Abstract: A computer-implemented method includes receiving first inputs associated with a first modality and second inputs associated with a second modality; processing the received first and second inputs with convolutional neural networks (CNN), wherein a set of first weights are used to handle the first inputs and a second set of weights are used to handle the second inputs; determining a loss for each of the first and the second inputs based on a loss function that applies the first set of weights, the second set of weights, and a presence of a co-occurrence; generating a shared feature space as an output of the CNNs, wherein a distance between cells associated with the first inputs and the second inputs in the shared feature space is determined based on the loss associated with each of the first inputs and the second inputs; and based on the shared feature space, providing an output.

Abstract: This disclosure provides an Ethernet header compression method, an Ethernet header decompression method, and a device. The compression method includes: transmitting, by using a transmitting PDCP entity of the transmitting end, a first PDCP PDU corresponding to a first data radio bearer DRB, where when the first DRB is configured with an Ethernet header compression function, the first PDCP PDU includes one or more pieces of first information, and the first information is used to indicate whether a specific Ethernet field in an Ethernet header of a first PDCP SDU corresponding to the first PDCP PDU is reused.

Abstract: A service node updating method is provided. The method is performed by a terminal device and includes: receiving configuration information, where the configuration information includes first connectivity configuration information used to maintain both a connection to a source node and a connection to a target node in a service node updating procedure and second connectivity configuration information used to release the connection to the source node and connect to the target node; processing, by applying the first connectivity configuration information, a layer 2 protocol entity corresponding to a bearer between the terminal device and the source node, to reconfigure the bearer as a source node split bearer; and processing, by applying the second connectivity configuration information, a layer 2 protocol entity corresponding to the bearer, to reconfigure the source node split bearer as a target node bearer.

Abstract: Provided are a random access method, a terminal device and a network device. The random access method includes transmitting a two-step random access request message to a network device. A data part is carried in the two-step random access request message, and the data part is acquired through performing layer-two processing in accordance with layer-two configuration information.

Abstract: Embodiments of this disclosure provide a serving node update method and a device. The method includes: sending a first message to a target node; receiving, from the target node, a second message used for responding to the first message; and sending a third message to a terminal device when the second message indicates that the target node rejects a multi-connectivity serving node update, where the third message is used to indicate the terminal device to perform a serving node update in a legacy serving node update manner.

Abstract: The present disclosure provides a random access method, a terminal and a network device. The random access method, performed by a terminal, includes: obtaining configuration information of a target random access; determining a first physical uplink shared channel (PUSCH) resource for transmitting a message 1, according to the configuration information; on the first PUSCH resource, transmitting the message 1 of the target random access.

Abstract: A bandwidth adjustment method, a mobile terminal, a network side device, and a computer storage medium are provided in the present disclosure. The bandwidth adjustment method includes: deactivating a currently activated bandwidth part BWP based on a deactivation condition, and switching to a pre-configured default BWP; where the currently activated BWP includes a to-be-adjusted BWP in the currently activated BWP.

Abstract: A cell management method, a trigger condition configuration method, a terminal device, and a network-side device are provided. The method includes: receiving configuration information of a trigger condition and configuration information of a trigger event that are sent by a network-side device, where an association relationship exists between the configuration information of the trigger condition and the configuration information of the trigger event, and configuration information of one trigger condition is associated with configuration information of at least two trigger events; determining, based on the configuration information of the at least two trigger events associated with the configuration information of the trigger condition, whether the trigger condition is satisfied; and when the trigger condition is satisfied, initiating a radio resource control RRC procedure for cell management.

Abstract: A resource monitoring method, a terminal, and a base station are provided. The method of the present disclosure includes receiving a CORESET configuration information sent by a base station, wherein the CORESET configuration information indicates a CORESET; determining, according to a predefined TCI state or a first downlink MAC CE sent by the base station, a target TCI state used for monitoring the CORESET; monitoring the CORESET according to the target TCI state.

Abstract: A method of transmitting configuration information and a related device are provided. The method includes sending IDC assistance information to a network-side device, wherein the network-side device includes at least one of an MN and an SN; receiving assistance configuration information of IDC interference cancellation sent by the network-side device, wherein the assistance configuration information of IDC interference cancellation corresponds to the IDC assistance information.

