US Patent Issued to SAI GROUP on July 28 for "Multimodal video-language artificial intelligence framework for surveillance environments" (Indian, British Inventors)

ALEXANDRIA, Va., July 28 -- United States Patent no. 12,694,682, issued on July 28, was assigned to SAI GROUP Ltd. (London).

"Multimodal video-language artificial intelligence framework for surveillance environments" was invented by Abhishek Singh (Bareilly, India), Abhijit Sanyal (West Bengal, India) and Somnath Sinha (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and systems monitor activity in a surveillance environment. A three-dimensional convolutional neural network is used to extract spatiotemporal features from video frames. A connector module projects the spatiotemporal feature embeddings into a multimodal latent space. A language model analyzes the multimodal embeddings to output st...