A method, apparatus, and storage medium for training a neural network model used for image processing are described. The method includes: obtaining a plurality of video frames; inputting the plurality of video frames through a neural network model so that the neural network model outputs intermediate images; obtaining optical flow information between an early video frame and a later video frame; modifying an intermediate image corresponding to the early video frame according to the optical flow information to obtain an expected-intermediate image; determining a time loss between an intermediate image corresponding to the later video frame and the expected-intermediate image; determining a feature loss between the intermediate images and a target feature image; and training the neural network model according to the time loss and the feature loss, and returning to obtaining a plurality of video frames continue training until the neural network model satisfies a training finishing condition.

A method of acquiring data, a computer program product for implementing the method, a system for acquiring data, and a vehicle including the system. The method includes determining one or more data types and virtual channels required for one or more applications. The method also includes allocating a plurality of circular buffers in memory according to the determined data type(s) and virtual channel(s). One or more of the circular buffers are allocated to safety data lines. The remaining circular buffers are allocated to functional data lines. The method further includes storing at least one functional data line in a circular buffer allocated to functional data lines according to a data type and virtual channel of the functional data line. The method also includes storing at least one safety data line in a circular buffer allocated to safety data lines.

A method of acquiring data, a computer program product for implementing the method, a system for acquiring data, and a vehicle including the system. The method includes determining one or more data types and virtual channels required for one or more applications. The method also includes allocating a plurality of circular buffers in memory according to the determined data type(s) and virtual channel(s). One or more of the circular buffers are allocated to safety data lines. The remaining circular buffers are allocated to functional data lines. The method further includes storing at least one functional data line in a circular buffer allocated to functional data lines according to a data type and virtual channel of the functional data line. The method also includes storing at least one safety data line in a circular buffer allocated to safety data lines.

A patient interface for supplying a flow of breathable gas to the airways of a patient may comprise a heat and moisture exchanger (HME). The HME may be positioned in a flow path of the flow of breathable gas. The HME may absorb heat and moisture from gas exhaled by the patient and the incoming flow of breathable gas to be supplied to the patient's airways may be heated and moisturized by the heat and moisture held in the HME.

Edge devices utilizing personalized machine learning and methods of operating the same are disclosed. An example edge device includes a model accessor to access a first machine learning model from a cloud service provider. A local data interface is to collect local user data. A model trainer is to train the first machine learning model to create a second machine learning model using the local user data. A local permissions data store is to store permissions indicating constraints on the local user data with respect to sharing outside of the edge device. A permissions enforcer is to apply permissions to the local user data to create a sub-set of the local user data to be shared outside of the edge device. A transmitter is to provide the sub-set of the local user data to a public data repository.

A processor of an ophthalmologic image processing device acquires an ophthalmologic image photographed by an ophthalmologic image photographing device. The processor inputs the ophthalmologic image into a mathematical model trained by a machine learning algorithm to acquire a result of an analysis relating to at least one of a specific disease and a specific structure of a subject eye. The processor acquires information of a distribution of weight relating to an analysis by a mathematical model, as supplemental distribution information, for which an image area of the ophthalmologic image input into the mathematical model is set as a variable. The processor sets a part of the image area of the ophthalmologic image, as an attention area, based on the supplemental distribution information. The processor acquires an image of a tissue including the attention area among a tissue of the subject eye and displays the image on a display unit.

Examples of systems and method described herein provide for the processing of image codes (e.g., a binary embedding) at a memory die. Such images codes may generated by various endpoint computing devices, such as Internet of Things (IoT) computing devices, Such devices can generate a Hamming processing command, having an image code of the image, to compare that representation of the image to other images (e.g., in an image dataset) to identify a match or a set of neural network results. Advantageously, examples described herein may be used in neural networks to facilitate the processing of datasets, so as to increase the rate and amount of processing of such datasets. For example, comparisons of image codes can be performed on a memory die itself, like a memory die of a NAND memory device.

According to various embodiments, a pore visualization service providing server based on artificial intelligence may include a data pre-processor for obtaining a user's face image captured by a user terminal from the user terminal and performing pre-processing based on facial feature points based on the face image; a pore image extractor for generating a pore image corresponding to the user's face image by inputting the user's face image that has been pre-processed through the data pre-processing into an artificial neural network; a data post-processor for post-processing the generated pore image; and a pore visualization service providing unit for superimposing the post-processed pore image on the face image and transmitting a pore visualization image to the user terminal.

A method of processing an image, a method of training a model, an electronic device and a medium, which relate to a field of artificial intelligence technology, in particular to deep learning, computer vision and other technical fields. A solution includes: generating a first face image, wherein a definition difference and an authenticity difference between the first face image and a reference face image are within a set range; adjusting, according to a target voice used to drive the first face image, a facial action information related to pronunciation in the first face image to generate a second face image with a facial tissue position conforming to a pronunciation rule of the target voice; and determining the second face image as a face image driven by the target voice.

A method automatically detects digital assets embedded into video frames or images. Each digital asset includes a plurality of embedded graphical representation elements with each element embedding an individual character of the digital asset’s unique identification code. The video frames or images are automatically scanned for the presence of embedded graphical representation elements with each detected element decoded to extract its individual character. The resultant extracted characters are then statistically analyzed in an attempt to reconstruct the digital asset’s unique identification code.