Hybrid Deep Learning Vision-based Models for Human Object Interaction Detection by Knowledge Distillation

People hope that computers can be in constant intelligence development. Just like humans, they ”see” the world and ”recognize” a visual event. We propose an approach based on computer vision methods to recognize Human-Object interaction(HOI). The technique stands aggregating significant contextual features interactions scene recognition. design branch architecture consisting of main for HOI detection supplementary explore deep learning models through knowledge distillation method Cross Branch Integration mechanism encoding into graph neural network architecture. construct merge between high-level context information. When trained collaboratively, those allow computing efficiency, strong knowledge.