Abstract: An image processing system has a memory storing a video depicting a multi-entity event, a trained reinforcement learning policy and a plurality of domain specific language functions. A graph formation module computes a representation of the video as a graph of nodes connected by edges. A trained machine learning system recognizes entities depicted in the video and recognizes attributes of the entities. Labels are added to the nodes of the graph according to the recognized entities and attributes. The trained machine learning system computes a predicted multi-entity event depicted in the video. For individual ones of the edges of the graph, select a domain specific language function from the plurality of domain specific language functions and assign it to the edge, the selection being made at least according to the reinforcement learning policy. An explanation is formed from the domain specific language functions.

Abstract: An image processing system has a memory storing a video depicting a multi-entity event, a trained reinforcement teaming policy and a plurality of domain specific language functions. A graph formation module computes a representation of the video as a graph of nodes connected by edges. A trained machine learning system recognizes entities depicted in the video and recognizes attributes of the entities. Labels are added to the nodes of the graph according to the recognized entities and attributes. The trained machine learning system computes a predicted multi-entity event depicted in the video. For individual ones of the edges of the graph, select a domain specific language function from the plurality of domain specific language functions and assign it to the edge, the selection being made at least according to the reinforcement learning policy. An explanation is formed from the domain specific language functions.

Abstract: The present invention relates to a computer-implemented method for 3D model database retrieval using a 3D model as a search input. The method converts the search input into a plurality of orthogonal 2D views; generates a signature for each 2D view; and then searches the 3D model database by comparing the plurality of generated signatures with signatures generated for each 3D model in the database. The signatures are compared with one another across at least two orthogonal rotations. A system for 3D model retrieval and a method and system for creating 3D model database are also disclosed.

Abstract: The present invention relates to a computer-implemented method for 3D model database retrieval using a 3D model as a search input. The method converts the search input into a plurality of orthogonal 2D views; generates a signature for each 2D view; and then searches the 3D model database by comparing the plurality of generated signatures with signatures generated for each 3D model in the database. The signatures are compared with one another across at least two orthogonal rotations. A system for 3D model retrieval and a method and system for creating 3D model database are also disclosed.