Abstract: Various embodiments provide an apparatus, a method and a computer program product for end-to-end learned predictive coding of media frames. An example apparatus includes at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: encode or decode one or more media frames for at least one neural network; wherein an inter-frame codec is applied to at least one media frame of the one or more media frames; and wherein a first decoded reference frame and a second decoded reference frame refer to reference frames for the at least one media frame.

Abstract: An example method includes: receiving an input extended block comprising an input block and input margins, wherein the input block is derived from an image or a video frame, and wherein the input block and the input margins are input to a filter, and wherein the input margins comprise pixels of the image or the video frame; filtering the input extended block to obtain a filtered extended block comprising a filtered block and filtered margins; receiving other blocks, wherein the other blocks are derived from the image or video frame, and wherein at least one pixel of the other blocks overlaps with at least one pixel of the filtered margins of the filtered extended block; and blending the filtered extended block with the other blocks, wherein an operation to blend the filtered extended block with the other blocks is applied to two or more overlapping pixels

Abstract: The present disclosure provides a call method and terminal, and a non-transitory computer-readable storage medium. The call method includes: receiving or initiating, by a first terminal, a call request to establish a call with a second terminal; detecting, by the first terminal, at least one of the following: a current task being executed by the first terminal, whether there is one or more third terminals capable of assisting in the call, and a current task being executed by a third terminal; and selecting whether a display interface of the first terminal displays a call assisting option according to the current task being executed by the first terminal and/or the current task being executed by the third terminal; wherein the call assisting option is used to prompt a user to select to answer the call with the second terminal through the assistance of the third terminal.

Abstract: The present disclosure relates to a human-computer interaction method, apparatus, and system, and a computer-readable storage medium. The human-computer interaction method includes: displaying an eraser icon on a touch display screen according to a first touch operation of a user; adjusting at least one of a direction, a size or a shape of the eraser icon according to a second touch operation of the user, wherein the second touch operation includes at least one of a rotation operation or a deformation operation on the eraser icon; and performing an erase operation on an area to be erased according to the adjusted eraser icon.

Abstract: A method is provided for computing predetermined loss terms based on original data and decoded data; training one or more neural networks of a system by using the predetermined loss terms; updating weights for one or more of other loss terms; and determining trade-offs between predetermined objectives of the system. Corresponding apparatuses and computer program products are also provided.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. An example method includes determining one or more quantization parameters (quantizers) based at least on one or more of the following: a mean absolute value computed based on a set of parameters of a neural network comprising a parameter; a maximum absolute value computed based on a set of activations of the neural network comprising an activation; a number of parameters in the set of parameters of the neural network comprising the parameter; or a maximum absolute value computed based on an output value computed based on the parameter and the activation; and quantizing at least one of the parameter or the activation based at least on the one or more quantization parameters.

Abstract: The embodiments of the present disclosure provide a display device, the display device comprising a display module and an infrared touch control assembly, wherein a display surface of the display module is in the shape of a rectangle with an edge extending in a first direction and an edge extending in a second direction, the first direction and the second direction being perpendicular to each other; the infrared touch control assembly comprises an infrared emitting frame and an infrared receiving frame which are arranged oppositely and extend in the first direction; a plurality of infrared emitting units are fixed in the infrared emitting frame; a plurality of infrared receiving units are fixed in the infrared receiving frame; and an orthographic projection of a light-emitting surface of the infrared emitting frame in the display module is positioned in an area outside a display area of the display module.

Abstract: An apparatus comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: maintain a first parameter update tree that tracks residuals of weight updates of a machine learning model; maintain a second parameter update tree that tracks the weight updates of the machine learning model; pass the first parameter update tree and the residuals to an encoder; receive a first bitstream generated for the residuals from the encoder; pass the second parameter update tree and the weight updates to the encoder; receive a second bitstream generated for the weight updates from the encoder; and determine whether to signal to a decoder the first bitstream generated for the residuals or the second bitstream generated for the weight updates.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. The apparatus includes at least one processor; and at least one non-transitory memory comprising computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: determine a plurality of weights used to calculate a weighted loss based at least on a performance of a plurality of neural networks on one or more training samples; and jointly train the plurality of neural networks, wherein at each training iteration the plurality of neural networks are trained based at least on the weighted loss.

