Sanjay Nair has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
Abstract: An enhanced encoder system generates residual bitstreams representing additional image information that can be used by an image enhancement system to improve a low quality image. The enhanced encoder system upsamples a low quality image and compares the upsampled image to a true high quality image to determine image inaccuracies that arise due to the upsampling process. The enhanced encoder system encodes the information describing the image inaccuracies using a trained encoder model as the residual bitstream. The image enhancement system upsamples the same low quality image to obtain a prediction of a high quality image that can include image inaccuracies. Given the residual bitstream, the image enhancement system decodes the residual bitstream using a trained decoder model and uses the additional image information to improve the predicted high quality image. The image enhancement system can provide an improved, high quality image for display.
Abstract: The compression system trains a machine-learned encoder and decoder through an autoencoder architecture. The encoder can be deployed by a sender system to encode content for transmission to a receiver system, and the decoder can be deployed by the receiver system to decode the encoded content and reconstruct the original content. The encoder is coupled to receive content and output a tensor as a compact representation of the content. The content may be, for example, images, videos, or text. The decoder is coupled to receive a tensor representing content and output a reconstructed version of the content. The compression system trains the autoencoder with a discriminator to reduce compression artifacts in the reconstructed content. The discriminator is coupled to receive one or more input content, and output a discrimination prediction that discriminates whether the input content is the original or reconstructed version of the content.
Abstract: A compression system trains a machine-learned encoder and decoder. The encoder can be deployed by a sender system to encode content for transmission to a receiver system, and the decoder can be deployed by the receiver system to decode the encoded content and reconstruct the original content. The encoder receives content and generates a tensor as a compact representation of the content. The content may be, for example, images, videos, or text. The decoder receives a tensor and generates a reconstructed version of the content. In one embodiment, the compression system trains one or more encoding components such that the encoder can adaptively encode different degrees of information for regions in the content that are associated with characteristic objects, such as human faces, texts, or buildings.
Abstract: A system and method for loading data into column-partitioned database tables. The system and method incorporate a mechanism for buffering data extracted from the rows of a source table in column-oriented fashion within an in-buffer memory, enabling an efficient bulk-write of large arrays of values from the buffer into column-partitioned database tables. The system and method may also include optimizations for grouping columns according to data types and altering the order in which columns are inserted into the database tables.
Abstract: During a training course, a user may select a practice session and practice using the application that is the basis of the course. A practice link is provided to the user which, when selected, launches an instance of the application. A template may also be loaded by the application that is based on the particular training session. The template may include a practice document and information relating to training content. When the practice session is initiated, a training window is displayed next to the application window that provides the user with training content for the practice session. The training content helps to guide the user through the practice session. After the user has finished practicing within the application, they may return to the point in the training course before the practice session was initiated. If desired, the user can choose to return to the practice session at any time during the training course.
October 28, 2004
May 18, 2006
Vlada Breiburg, Sanjay Nair, Penny Parks, Tracy Ferrier, Jessica Reading, David Ludwig