US Patent 11361489 Dense captioning with joint interference and visual context

A dense captioning system and method is provided for analyzing an image to generate proposed bounding regions for a plurality of visual concepts within the image, generating a region feature for each proposed bounding region to generate a plurality of region features of the image, and determining a context feature for the image using a proposed bounding region that is a largest in size of the proposed bounding regions. For each region feature of the plurality of region features of the image, the dense captioning system and method further provides for analyzing the region feature to determine for the region feature a detection score that indicates a likelihood that the region feature comprises an actual object, and generating a caption for a visual concept in the image using the region feature and the context feature when a detection score is above a specified threshold value.