Abstract: Methods and systems are provided for implementing preprocessing operations and augmentation operations upon image datasets transformed to frequency domain representations, including decoding images of an image dataset to generate a frequency domain representation of the image dataset; performing a resizing operation based on resizing factors on the image dataset in a frequency domain representation; performing a reshaping operation based on reshaping factors on the image dataset in a frequency domain representation; and performing a cropping operation on the image dataset in a frequency domain representation. The methods and systems may further include performing an augmentation operation on the image dataset in a frequency domain representation. Methods and systems of the present disclosure may free learning models from computational overhead caused by transforming image datasets into frequency domain representations.

Abstract: A neural network, trained on a plurality of random size data samples, can receive a plurality of inference data samples including samples of different sizes. The neural network can generate feature maps of the plurality of inference data samples. Pooling can be utilized to generate feature maps having a fixed size. The fixed size feature maps can be utilized to generate an indication of a class for each of the plurality of inference data samples.

Abstract: In one embodiment, an apparatus comprises processing circuitry to: receive, via a communication interface, a compressed video stream captured by a camera, wherein the compressed video stream comprises: a first compressed frame; and a second compressed frame, wherein the second compressed frame is compressed based at least in part on the first compressed frame, and wherein the second compressed frame comprises a plurality of motion vectors; decompress the first compressed frame into a first decompressed frame; perform pixel-domain object detection to detect an object at a first position in the first decompressed frame; and perform compressed-domain object detection to detect the object at a second position in the second compressed frame, wherein the object is detected at the second position in the second compressed frame based on: the first position of the object in the first decompressed frame; and the plurality of motion vectors from the second compressed frame.

Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store visual data associated with a visual representation captured by one or more sensors. The processor is to: obtain the visual data associated with the visual representation captured by the one or more sensors, wherein the visual data comprises uncompressed visual data or compressed visual data; process the visual data using a convolutional neural network (CNN), wherein the CNN comprises a plurality of layers, wherein the plurality of layers comprises a plurality of filters, and wherein the plurality of filters comprises one or more pixel-domain filters to perform processing associated with uncompressed data and one or more compressed-domain filters to perform processing associated with compressed data; and classify the visual data based on an output of the CNN.

Abstract: The present disclosure relates to a system and method for image processing. In some embodiments, an exemplary image processing method includes: receiving an image; compressing, with a compression neural network, the image into a compressed representation; and performing, with a processing neural network, a machine learning task on the compressed representation to generate a learning result. The compression neural network and the processing neural network are jointly trained.

Abstract: In one embodiment, an apparatus comprises a storage device and a processor. The storage device may store a plurality of compressed images comprising one or more compressed master images and one or more compressed slave images.

Abstract: Methods and apparatuses for video transcoding based on spatial or temporal importance include: in response to receiving an encoded video bitstream, decoding a picture from the encoded video bitstream; determining a first level of spatial importance for a first region of a background of the picture based on an image segmentation technique; applying to the first region a first resolution-enhancement technique associated with the first level of spatial importance for increasing resolution of the first region by a scaling factor, wherein the first resolution-enhancement technique is selected from a set of resolution-enhancement techniques having different computational complexity levels; and encoding the first region using a video coding standard.

Abstract: In one embodiment, an apparatus comprises a communication interface and a processor. The communication interface is to communicate with a plurality of devices. The processor is to: receive compressed data from a first device, wherein the compressed data is associated with visual data captured by sensor(s); perform a current stage of processing on the compressed data using a current CNN, wherein the current stage of processing corresponds to one of a plurality of processing stages associated with the visual data, and wherein the current CNN corresponds to one of a plurality of CNNs associated with the plurality of processing stages; obtain an output associated with the current stage of processing; determine, based on the output, whether processing associated with the visual data is complete; if the processing is complete, output a result associated with the visual data; if the processing is incomplete, transmit the compressed data to a second device.

Abstract: The present disclosure relates to a method and an apparatus for map reduce. In some embodiments, an exemplary processing unit includes: a 2-dimensional (2D) processing element (PE) array comprising a plurality of PEs, each PE comprising a first input and a second input, the first inputs of the PEs in a linear array in a first dimension of the PE array being connected in series and the second inputs of the PEs in a linear array in a second dimension of the PE array being connected in parallel, each PE being configured to perform an operation on data from the first input or second input; and a plurality of reduce tree units, each reduce tree unit being coupled with the PEs in a linear array in the first dimension or the second dimension of the PE array and configured to perform a first reduction operation.

Abstract: Scene aware video content encoding techniques can determine if video content is a given content type and is one of one or more given titles that include one or more given scenes. The one or more given scenes of the video content of the given type and given one of the titles can be encoded using corresponding scenes specific encoding parameter values, and the non-given scenes can be encoded using one or more general encoding parameter values. The one or more given titles can be selected based on a rate of streaming of various video content titles of the given type.

