Abstract: Disclosed are a liveness determining method and apparatus and a method and apparatus for training the liveness determining apparatus. The liveness determining method includes extracting, by a processor, a feature from an input fingerprint image, inputting the feature into the current layer classifier, inputting the feature into the subsequent layer classifier, based on a determination that an output of the current layer classifier is live, and determining a liveness of the input fingerprint image to be false, based on a determination that an output of the subsequent layer classifier is fake, wherein the current layer classifier and the subsequent layer classifier are respectively trained based on a plurality of training fake images belonging to different groups.

Abstract: A class labeling system for autonomous driving includes a detection module, a segmentation module, and a lane road boundary detection module. The detection module is configured to detect objects for autonomous driving from an image captured by a camera to generate a bounding box for each of the objects and detect property information about the object. The segmentation module is configured to determine classes for each pixel of the bounding box detected by the detection module and process at least one of the classes as don't care. The lane road boundary detection module is configured to detect at least one of lane and road boundaries using the bounding box detected by the detection module.

Abstract: The present disclosure relates to passive optical network (PON) systems, an optical line terminal (OLT), and an optical network unit (ONU). One example PON system includes an OLT and at least two ONUs, and the OLT and the ONUs exchange data on one downstream channel and two upstream channels. The OLT sends downstream data to each ONU on the downstream channel, where the downstream data includes an upstream bandwidth grant which is used to control the ONU to send upstream data. Each ONU receives the downstream data on the downstream channel, and sends the upstream data on a first upstream channel or a second upstream channel based on the upstream bandwidth grant included in the downstream data. The OLT receives, on the first upstream channel and the second upstream channel, the upstream data sent by each ONU.

Abstract: An analogy generating system includes one or more image databases that include a first set of images depicting a first symbolic class and a second set of images depicting a second symbolic class and an autoencoder that receive images from the first set of images and the second set of images; determines a first characteristic shared between the first symbolic class and the second symbolic class using a first node from multiple nodes on a neural network; determine a second characteristic shared between the first symbolic class and the second symbolic class using a second node from multiple nodes on the neural network; and exchange the first characteristic and the second characteristic between the first node and the second node to establish an analogy between the first symbolic class and the second symbolic class.

Abstract: According to an embodiment, a collation device includes a hardware processor configured to: generate, based at least in part on input data, an input vector comprising input data features indicating features of the input data, the input data features comprising D number of features, D being an integer equal to or larger than two; and generate first specification information that specifies d selected features among the input data features of the input vector, based at least in part on a plurality of reference vectors and the input vector, the plurality of reference vectors each comprising reference features in the same form as the input vector, the reference features comprising the D number of features, d being an integer equal to or larger than one and smaller than D.

Abstract: Embodiments include a method, an electronic device, and a computer program product for information processing. In an example embodiment, a method for information processing includes: acquiring, at a first device, a first feature associated with a target object; applying the first feature to a trained first model deployed at the first device to determine a first confidence coefficient, the first confidence coefficient being associated with probabilities that the first model determines the target object as a real object and as a false object; if the first confidence coefficient is lower than a first threshold confidence coefficient, sending a request for verifying the target object to a second device, the second device being deployed with a trained second model for verifying the target object, and the second model being more complex than the first model; and updating the first model based on a response to the request.

Abstract: Aspects of the subject disclosure may include, for example, obtaining a first plurality of inputs that identify a plurality of geographical locations and a plurality of infrastructure located at the plurality of geographical locations, classifying each of the plurality of geographical locations in accordance with the first plurality of inputs to obtain a plurality of classes, obtaining a second plurality of inputs that identify costs, revenue, profits, or any combination thereof, associated with the plurality of infrastructure, processing the second plurality of inputs in conjunction with the plurality of classes to identify a first plurality of locations included in the plurality of geographical locations to decommission infrastructure included in the plurality of infrastructure, and presenting the first plurality of locations via a device. Other embodiments are disclosed.

