Egocentric visual scene description based on human-object interaction and deep spatial relations among objects

Visual Scene interpretation is one of the major areas of research in the recent past. Recognition of human object interaction is a fundamental step towards understanding visual scenes. Videos can be described via a variety of human-object interaction scenarios such as when both human and object are static (static-static), one is static while other is dynamic (static-dynamic) and both are dynamic (dynamic-dynamic). This paper presents a unified framework for the explanation of these interactions between humans and a variety of objects using deep learning as a pivot methodology. Human-object interaction is extracted through native machine learning techniques, while spatial relations are captured by training a model through convolution neural network. We also address the recognition of human posture in detail to provide egocentric visual description. After extracting visual features, sequential minimal optimization is employed for training our model. Extracted inter-action, spatial relations and posture information are fed into natural language generation module along with interacting object label to generate scene understanding. Evaluation of the proposed framework is done for two state of the art datasets i.e., MSCOCO and MSR3D Daily activity dataset; where achieved results are 78 and 91.16% accurate, respectively.