Abstract: A computer-implemented method for vision transforming includes, for each of one or more channels of each of a set of tiles of an image: splitting the channel into at least a first channel portion and a second channel portion; processing the first channel portion using depthwise convolution; processing the second channel portion with multi-head self-attention; and combining the processed first channel portion and the processed second channel portion; and identifying an object in the image at least partially based on the combined processed first channel portion and processed second channel portion for each of the one or more channels of each of the set of tiles of the image.

Abstract: The present invention provides compounds of Formula I, pharmaceutical compositions comprising these compounds and methods of using these compounds to prevent or treat FXR-mediated or TGR5-mediated diseases or conditions.

Abstract: The present disclosure provides a motion capture method and apparatus, an electronic device, and a storage medium. The method comprises: obtaining human inertial data collected by an extended reality device; and obtaining human pose information by inputting the human inertial data into a pre-trained motion capture model, where the motion capture model is obtained by training a neural network model based on a preset loss function; and the motion capture model comprises one or more of a neural network for predicting a human pose, a neural network for predicting global displacement information, a neural network for predicting a human bone parameter, and a classification network for predicting a human ground-stepping state.

Abstract: Methods, systems, and media for training deep neural networks for cross-domain few-shot classification are described. The methods comprise an encoder and a decoder of a deep neural network. The training of the autoencoder comprises two training stages. For each iteration in the first training stage, a batch of data samples from the source dataset are sampled and fed to the encoder to generate a plurality of source feature maps, then determining a first training stage loss, which updates the autoencoder's parameters. For each iteration in the second training stage, the novel dataset is split into a support set and a query set. The support set is fed to the encoder to determine a prototype for each class label. The query set is also fed to the encoder to calculate a query set metric classification loss. The query set metric classification loss updates the autoencoder's parameters.

Abstract: Embodiments of the present application provide a model training method and apparatus, and a device and a storage medium, and relate to the technical field of motion capture. The method includes: training a motion capture model according to a preset training set, wherein the motion capture model includes a time series prediction unit; performing, through a quantization node in the time series prediction unit, a quantization operation and an inverse quantization operation in sequence on model data passing through the quantization node; and adjusting a weight parameter of the time series prediction unit according to an update on a gradient of the time series prediction unit until the motion capture model converges, wherein the weight parameter includes a weight scaling parameter and a weight direction.

Abstract: Embodiments of the disclosure provide a method, an apparatus, an electronic device, and a storage medium of pose prediction. The method includes: extracting temporal information of input data through a long short-term memory network, the temporal information including recent memory data, and the input data including pose data of a current frame of a target object collected by a pose sensor; generating first intermediate data by fully connecting and activation mapping the input data through a nonlinear learning unit; generating second intermediate data by stacking the recent memory data and the first intermediate data of the nonlinear learning unit through a stacked unit, the long short-term memory network, the nonlinear learning unit, and the stacked unit forming a basic learning module; and predicting a current pose of the target object based on the second intermediate data.

Abstract: The present invention provides compounds represented by Formula I, or pharmaceutically acceptable salts, stereoisomers, solvates, hydrates or combination thereof, The invention also provides pharmaceutical compositions comprising these compounds and methods of using this compounds for treating FXR-mediated or TGR5-mediated diseases or conditions.

Abstract: Methods and systems for gesture-based control of a device are described. An input frame is processed to determine a location of a distinguishing anatomical feature in the input frame. A virtual gesture-space is defined based on the location of the distinguishing anatomical feature, the virtual gesture-space being a defined space for detecting a gesture input. The input frame is processed in only the virtual gesture-space, to detect and track a hand. Using information generated from detecting and tracking the at least one hand, a gesture class is determined for the at least one hand. The device may be a smart television, a smart phone, a tablet, etc.

Abstract: Methods and devices for generating a customized video segment from a video are disclosed. The video is partitioned into video segments. For each respective video segment, a respective set of scores is computed, where each score represents a respective content feature in the respective video segment. A respective weighted aggregate score is computed for each respective video segment by applying, to each respective set of scores, a common set of weight values. A selected video segment is outputted as the customized video segment, where the selected video segment is selected from one or more high-ranked video segments having high-ranked weighted aggregate scores.

Abstract: Techniques for decoupling compute and storage resources in a hyper-converged infrastructure (HCI) are provided. In one set of embodiments, a control plane of the HCI deployment can provision a host from a host platform of an infrastructure on which the HCI deployment is implemented and can provision one or more storage volumes from a storage platform of the infrastructure, where the storage platform runs on physical server resources in the infrastructure that are separate from the host platform. The control plane can then cause the one or more storage volumes to be network-attached to the host in a manner that enables a hypervisor of the host to make the one or more storage volumes available, as part of a virtual storage pool, to one or more virtual machines in the HCI deployment for data storage.

