Abstract: Systems and methods for panoptic video segmentation are described. A method may include identifying a target frame and a reference frame from a video, generating target features for the target frame and reference features for the reference frame, combining the target features and the reference features to produce fused features for the target frame, generating a feature matrix comprising a correspondence between objects from the reference features and objects from the fused features; and generating panoptic segmentation information for the target frame based on the feature matrix.

Abstract: A method for approximating spectral data, the method comprising using at least one hardware processor for: providing a digital image comprising data in a first set of spectral bands; providing a dictionary comprising (a) signatures in a second set of spectral bands and (b) values in said first set of spectral bands, wherein said values correspond to the signatures, and wherein said first and second sets of spectral bands are different; and approximating, based on the dictionary, data in said second set of spectral bands of said digital image.

Abstract: The present disclosure relates to a method for activating a relay functionality of a ProSe capable and relay-capable user equipment within a mobile communication network. The radio base station, to which the relay UE is connected, determines whether further relays are necessary in the radio cell controlled by the radio base station. In case further relays are necessary in the radio cell, the radio base station selects a persistence check value and transmits a broadcast message in the radio cell. The broadcast message at least indicates that further relays are necessary and comprises the selected persistence check value. Upon receiving the broadcast message, the relay UE activates its relay functionality in case it determines that relay requirements for activating its relay functionality in the radio cell are fulfilled and in case a persistence check performed by the relay UE based on the received persistence check value is successful.

Abstract: The present disclosure includes systems and methods for color transfer. The method includes receiving a target image, and determining dominant source colors. The method further includes transforming the target image into a color model including a target luminance component and a target color information component. Additionally, the method includes segmenting the target image into a plurality of target segments based on the target color information component or the target luminance component and extracting dominant target colors from the target image by extracting information for at least one of the dominant target colors from each target segment of the plurality of target segments. Further, the method includes generating a color mapping relationship between the dominant target colors and the dominant source colors, and creating a recolored target image using the color mapping relationship.

Abstract: An electronic device of a charging module system may include a housing having a first surface facing a first direction and a second surface facing a second direction opposite to the first direction; a display device at least partially is exposed through the first surface to display information to the outside; a biometric sensor disposed to be exposed in at least an area of the second surface and sensing biometric information of a user; a battery disposed between the display device and the biometric sensor; and a plurality of electrodes disposed adjacent to the at least an area of the second surface and formed to be exposed in at least another area of the second surface, in which the plurality of electrodes may surround at least a portion of the biometric sensor, and each of the plurality of electrodes has a notch protruding or recessed at least at one end.

Abstract: Images of an undercarriage of a vehicle may be captured via one or more cameras. A point cloud may be determined based on the images. The point cloud may includes points positioned in a virtual three-dimensional space. A stitched image may be determined based on the point cloud by projecting the point cloud onto a virtual camera view. The stitched image may be stored on a storage device.

Abstract: A communication device receives an uplink grant from a node of a cellular network. The uplink grant indicates uplink radio resources allocated to the communication device in reoccurring time intervals. For each of these time intervals, the communication device selects between an active mode and an inactive mode. In the active mode the communication device performs an uplink transmission in the allocated uplink radio resources. In the inactive mode the communication device performs no uplink transmission in the allocated uplink radio resources.

Abstract: Certain aspects of the present disclosure provide a method for lane marker detection, including: receiving an input image; providing the input image to a lane marker detection model; processing the input image with a shared lane marker portion of the lane marker detection model; processing output of the shared lane marker portion of the lane marker detection model with a plurality of lane marker-specific representation layers of the lane marker detection model to generate a plurality of lane marker representations; and outputting a plurality of lane markers based on the plurality of lane marker representations.

Abstract: In tracking of a moving body using image data in detecting a target moving body having few externally outstanding features, such as coloring and a shape, from an image in an image frame, if an image of the target moving body overlaps a background image largely and their colorings are the same or similar to one another, it is difficult to detect the target moving body. A template image of the target moving body is superimposed on a background image of a region (periphery) of a candidate position of the target to generate a composite image and the moving body is detected based on a degree of match calculated through comparison of the composite image with an image of the region (periphery) of the candidate position of the target.

Abstract: Distributed systems, controllers and methods for processing information from a plurality of devices are provided. A distributed system includes a plurality of devices distributed in an environment. Each device has at least a communication capability for interchanging information with others of the devices and/or with a communication system. Each of at least some of the devices has one or more sensors for acquiring sensor data related to the environment proximate to the device. At least one of the communication system or one or more of the devices is configured as a controller configured to: select a subset of devices from among the plurality of devices, receive information based on the acquired sensor data of the selected subset, and combine the received information from the selected subset to determine a characteristic of the environment proximate to one or more of the devices.

