Abstract: Systems and methods for generating a panoptic segmentation mask for an input image. The methods include receiving the input image comprising a plurality of pixels, generating a semantic mask and an instance mask from the input image, and combining the semantic mask and the instance mask to generate a panoptic mask for the input image. The semantic mask includes a single-channel mask that associates each pixel in the input image with a corresponding one of a plurality of labels. The instance mask includes a plurality of masks, where each of the plurality of masks identifies an instance of a countable object in the input image, and is associated with an indication of whether that instance of the countable object is hidden behind another object in the input image.

Abstract: Systems and methods for generating a panoptic segmentation mask for an input image. The methods include receiving the input image comprising a plurality of pixels, generating a semantic mask and an instance mask from the input image, and combining the semantic mask and the instance mask to generate a panoptic mask for the input image. The semantic mask includes a single-channel mask that associates each pixel in the input image with a corresponding one of a plurality of labels. The instance mask includes a plurality of masks, where each of the plurality of masks identifies an instance of a countable object in the input image, and is associated with an indication of whether that instance of the countable object is hidden behind another object in the input image.

Abstract: Systems and methods are provided to provide enhanced social networking to users of remote computing devices. Users of the disclosed system are able to interact with other participants in real-time and in relation to experiencing live or recorded media content. The system receives audio data that is captured by the user's device, wherein the audio data includes a processed or unprocessed audio sample of the media content being viewed by the user. The audio sample is compared to a database containing audio samples from a number of media programs to determine whether a match exists. If a match is found, the system determines other participants who are, at the same time, viewing the matched media program and establishes a connection between each of them. The connection enables participants to exchange real-time messages, participate in polls, and receive offers.

Abstract: A system and method are described for processing transaction instructions without human intervention. In one embodiment, a voice interpreter receives transaction information in the form of voice utterances, processes that information and transmits it to a business application server, which compiles the processed information and generates transaction instructions based on the compiled information. The business application server transmits the transaction instructions to an enterprise system via a connector manager that integrates the enterprise system with the business application server. At least one housing encloses the voice interpreter, the business application server and the hardware platform that supports the connector manager.