In one embodiment, a system for setting frame priority according to priority levels includes a video encoder to encode a first video frame of a live video stream yielding an encoded first video frame having a first priority level, and a processor to read, from a memory, an estimate of a time delay, the time delay being a time for data in the live video stream to be transferred from a first device to a second device, and determine if the estimate of the time delay exceeds a pre-defined delay, and wherein if the estimate of the time delay exceeds the pre-defined delay, the video encoder is operative to encode a second video frame with a higher priority level than the first priority level, the second video frame being a most recent video frame to be presented from the live video stream for encoding after the first video frame. Related apparatus and methods are also described.

In one embodiment, a system for setting frame priority according to priority levels includes a video encoder to encode a first video frame of a live video stream yielding an encoded first video frame having a first priority level, and a processor to read, from a memory, an estimate of a time delay, the time delay being a time for data in the live video stream to be transferred from a first device to a second device, and determine if the estimate of the time delay exceeds a pre-defined delay, and wherein if the estimate of the time delay exceeds the pre-defined delay, the video encoder is operative to encode a second video frame with a higher priority level than the first priority level, the second video frame being a most recent video frame to be presented from the live video stream for encoding after the first video frame. Related apparatus and methods are also described.

A method for managing consumption of a device for processing multimedia content. The method includes the following acts executed on the processing device: receiving a request for processing a multimedia content; analyzing the request in order to extract from it at least one rendering quality of the content; obtaining a power supply state of the device; checking the match between the quality of the content and the power supply state of the device; on the basis of the results of the check, modifying a rendering quality for the content; and processing the multimedia content in order to render it in the quality.

A method for managing consumption of a device for processing multimedia content. The method includes the following acts executed on the processing device: receiving a request for processing a multimedia content; analyzing the request in order to extract from it at least one rendering quality of the content; obtaining a power supply state of the device; checking the match between the quality of the content and the power supply state of the device; on the basis of the results of the check, modifying a rendering quality for the content; and processing the multimedia content in order to render it in the quality.

A method and apparatus of line buffer reduction for context adaptive entropy processing are disclosed. The context formation for context adaptive entropy processing depends on block information associated with one or more neighboring blocks. When the neighboring block is on a different side of a region boundary from the current block, the block information is replaced by replacement block information to reduce or remove line buffer requirement for storing the block information of neighboring blocks on the other side of the region boundaries from the current block. The context adaptive entropy processing is CABAC encoding, CABAC decoding, CAVLC encoding, or CAVLC decoding.

A method and apparatus of line buffer reduction for context adaptive entropy processing are disclosed. The context formation for context adaptive entropy processing depends on block information associated with one or more neighboring blocks. When the neighboring block is on a different side of a region boundary from the current block, the block information is replaced by replacement block information to reduce or remove line buffer requirement for storing the block information of neighboring blocks on the other side of the region boundaries from the current block. The context adaptive entropy processing is CABAC encoding, CABAC decoding, CAVLC encoding, or CAVLC decoding.

Techniques for efficient coding of digital media data are presented. A resource controller component dynamically allocates computing resources between an estimator component and a coder component. The estimator component generates an initial motion estimation of a raw video frame of a sequence of raw video frames based on a previous raw video frame. The coder component encodes the previous raw video frame to generate a reconstructed video frame in parallel with the generation of the initial motion estimation. When the previous raw video frame is reconstructed, the coder component dynamically determines whether and/or how to refine the motion estimation to encode the raw video frame based on a predefined encoding criterion. In making that determination, the coder component selects and uses a mode(s) of motion estimation refinement from a plurality of available motion estimation refinement modes to encode the raw video frame.

Techniques for efficient coding of digital media data are presented. A resource controller component dynamically allocates computing resources between an estimator component and a coder component. The estimator component generates an initial motion estimation of a raw video frame of a sequence of raw video frames based on a previous raw video frame. The coder component encodes the previous raw video frame to generate a reconstructed video frame in parallel with the generation of the initial motion estimation. When the previous raw video frame is reconstructed, the coder component dynamically determines whether and/or how to refine the motion estimation to encode the raw video frame based on a predefined encoding criterion. In making that determination, the coder component selects and uses a mode(s) of motion estimation refinement from a plurality of available motion estimation refinement modes to encode the raw video frame.

A method of multi-rate neural image compression includes selecting encoding masks, based on a hyperparameter, and performing a convolution of a first plurality of weights of a first neural network and the selected encoding masks to obtain first masked weights. The method further includes encoding an input image to obtain an encoded representation, using the first masked weights, and encoding the obtained encoded representation to obtain a compressed representation.

Provided is an artificial intelligence (AI) decoding apparatus including a memory storing one or more instructions; and a processor configured to execute the one or more instructions to, when an image is input to a second DNN including a plurality of layers, obtain first result values based on an operation between the image and a first filter kernel and obtain second result values based on an operation between the image and a second filter kernel, from a first layer including the first and second filter kernels from among the plurality of layers, perform normalization by transforming the first result values into first values by using a first scale factor, and, perform normalization by transforming the second result values into second values by using a second scale factor, transform the first values and the second values into integer values included in a preset range.