Abstract: The present invention relates to a method for learning class descriptors for the detection and the automatic location of objects in a video, each object belonging to a class of objects from among a set of classes, the method using: a learning base, composed from reference videos and containing annotated frames each comprising one or more labels identifying each object detected in the frames, descriptors associated with these labels and learned previously by a preprocessing neural network from the annotated frames of the learning base, an architecture of neural networks defined by parameters centralized on a plurality of parameter servers, and a plurality of computation entities working in parallel, a method in which, for each class of objects, one of the neural networks of the architecture is trained by using as input data the descriptors and the labels to define class descriptors, each computation entity using, for the computation of the class descriptors, a version of the parameters of the parameter ser

Abstract: Embodiments of the present disclosure provide a method and apparatus for extracting image data in parallel from multiple convolution windows, a device, and a computer-readable storage medium. The method includes: dividing an image into multiple groups of convolution windows, where the multiple groups of convolution windows include a first group of convolution windows and a second group of convolution windows, and each group of convolution windows include multiple convolution windows. The method further includes extracting image data in parallel from multiple convolution windows in the first group of convolution windows by using multiple data processing units, and extracting, after the extraction of image data from the first group of convolution windows is completed, image data from multiple convolution windows in the second group of convolution windows in parallel by using the multiple data processing units.

Abstract: Disclosed is a mobile device and a control method thereof. The mobile device includes a communication interface configured to perform communication via a network; a display configured to display an image; and a processor.

Abstract: An image processing device has a function for plotting a luminance gradient co-occurrence pair of an image on a feature plane and applying an EM algorithm to form a GMM. The device learns a pedestrian image and creates a GMM, subsequently learns a background image and creates a GMM, and calculates a difference between the two and generates a GMM for relearning based on the calculation. The device plots a sample that conforms to the GMM for relearning on the feature plane by applying an inverse function theorem. The device forms a GMM that represents the distribution of samples at a designated mixed number and thereby forms a standard GMM that serves as a standard for image recognition. When this mixed number is set to less than a mixed number designated earlier, the dimensions with which an image is analyzed are reduced, making it possible to reduce calculation costs.

Abstract: Systems, methods, and computer-readable media for context-aware synthesis for video frame interpolation are provided. A convolutional neural network (ConvNet) may, given two input video or image frames, interpolate a frame temporarily in the middle of the two input frames by combining motion estimation and pixel synthesis into a single step and formulating pixel interpolation as a local convolution over patches in the input images. The ConvNet may estimate a convolution kernel based on a first receptive field patch of a first input image frame and a second receptive field patch of a second input image frame. The ConvNet may then convolve the convolutional kernel over a first pixel patch of the first input image frame and a second pixel patch of the second input image frame to obtain color data of an output pixel of the interpolation frame. Other embodiments may be described and/or claimed.

Abstract: A method for supporting activation/deactivation of serving cells by a base station (BS) in a wireless communication system provides decreased overhead and decreased power consumption for a user equipment (UE). The method includes configuring M supportable serving cells in the UE, configuring an indicator indicating activation/deactivation of each of the M serving cells, configuring a medium access control (MAC) message which includes a MAC control element (CE) and a logical channel identifier (LCID), the MAC CE including the indicator configured for each of the M serving cells and having a length corresponding to an integer multiple of 8 bits, the LCID indicating that the MAC CE includes the indicator indicating activation/deactivation of each serving cell, and transmitting the configured MAC message to the UE. Accordingly, a control channel or data channel regarding a component carrier is selectively received depending on whether the component carrier is activated.

Abstract: Methods, systems, and computer program products are provided for signature verification. Signature verification may be provided for target signatures using genuine signatures. A signature verification model pipeline may extract features from a target signature and a genuine signature, encode and submit both to a neural network to generate a similarity score, which may be repeated for each genuine signature. A target signature may be classified as genuine, for example, when one or more similarity scores exceed a genuine threshold. A signature verification model may be updated or calibrated at any time with new genuine signatures. A signature verification model may be implemented with multiple trainable neural networks (e.g., for feature extraction, transformation, encoding, and/or classification).

Abstract: A tracking system for tracking movements of an object in an area using a plurality of cameras: obtains a first recognized object and first information associated with the first recognized object, where the first recognized object is detected in a first image captured by a first camera, where the first information includes a first location of the first recognized object; stores the first recognized object and the first information in a tracking object on a list of tracking objects; obtains a second recognized object and second information associated with the second recognized object, where the second recognized object is detected in a second image captured by a second camera, where the second information includes a second location of the second recognized object; compares the first information with the second information; and when matched, stores the second information comprising the second location in the tracking object.

Abstract: Aspects of the subject disclosure may include, for example, obtaining user input identifying a first user-identified network feature of a training image of a geographical region. The training image and the user-identified feature are provided to a neural network adapted to train itself according to the user-identified features to obtain a first trained result that classifies objects within the image according to the user-identified feature. The training image and the first trained result are displayed, and user-initiated feedback is obtained to determine whether a training requirement has been satisfied. If not satisfied, the user-initiated feedback is provided to the neural network, which retrains itself according to the feedback to obtain a second trained result that identifies an updated machine-recognized feature of the training image. The process is repeated until a training requirement has been satisfied, after which a map is annotated according to the machine-recognized feature.