Abstract: A power over fiber system includes a power sourcing equipment, a powered device, an optical fiber cable and a controller. The power sourcing equipment includes semiconductor lasers. The semiconductor lasers output feed light of different wavelengths by oscillating with electric power. The powered device includes photoelectric conversion elements. The photoelectric conversion elements have different photoelectric conversion efficiencies and convert the feed light output from the power sourcing equipment into electric power with their respective photoelectric conversion efficiencies. The optical fiber cable transmits the feed light from the power sourcing equipment to the powered device. The controller performs a process of selecting and activating one of the semiconductor lasers and a process of selecting and activating one of the photoelectric conversion elements in order that the power over fiber system perform predetermined power supply.

Abstract: A processing device includes a first processor configured to detect a bounding box of a distant vehicle, in an input image generated by imaging the distant vehicle, and extract at least one feature of the distant vehicle. A second processor is configured to estimate a geometry of a road on which the distant vehicle is located, based on a position of at least one feature relative to at least a portion of the bounding box.

Abstract: The present disclosure discloses a visual relationship detection method based on adaptive clustering learning, including: detecting visual objects from an input image and recognizing the visual objects to obtain context representation; embedding the context representation of pair-wise visual objects into a low-dimensional joint subspace to obtain a visual relationship sharing representation; embedding the context representation into a plurality of low-dimensional clustering subspaces, respectively, to obtain a plurality of preliminary visual relationship enhancing representation; and then performing regularization by clustering-driven attention mechanism; fusing the visual relationship sharing representations and regularized visual relationship enhancing representations with a prior distribution over the category label of visual relationship predicate, to predict visual relationship predicates by synthetic relational reasoning.

Abstract: A non-transitory computer-readable medium encoded with a computer-readable program which, when executed by a first processor, will cause a computer to execute a method of authenticating a user, the method including training a plurality of models. The method additionally includes sending, by a computer, an acoustic signal. Further, the method includes receiving, by the computer, a reflected acoustic signal, wherein the reflected acoustic signal comprises information about a signature. Moreover, the method includes receiving, by the computer, motion data about the information about the signature. The method additionally includes comparing the information about the signature to a model to generate a score. Additionally, the method includes deciding, based on the score, if the information about the signature is within a predetermined tolerance level.

Abstract: Improved techniques for determining an object's 3D orientation. An image is analyzed to identify a 2D object and a first set of key points. The first set defines a first polygon. A 3D virtual object is generated. This 3D virtual object has a second set of key points defining a second polygon representing an orientation of the 3D virtual object. The second polygon is rotated a selected number of times. For each rotation, each rotated polygon is reprojected into 2D space, and a matching score is determined between each reprojected polygon and the first polygon. A specific reprojected polygon is selected whose corresponding matching score is lowest. The orientation of the 3D virtual object is set to an orientation corresponding to the specific reprojected polygon. Based on the orientation of the 3D virtual object, an area of focus of the 2D object is determined.

Abstract: Novel tools and techniques are provided for implementing visual impairment detection for free-space optical communication (“FSOC”) systems. In various embodiments, a computing system might receive, either from a camera or from a database, images (and/or videos) of an optical field of view (“FOV”) of the camera, the optical FOV comprising an optical beam(s) of a first FSOC system; might autonomously analyze the captured images (and/or videos) to determine whether an object(s) is moving within proximity to an optical beam(s) of the first FSOC system, to perform at least one of reactive learning or proactive learning regarding potential interruption of the optical beam(s) of the first FSOC system, and/or to determine one or more preventative measures to prevent interruption of the optical beam(s) of the first FSOC system; and might autonomously initiate one or more first tasks and/or the one or more preventative measures, based on the analysis.