Abstract: Example task assignment methods disclosed herein for video analytics processing in a cloud computing environment include determining a graph, such as a directed acyclic graph, including nodes and edges to represent a plurality of video sources, a cloud computing platform, and a plurality of intermediate network devices in the cloud computing environment. Disclosed example task assignment methods also include specifying task orderings for respective sequences of video analytics processing tasks to be executed in the cloud computing environment on respective video source data generated by respective ones of the video sources.

Abstract: A method for of encoding an application screen comprises partitioning graphic data into a plurality of graphic layers and classifying each of the plurality of graphic layers as either a screen content (SC) or a non-screen content (non-SC) layer. The method further comprises classifying each of the plurality of graphic layers as either a screen content (SC) or a non-screen content (non-SC) layer. Further, the method comprises rendering and encoding the one or more SC layers using a first codec and the one or more non-SC layers using a second codec.

Abstract: Embodiments of the disclosure provide systems and methods for processing video content. The method can include: receiving raw video data of a video; determining a texture complexity for the video based on the raw video data; determining an encoding mode for the raw video data based on the texture complexity; and encoding the raw video data using the determined encoding mode.

Abstract: The present disclosure relates to a method for compensating an image. The method comprises estimating transform coefficients of a frequency component for a first image based on the first image, performing a dot multiplication operation between the estimated transform coefficients and a basis function associated with the frequency component to generate a compensation image, and combining the first image and the compensation image to generate a combined image.

Abstract: The present disclosure relates to a method for controlling execution of a GEMM operation on an accelerator comprising multiple computation units, a first memory device, and a second memory device. The method comprises determining an execution manner of the GEMM operation, the execution manner comprising partition information of the GEMM operation and computation unit allocation information of the partitioned GEMM operation; generating one or more instructions to compute the partitioned GEMM operation on one or more allocated computation units; and issuing the one or more instructions to at least one of a first queue and a second queue, which enables at least one of a first local controller and a second local controller to execute the one or more instructions, wherein the first local controller and the second local controller are configured to control data movement between the computation units, the first memory device, and the second memory device.

Abstract: This application describes methods, systems, and apparatus, including computer programs encoded on computer storage media, of an AI-assisted compiler. An example method includes obtaining intermediate code and executable code generated by compiling a computer program with a compiler; determining a reward based on one or more traces obtained by executing the executable code in a runtime system; generating an embedding vector based on the intermediate code and the one or more traces to represent code execution states; determining, using a reinforcement learning agent, one or more optimization actions based on the embedding vector and the reward; and updating the compiler by applying the one or more optimization actions.

Abstract: A system for processing encoded image components for artificial intelligence tasks. The system can include one or more compute units, one or more controllers and memory. The one or more controllers can include one or more micro-op schedulers and one or more channel switches. The one or more compute units can be configured to process components of the transformed domain image data according to one or more micro-operations for an artificial intelligence task. The one or more channel switches can be configured to selectively control the transfer of the components of transformed domain image data to the one or more compute units based on one or more gating flags. The one or more channel switches can also be configured to selectively control generation of the one or more micro-operations by the one or more micro-op schedulers based on the one or more gating flags.

Abstract: Methods and systems are provided for implementing static channel filtering operations upon image datasets transformed to frequency domain representations, including decoding images of an image dataset to generate a frequency domain representation of the image dataset; discarding coefficient values of one or more particular frequency channels of each image of the image dataset in a frequency domain representation; and transporting the image dataset in a frequency domain representation to one or more special-purpose processor(s). Methods and systems of the present disclosure may enable a filtered image dataset to be input to a second layer of a learning model, bypassing a first layer, or may enable a learning model to be designed with a reduced-size first layer. This may achieve benefits such as reducing computational overhead and time of machine learning training and inference computations, reducing volume of image data input into the learning model, and reducing convergence time.

Abstract: In one embodiment, an apparatus comprises a memory and a processor. The memory is to store sensor data captured by one or more sensors associated with a first device. Further, the processor comprises circuitry to: access the sensor data captured by the one or more sensors associated with the first device; determine that an incident occurred within a vicinity of the first device; identify a first collection of sensor data associated with the incident, wherein the first collection of sensor data is identified from the sensor data captured by the one or more sensors; preserve, on the memory, the first collection of sensor data associated with the incident; and notify one or more second devices of the incident, wherein the one or more second devices are located within the vicinity of the first device.

Abstract: A method for of encoding an application screen comprises partitioning graphic data into a plurality of graphic layers and classifying each of the plurality of graphic layers as either a screen content (SC) or a non-screen content (non-SC) layer. The method further comprises classifying each of the plurality of graphic layers as either a screen content (SC) or a non-screen content (non-SC) layer. Further, the method comprises rendering and encoding the one or more SC layers using a first codec and the one or more non-SC layers using a second codec.