Abstract: A computer-implemented method is provided, comprising, based on information of a subject positioned on an object in an environment, generating a data stream; for the data stream, extracting features associated with a movement of the subject with respect to the object or the environment, wherein the movement is represented by spatio-temporal features extracted from sensors; generating a prediction associated with a likelihood of the movement based on the extracted features, and a risk profile of the movement based on a plurality of fall risk factors; and applying the prediction and the risk profile to a rule base to perform an action.

Abstract: A computer-implemented method, comprising extracting each frame of a video sequence, estimating current poses of a subject within each frame and determining joint locations for a joint associated with the subject within each frame, computing optical flows between each pair of consecutive video frames, extracting motion features from each video frame of the video sequence based on the optical flows, encoding state information based on the current poses and the motion features, determining a current action label for each motion feature in the state information for a first frame; predicting future action labels for each motion feature in a second frame subsequent to the first frame, based on the current pose, action label and state information, predicting future poses for each motion feature in the second frame based on the current poses and the state information; and refining the current action label, the future action labels, and the future poses.

Abstract: A receiving method, a sending method and communications device are provided. The receiving method includes: obtaining a duplication detection parameter; and performing duplication detection on a received sidelink packet data convergence protocol PDCP protocol data unit PDU by using the duplication detection parameter.

Abstract: The present application discloses a sidelink data indication method and a terminal equipment. The method includes: determining indication information, the indication information including at least one of a first identifier or a second identifier, wherein the first identifier is used to identify a first logical channel, the second identifier is used to identify a second logical channel, the first logical channel is used to carry original sidelink data, the second logical channel is used to carry duplicated sidelink data, the duplicated sidelink data is obtained by duplicating the original sidelink data; and sending the indication information.

Abstract: This disclosure provides a data sending method and receiving method, and user equipment thereof, and relates to the field of communications technologies. The data receiving method applied to user equipment includes: determining whether a Medium Access Cntrol (MAC) Protocol Data Unit (PDU) received by the user equipment includes a reserved Logical Channel Identity (LCID) value; and when the MAC PDU includes a reserved LCID value, discarding a Service Data Unit (SDU) or sub-PDU corresponding to the reserved LCID value in the MAC PDU.

Abstract: A bandwidth switching method and a UE are provided. The bandwidth switching method includes: determining, when a BWP switching command is received while successfully receiving a random access completion message for a non-contention-based random access process, that the non-contention-based random access process has been completed successfully in accordance with the random access completion message; and determining that a BWP switching process is not to be performed, or performing the BWP switching process in accordance with the random access completion message and the BWP switching command.

Abstract: The present disclosure provides a spatial relationship determination method, a terminal and a base station. The method in the present disclosure includes: receiving PUCCH resource configuration information sent by a base station, the PUCCH resource configuration information indicating a PUCCH resource; determining a target QCL required when using the PUCCH resource according to a predefined QCL or according to a downlink media access control layer control element (MAC CE) sent by the base station.

Abstract: An interference processing method, a user terminal and a network-side device are provided. The method includes sending interference-cancellation assistance information to a network-side device; receiving interference-cancellation configuration information sent by the network-side device according to the interference-cancellation assistance information, wherein, the interference-cancellation configuration information includes at least one of configuration information for stopping uplink transmission and configuration information for stopping downlink reception; and in case that interference occurs, performing an interference processing behavior according to the interference-cancellation configuration information, wherein the interference processing behavior includes at least one of stopping uplink transmission and stopping downlink reception.

Abstract: A computer-implemented method is provided for coordinating sensed poses associated with real-time movement of a first object in a live video feed, and pre-recorded poses associated with movement of a second object in a video. The computer-implemented method comprises applying a matching function to determine a match between a point of one of the sensed poses and a corresponding point of the pre-recorded poses, and based on the match, determining a playtime and outputting at least one frame of the video associated with the second object for the playtime.

Abstract: Example implementations described herein are directed to systems and methods for skill assessment, such as hand washing compliance in hospitals, or assembling products in factories. Example implementations involve body part tracking (e.g., hands), skeleton tracking and deep neural networks to detect and recognize sub-tasks and to assess the skill on each sub-task. Furthermore, the order of the sub-tasks is checked for correctness. Beyond monitoring individual users, example implementations can be used for analyzing and improving workflow designs with multiple sub-tasks.