Abstract: An image segmentation model training apparatus according to a disclosed embodiment includes a predictor, which generates a plurality of original masks using an unlabeled original image set and a pre-trained image segmentation model, a label generator, which generates a synthesized image set based on the original image set and the plurality of original masks, and generates a plurality of pseudo labels based on the synthesized image set, a pre-processor, which generates a training image set by performing pseudo labeling on the original image set and the synthesized image set using the plurality of pseudo labels, and a model trainer, which further trains the image segmentation model based on the training image set.

Abstract: Techniques for automatic image tagging and selection at a mobile device include generating a smart image tagging model by first training an initial model based on different angles of image capture of subject vehicles, and then re-training the trained model using weights discovered from the first training and images that have been labeled with additional tags indicative of different vehicle portions and/or vehicle parameters. Nodes that are training-specific are removed from the re-trained model, and the lightweight model is serialized to generate the smart image tagging model. The generated model may autonomously execute at an imaging device to predict respective tags associated with a stream of frames; select, capture and store respective suitable frames as representative images corresponding to the predicted tags; and provide the set of representative images and associated tags for use in determining vehicle damage, insurance claims, and the like.

Abstract: In order to provide a submarine optical transmission system that utilizes multiple wavelength bands, the submarine branching apparatus is provided with: a first demultiplexing part for demultiplexing a wavelength-multiplex optical signal input from a first terminal station into a first wavelength-multiplex optical signal and a second wavelength-multiplex optical signal; an optical add-drop part for outputting at least a third wavelength-multiplex optical signal included in the first wavelength-multiplex optical signal to a second terminal station, and for outputting a fifth wavelength-multiplex optical signal by multiplexing at least a fourth wavelength-multiplex optical signal included in the first wavelength-multiplex optical signal with a wavelength-multiplex optical signal input from the second terminal station; and a first multiplex part for multiplex the second wavelength-multiplex optical signal with the fifth wavelength-multiplex optical signal input from the optical add-drop part and outputting the r

Abstract: In one example, the present disclosure describes a device, computer-readable medium, and method for enabling secure video sharing by exploiting data sparsity. In one example, the method includes applying a transformation to a video dataset containing a plurality of video samples, to produce a plurality of sparse vectors in a first dimensional space, wherein each sparse vector of the plurality of sparse vectors corresponds to one video sample of the plurality of video samples, and multiplying each sparse vector of the plurality of sparse vectors by a transformation matrix to produce a plurality of reduced vectors in a second dimensional space, wherein the dimension of the second dimensional space is smaller than a dimension of the first dimensional space, and wherein the plurality of reduced vectors in the second dimensional space hides information about the video dataset while preserving relational properties between the plurality of video samples.

Abstract: Wireless data communication between two devices is described. In an example implementation, an image frame displayed on a display unit of a transmitting device is captured by a camera of a receiving device, where the image frame comprises text characters converted from binary data bits based on a text mapping table. The text characters in the captured image frame are converted to the binary data bits based on the text mapping table by the receiving device.

Abstract: An image processing apparatus including: at least one memory; and at least one processor coupled to the at least one memory and configured to implement: an image acquisition module configured to acquire an input image including an object region; a mask image generation module configured to generate a mask image based on the input image; and an image inpainting module configured to extract a fusion feature map corresponding to the input image using an encoding network according to the input image and the mask image, and to inpaint the object region in the input image using a decoding network based on the fusion feature map, to obtain an inpainting result.

Abstract: A mask structure optimization device includes a classification target image size acquisition unit that is configured to acquire a size of a classification target image which is an image including a classification target, a mask size setting unit that is configured to set a size of a mask applied to the classification target image, a brightness detection unit that is configured to detect a brightness of each pixel within the classification target image at a position on an opposite side of the mask from the classification target image, a sum total brightness calculation unit that is configured to calculate the sum total brightness of the each pixel within the classification target image detected by the brightness detection unit, an initial value setting unit that is configured to set an initial value for a mask pattern of the mask, and a movement unit that is configured to relatively move the mask with respect to the classification target image.