Human Object Interaction: A Survey on Models and Their Key Challenges and Potential Applications in Future Fields

Human-object interaction is a crucial task in computer vision that involves accurately identifying and recognizing human-object interactions. This survey paper presents an overview of various approaches and methodologies for Human-Object interaction using Deep Learning. The surveyed papers explore different techniques, including deep learning, wearable sensors, pressure sensors, and graph neural networks, to address the challenges in understanding and interpreting human-object interactions. This survey paper discusses the data sets used in these research papers and proposed models. It also identifies key challenges in human-object detection, such as ambiguity in interaction interpretation and noisy or incomplete sensor data. In conclusion, this survey paper provides insights into the advancements in human-object detection research, showcasing various methodologies and technologies employed in recent years. It contributes to the existing body of knowledge and serves as a valuable resource for researchers and practitioners working in the field of human-object interaction.