[ Patent Deposit – Samsung ] Video Recognition Method Able to Encode Time and Space Relationships of Concepts Using Contextual Information
The proposed invention aims to encode contextual information for video analysis and understanding, encoding spatial and temporal relations of objects and the main agent in a scene. The main target application of the invention is the recognition of human activity. The coding of these spatial and temporal relationships can be crucial in distinguishing different categories of human activities and can be important in helping to discriminate between different video categories for video classification, retrieval, categorization, and other video analysis applications.
Laboratory inventors: Jesimon Barreto Santos, Victor Hugo Cunha de Melo, William Robson Schwartz.
This patent is a result of the project that was promoted by Samsung.
The deposit took place on 21/11/2019 at INPI