Abstract:
Certain aspects of the present disclosure provide techniques for training and using an instance segmentation neural network to detect instances of a target object in an image. An example method generally includes generating, through an instance segmentation neural network, a first mask output from a first mask generation branch of the network. The method further includes generating, through the instance segmentation neural network, a second mask output from a second, parallel, mask generation branch of the network. The second mask output is typically of a lower resolution than the first mask output. The method further includes combining the first mask output and second mask output to generate a combined mask output. Based on the combined mask output, an output of the instance segmentation neural network is generated. One or more actions are taken based on the generated output.
Abstract:
Aspects of the methods and apparatus include determining that a time-to-trigger (TTT) timer has expired, and determining that a serving radio access technology (RAT) received signal characteristic is less than a signal characteristic threshold when the TTT timer has expired. Further, the aspects include determining, in response to the serving RAT received signal characteristic being less than the signal characteristic threshold, that a target RAT frequency measurement associated with a Measurement Report Message (MRM) for performing an inter-RAT (IRAT) handover cannot be completed within a time limit according to a current measurement gap configuration. Also, the aspects include calculating a measurement gap duration sufficient to complete the target RAT frequency measurement associated with the MRM for performing the IRAT handover, and configuring a new measurement gap prior to the time limit, wherein the new measurement gap comprises the calculated measurement gap duration.
Abstract:
Disclosed are systems and techniques for image processing. For example, a computing device can generate, using a multi-task model, a segmentation output and a normal output based on image(s) of a scene and a gravity vector for the scene. The computing device can learn semantic prediction(s) based on comparing the segmentation output to at least one ground truth semantic segmentation map. The computing device can also learn normal prediction(s) based on comparing the normal output to at least one ground truth normal map. The computing device can extract a semantics normal from the semantic prediction(s) and the normal prediction(s). The computing device can optimize a regularization loss based on the semantics normal and the gravity vector for the scene by learning gravity-normal regularization(s) for the scene. The computing device can determine final semantic labels for regions of the scene based on the gravity-normal regularization(s).
Abstract:
A user equipment (UE) may monitor a channel for wireless communication associated with a first radio access technology (RAT) during one or more of a first active duration or a first inactive duration. The UE may operate in a first power mode during the first inactive duration. The UE may monitor the channel for wireless communication associated with a second RAT during one or more of a second active duration or a second inactive duration. The UE may operate during the second inactive duration in one or more of the first power mode or a second power. The UE may operate according to the first mode or the second mode based on the monitoring of the channel associated with the first RAT and the second RAT.
Abstract:
A user equipment (UE) with multiple receive chains and one or more subscriber identity modules improves radio access technology (RAT) measurements when one or more of the subscriber identity modules are active and valid measurement gaps or consecutive idle time slots are unavailable for the radio access technology measurements. The UE communicates with a first receive (RX) chain for a first subscriber identity module (SIM). The UE also performs the radio access technology (RAT) measurement with a second receive (RX) chain while maintaining communications with the first receive chain.
Abstract:
Certain aspects of the present disclosure provide a technique for wireless communications by a user equipment (UE). The UE monitors a concurrent operation on multiple operating bands within a same subscriber identity module (SIM) or between multiple SIMs that involves sharing at least one radio frequency (RF) component. The UE enables or disables the at least one RF component based on the monitoring.
Abstract:
Methods, systems, and devices for wireless communications are described. A user equipment (UE) may operate in a dual-connectivity (DC) configuration, and may measure signals from more than one radio access technology (RAT). The UE may receive a first signal power for a first RAT and a second signal power for a second RAT. The UE may determine a common gain state for the first RAT and the second RAT based on the first signal power and the second signal power. The UE may then apply the common gain state to a first receiver chain within the UE for the first RAT and to a second receiver chain within the UE for the second RAT, where the first receiver chain and the second receiver chain share at least one shared low noise amplifier (LNA).
Abstract:
A method of wireless communication includes controlling a rate of forced measurement gap requests for a serving radio access technology (RAT) to measure a target RAT based on an impact to quality of service on the serving RAT by forced measurement gaps.