Abstract: The present invention relates to representing image features used by a convolutional neural network (CNN) to identify concepts in an input image. The CNN includes a plurality of filters in each of a plurality of layers. The method generates the CNN based on a set of images for training with predetermined concepts in regions of the set of images. For a select layer of the CNN, the method generates integrated maps, Each integrated map is based on a set of feature maps in a cluster and relevance between the set of feature maps for the select layer and a region representing one of the features in the image data. The method provides a pair of a feature representation visualization image of a feature in the select layer and a concept information associated with the integration map.

Abstract: Methods and apparatuses for verifying HeNB. A method reduces and/or avoids affecting the operator's network due to the attack from HeNB, and ensures the safety of the users who have accessed the network.

Abstract: The present disclosure relates to a method, device, computer readable media, and electronic devices for identifying a traffic light signal from an image. The method for identifying a traffic light signal from an image includes extracting, based on a deep neural network, multiple layers of first feature maps corresponding to different layers of the deep neural network from the image. The method includes selecting at least two layers of the first feature maps having different scales from the multiple layers of the first feature maps. The method includes inputting the at least two layers of the first feature maps to a convolution layer having a convolution kernel matching a shape of a traffic light to obtain a second feature map. The method includes obtaining a detection result of the traffic light signal based on the second feature map.

Abstract: A vision system for detecting free space in front of a motor vehicle includes a mono imaging apparatus (11) adapted to capture images (30) from the surrounding of a motor vehicle, and an electronic processing device (14) adapted to perform image processing of images (30) captured by the mono imaging apparatus (11) in order to detect objects in the surrounding of a motor vehicle. The electronic processing device (14) is adapted to calculate a horizontal component of the optical flow (31), and to determine transitions (33, 35) between regions of essentially constant horizontal optical flow and regions of essentially non-constant horizontal optical flow.

Abstract: An artificial intelligence moving agent is provided. The artificial intelligence moving agent includes: a camera configured to photograph an image, and a processor configured to photograph an object, acquire type information of the object by providing an image of the photographed object to an artificial intelligence model, acquire correction type information designated by a user with respect to the image of the photographed object, and train the artificial intelligence model by using the correction type information.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for recognizing a body movement. A specific embodiment of the method includes: sampling an input to-be-recognized video to obtain a sampled image frame sequence of the to-be-recognized video; performing key point detection on the sampled image frame sequence by using a trained body key point detection model, to obtain a body key point position heat map of each sampled image frame in the sampled image frame sequence, the body key point position heat map being used to represent a probability feature of a position of a preset body key point; and inputting body key point position heat maps of the sampled image frame sequence into a trained movement classification model to perform classification, to obtain a body movement recognition result corresponding to the to-be-recognized video.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods provide systems and methods for automatically creating a caption comprising a sequence of words in connection with digital content.

Abstract: An image generation method and a computing device employing the method includes: acquiring a plurality of original images; and processing the plurality of original images to obtain a training data set. An anti-neural network model is trained according to the training data set. A candidate image is generated through the trained anti-neural network model. The candidate image is complemented through a detail completion network model to obtain a target image according to a comparison image. Thereby, a style of the generated image is the same as that of the comparison image. A more realistic image can be randomly generated saving the time and energy of artificially creating an image.

Abstract: Techniques are discussed for determining a data level for portions of data for processing. In some cases, a data level can correspond to a resolution level, a compression level, a bit rate, and the like. In the context of image data, the techniques can determine a region of first image data to be processed a high resolution and a region of second image data to be processed at a low resolution. The regions can be determined by a machine learned algorithm that is trained to output identifications of such regions. Training data may be determined by identifying differences in outputs based on the first and second image data. The image data associated with the determined regions and the determined resolutions can be processed to perform object detection, classification, segmentation, bounding box generation, and the like, thereby conserving processing, bandwidth, and/or memory resources in real time systems.

Abstract: An encoding device and a decoding device is disclosed. The encoding device includes a processor and a communication interface. The processor is configured to generate, for a 3D point cloud, a first frame representing a first attribute and a second frame representing a second attribute. The first and second frames include patches representing respective clusters of points from the 3D point cloud. The processor is configured to generate an occupancy map frame. The processor is configured to identify a query point that is positioned on a boundary of one of the patches. The processor is configured to perform smoothing with respect to the query point. The processor is configured to encode the frames and generate a compressed bitstream. The communication is configured to transmit the compressed bitstream.

Abstract: A hardware circuit in which integer numbers are used to represent fixed-point numbers having an integer part and a fractional part is disclosed. The hardware circuit comprises a multiply-accumulate unit configured to perform convolution operations using input data and weights and, in dependence thereon, to generate an intermediate result. The hardware circuit comprises a bias bit shifter configured to shift a bias value bitwise by a bias shift value so as to provide a bit-shifted bias value, a carry bit shifter configured to shift a carry value bitwise by a carry shift value so as to provide a bit-shifted carry value, an adder tree configured to add the intermediate result, the bit-shifted bias value and the bit-shifted carry value so as to provide a multiple-accumulate result and a multiply-accumulate bit shifter configured to shift the multiple-accumulate result bitwise by a multiply-accumulate shift value) to provide a bit-shifted multiply-accumulate result.