Abstract: In example embodiments, an apparatus, a method, and a computer program product are provided. An example apparatus include processing circuitry; and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processing circuitry, cause the apparatus at least to: overfit a neural network on each media item, from a batch of media items, for a number of iterations to obtain an overfitted neural network model for the each media item; evaluate the overfitted neural network model on the each media item to obtain evaluation errors; and update parameters of the neural network to be based on the evaluation errors.

Abstract: An apparatus comprising: at least one processor; and at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the apparatus at least to: receive a signal, the signal comprising a sparse signal; perform residual coding on the signal; perform predictive coding on the signal; determine a residual, the residual comprising a residual of the signal and a base signal or a residual of an approximation and the base signal, the approximation being an approximation of the signal; and determine whether to transmit the residual or the signal over a communication channel.

Abstract: Provided are compounds represented by general formula (I), which can be used for treating ATR kinase-mediated diseases, such as proliferative diseases, such as cancer. Further provided are a pharmaceutical composition of the compound represented by general formula (I), a use thereof in treating ATR kinase-mediated diseases, and a preparation thereof.

Abstract: In example embodiments, an apparatus, a method, and a computer program product are provided. The apparatus comprises at least one processor; and at least one non-transitory memory including computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform determine a processing order of building blocks to encode or decode a media item; and determine a number of processing steps required to encode or decode the media item; wherein the processing order of building blocks and the number of processing steps are determined based on a content of the media item by using a guided probability model based on a neural network.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. An example apparatus includes at least one processor; and at least one non-transitory memory comprising computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: determine a subset of parameters to overfit from a set of candidate parameters of decoder side neural network to be overfitted (OPs); wherein the subset of parameters to overfit is smaller than the set of candidate parameters to be overfitted; and overfit the determined subset of parameters.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. The apparatus includes at least one processor; and at least one non-transitory memory comprising computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to perform: organize plurality of decoders side neural networks based on one or more task categories or one or more tasks; and select a decoder side neural network based at least on the one or more task categories or the one or more task.

Abstract: The present disclosure provides a monitoring method, a monitoring device and a monitoring server. The monitoring method includes: acquiring physical sign information of a user; determining whether a physical sign of the user is in an abnormal state based on the physical sign information; acquiring first physical symptom information of the user in response to the physical sign of the user being in the abnormal state; and transmitting the physical sign information and the first physical symptom information to a monitoring server to determine a health status of the user.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. 1. An apparatus incudes at least one processor; and at least one non-transitory memory includes computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to: perform an overfitting operation, at an encoder side, to obtain an overfitted probability model, wherein overfitting comprises one or more training operations applied to a probability model, wherein one or more parameters of the probability model are trained; use the overfitted probability model to provide probability estimates to a lossless codec or a substantially lossless codec for encoding data or a portion of the data; and signal information to a decoder on whether to perform the overfitting operation at the decoder side.

Abstract: Various embodiments provide an apparatus, a method, and a computer program product. An example apparatus includes at least one processor; and at least one non-transitory memory comprising computer program code; wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus at least to iteratively perform following until a stopping criterion is met: provide a finetuning driving content (FDC) or a content derived from FDC to a decoder side neural network (DSNN); compute an output of the DSNN as a processed FDC; compute a loss based on the processed FDC and an approximated ground truth data (AGT) associated with the FDC; compute an update to the DSNN; and apply the computed update to the DSNN.

Abstract: A face recognition method. The method includes: obtaining a face image to be recognized; extracting a face image feature based on the face image by using a pre-trained feature extraction network; extracting a plurality of facial geometric feature points from the face image to determine a plurality of feature point sets, where each of the plurality of feature point sets corresponds to one face part, and the feature point set includes at least one facial geometric feature point; obtaining a face topology structure feature based on the plurality of feature point sets, where the face topology structure feature is used to determine a relative location relationship between the plurality of feature point sets; and performing matching in a preset face database based on the face topology structure feature and the face image feature, to obtain a face recognition result.

Abstract: Data may be encoded to minimize distortion after decoding, but the quality required for presentation of the decoded data to a machine and the quality required for presentation to a human may be different. To accommodate different quality requirements, video data may be encoded to produce a first set of encoded data and a second set of encoded data, where the first set may be decoded for use by one of a machine consumer or a human consumer, and a combination of the first set and the second set may be decoded for use by the other of a machine consumer or a human consumer. The first and second set may be produced with a neural encoder and a neural decoder, and/or may be produced with the use of prediction and transform neural network modules. A human-targeted structure and a machine-targeted structure may produce the sets of encoded data.