reference to future researches.