Abstract: The present application discloses a method, an apparatus, a system, and a storage medium for calibrating an exterior parameter of an on-board camera, relating to the field of autonomous driving technologies. A specific implementation scheme of the method in the application is: preprocessing two frames of images of a former frame and a latter frame collected by the on-board camera; performing feature point matching on the two preprocessed frames of images to obtain matched feature points; determining a moving posture of the on-board camera according to the matched feature points; determining a conversion relationship between a vehicle coordinate system and an on-board camera coordinate system according to the moving posture, and obtaining the external parameter of the on-board camera relative to a vehicle body.

Abstract: Computer-implemented systems and methods for generating and using a location sensitive ensemble classifier for classifying content includes dividing a validation data set into regions. Each region encompasses data points of the validation data set that fall within the region. A regional ensemble classifier is generated for each region based on the data points that fall within the region. A content item is then classified in at least one of a plurality of classes using the regional ensemble classifier for the region to which the content item belongs.

Abstract: Deep feature extraction and training tools and processes may facilitate extraction and understanding of deep features utilized by deep learning models. For example, imaging data may be tessellated and masked to generate a plurality of masked images. The masked images may be processed by a deep learning model to generate a plurality of masked outputs. The masked outputs may be aggregated for each cell of the tessellated image and compared to an original output for the imaging data from the deep learning model. Individual cells and associated image regions having masked outputs that correspond to the original output may comprise deep features utilized by the deep learning model.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating shift-resilient neural network outputs based on utilizing a dense pooling layer, a low-pass filter layer, and a downsampling layer of a neural network. For example, the disclosed systems can generate a pooled feature map utilizing a dense pooling layer to densely pool feature values extracted from an input. The disclosed systems can further apply a low-pass filter to the pooled feature map to generate a shift-adaptive feature map. In addition, the disclosed systems can downsample the shift-adaptive feature map utilizing a downsampling layer. Based on the downsampled, shift-adaptive feature map, the disclosed systems can generate shift-resilient neural network outputs such as digital image classifications.

Abstract: Methods and systems for wireless communication are provided. In one example, a mobile device is configured to: obtain beam support information of a plurality of cells; perform measurements of one or more signals at the mobile device based on the beam support information of the plurality of cells to support a location determination operation for the mobile device; and transmit results of the measurements of the one or more signals to at least one of a location server or to a base station to support the location determination operation. The beam support information may include: a number of beams supported at each cell of the plurality of cells, information to identify each beam of the number of beams supported at the each cell, beam width information of the each beam, and/or Positioning reference Signals (PRS) codebook information which encapsulates the beams which are enabled along various elevation and azimuth angles.

Abstract: A system and a method of position and orientation determination use an image capturing device and position and orientation sensors in user equipment such as a head mounted device “HMD”. The method may comprise receiving position measurements from the position sensor and receiving a selection of one or more anchors based on said position measurements including the position of each anchor. The position and orientation measurements may be used to determine whether any selected anchor is visible to said image capturing device based on said position and orientation measurements. Then the image capturing device may be activated to capture an image including said one or more anchors when a selected anchor is visible. The image may be analyzed to determine the position and orientation of the image capturing device relative to the one or more anchors.

Abstract: A circuit includes a controller to determine whether to prohibit entry of an end unit to a base station in a wireless communication network, the controller configured to process a media access control (MAC) management message that includes a timer value, the timer value designating a time period during which entry is prohibited.

Abstract: A method is described which includes receiving a point cloud having a plurality of data points each representing a 3D location in a 3D space, the point cloud being obtained using a detection and ranging (DAR) sensor. For each data point, associating the data point with a 3D volume containing the 3D location of the data point, the 3D volume being defined using a 3D lattice that partitions the 3D space based on spherical coordinates. For at least one 3D volume, the data points are sorted within the 3D volume based on at least one dimension of the 3D lattice; and the sorted data points are stored as a set of ordered data points. The method also includes performing feature extraction on the set of ordered data points to generate a set of ordered feature vectors and providing the set of ordered feature vectors to perform a machine learning inference task.

Abstract: A method comprising configuring a user equipment in a low activity state to operate within a radio access network wherein a radio access network notification area for the user equipment is defined based on a list of logically associated radio access network paging areas, wherein each of the logically associated radio access network paging areas is a subset of a core network tracking area identified by a paging area code value which is unique within the core network associated tracking area.

Abstract: Disclosed herein are system, method, and computer program product embodiments for estimating shipping costs of items purchased in an online market using machine learning techniques. By determining in real-time the dimensional weight of an item with reference to a machine learning model describing past transactions, a buyer and seller in the online market can finalize the transaction in real-time. The machine learning model further implements a bias within the machine learning algorithm towards heavier estimation to avoid undercharging the market participants for shipping costs. One embodiment involves using these cost-estimation techniques in the context of a local shipping feature, which allows buyers and sellers to schedule a same-day delivery by seamlessly involving a local carrier.