Abstract: An example method of providing a common volume (cVol) datastore for virtual machines (VMs) managed by a hypervisor in a virtualized computing system is described. The method includes: mounting, by the hypervisor, a network file system share of a common volume (cVol), the cVol stored in shared storage of the virtualized computing system, the network file system share storing metadata for the VMs; creating a file system for the cVol datastore backed by the network file system share; routing file operations targeting the metadata to the file system for the cVol datastore; and routing file operations targeting virtual disks of the VMs to an object storage pool of the cVol based on descriptors in the metadata that point to objects backing the virtual disks.

Abstract: Methods and systems for gesture-based control of a device are described. A virtual gesture-space is determined in a received input frame. The virtual gesture-space is associated with a primary user from a ranked user list of users. The received input frame is processed in only the virtual gesture-space, to detect and track a hand. Using a hand bounding box generated by detecting and tracking the hand, gesture classification is performed to determine a gesture input associated with the hand. A command input associated with the determined gesture input is processed. The device may be a smart television, a smart phone, a tablet, etc.

Abstract: A compound is provided as having a structure of Formula I: where X1 and X2 are each independently a nitrogen atom or a C—R group, C is a carbon atom, R is a hydrogen atom, a deuterium atom, a halogen atom, or a cyano group, CR, and at least one of X1 and X2 is N; L1, L2, and L3 are each independently a single bond, a substituted or unsubstituted aryl group, or substituted or unsubstituted aryl heteroaryl group; and Ar1, Ar2 are each independently a substituted or unsubstituted aryl group or a substituted or unsubstituted heteroaryl group.

Abstract: The present invention provides compounds of Formula I, pharmaceutical compositions comprising these compounds and methods of using these compounds to prevent or treat FXR-mediated or TGR5-mediated diseases or conditions.

Abstract: Methods and systems for gesture-based control of a device are described. A virtual gesture-space is determined in a received input frame. The virtual gesture-space is associated with a primary user from a ranked user list of users. The received input frame is processed in only the virtual gesture-space, to detect and track a hand. Using a hand bounding box generated by detecting and tracking the hand, gesture classification is performed to determine a gesture input associated with the hand. A command input associated with the determined gesture input is processed. The device may be a smart television, a smart phone, a tablet, etc.

Abstract: The present invention provides compounds represented by Formula I, or pharmaceutically acceptable salts, stereoisomers, solvates, hydrates or combination thereof, The invention also provides pharmaceutical compositions comprising these compounds and methods of using this compounds for treating FXR-mediated or TGR5-mediated diseases or conditions.

Abstract: Methods, systems, and media for image searching are described. Images comprising one query image and a plurality of candidate images are received. For each candidate image, a first model similarity measure from an output of a first model configured for scene classification to perceive scenes in the images is determined. Further, for each candidate image of the plurality of candidate images, a second model similarity measure from the output of a second model configured for attribute classification to perceive attributes in the images is determined. For each candidate image of the plurality of candidate images, a similarity agglomerate index of a weighted aggregate of the first model similarity measure and the second model similarity measure is computed. The plurality of candidate images based on the respective similarity agglomerate index of each candidate image are ranked and a first ranked candidate images corresponding to the searched images are generated.

Abstract: Methods and systems for gesture-based control of a device are described. A virtual gesture-space is determined in a received input frame. The virtual gesture-space is associated with a primary user from a ranked user list of users. The received input frame is processed in only the virtual gesture-space, to detect and track a hand. Using a hand bounding box generated by detecting and tracking the hand, gesture classification is performed to determine a gesture input associated with the hand. A command input associated with the determined gesture input is processed. The device may be a smart television, a smart phone, a tablet, etc.

Abstract: Systems and methods for temporal action localization of video data are described. A feature representation extracted from video data has a temporal dimension and a spatial dimension. The feature representation is self-aligned in the spatial dimension. Spatial multi-sampling is performed to obtain a plurality of sparse samples of the self-aligned representation along the spatial dimension, and the multi-sampled representation is fused with the self-aligned representation. Attention-based context information aggregation is applied on the fused representation to obtain a spatially refined representation. Local temporal information aggregation is applied on the self-aligned representation to obtain a temporally refined representation. Action localization is performed on a concatenation of the spatially refined representation and the temporally refined representation.

Abstract: Systems, methods, and computer media of processing a video are disclosed. An example method may include: receiving a plurality of video frames of a video; generating a plurality of first input features based on the plurality of video frames; generating a plurality of second input features based on reversing a temporal order of the plurality of first input features; generating a first set of joint attention features based on the plurality of first input features; generating a second set of joint attention features based on the plurality of second input features; and concatenating the first set of joint attention features and the second set of joint attention features to generate a final set of joint attention features.