Abstract: A method for managing data center failures, executed by one or more processors of a leader management node, includes allocating a first data node among a first plurality of data nodes a master data node, the first plurality of data nodes being in a first data center, allocating a second data node among the first plurality of data nodes as a first backup data node, allocating one among a second plurality of data nodes as a second backup data node, the second plurality of data nodes being in a second data center, and the first data center and the second data center being located in different regions, and setting a data replication mode between the master data node, the first backup data node and the second backup data node, the data replication mode being selected from a set of modes including a first mode and a second mode.

Abstract: A generative adversarial network, a method of training a generator neural network, and a method of generating images using the generator network is provided. The generator neural network is configured to process an input comprising a noise vector and a pair of conditioning variables to generate an image according to the conditioning variables. The generator neural network includes a mixed-conditional batch normalization layer. The mixed-conditional batch normalization layer is configured to normalize a network layer output to generate a normalized network layer output, comprising transforming the network layer output in accordance with mixed-conditional batch normalization layer parameters to generate the normalized network layer output, wherein the mixed-conditional batch normalization layer parameters are computed by applying an affine transformation to the conditioning variables.

Abstract: An image synthesis method includes inputting an original image and a watermark image into a synthesis model and obtaining a synthesized image output from the synthesis model. The original image and the watermark image are respectively processed in first and second sub-models of the synthesis model and then combined, and the concatenated result is processed in a third sub-model to generate the synthesized image.

Abstract: A system includes: a training dataset including first objects of a first modality and second objects of a second modality different than the first modality, where the second objects include text that is descriptive of the first objects; a first matrix including first relevance values indicative of relevance between the first objects and the second objects, respectively; a second matrix including second relevance values indicative of relevance between the second objects and the first objects, respectively; and a training module configured to: assign ones of the second objects to bins based on distances between the ones of the objects and a query; determine a ranking measure based on a number of the ones of the second objects assigned to the bins; determine losses based on the ranking measure and the first and second matrices; determine a final loss based on the losses; train embedding functions based on the final loss.

Abstract: A confidence estimation system includes: a neural network including at least one an attention module including N heads configured to: generate attention matrices based on interactions between tokens for words in an input sequence of words, the input sequence of words including a word that is obscured; and determine the word that is obscured in the input sequence; and a confidence module configured to determine a confidence value indicative of a probability of the neural network correctly determining the word that is obscured, the confidence module determining the confidence value of the word that is obscured using a convolutional neural network that projects the attention matrices generated by the attention module over a multi-dimensional space, the attention matrices recording interactions between the tokens in the input sequence of words without information regarding the tokens for the words and the word that is obscured.

Abstract: A method extends the Trip Based Public Transit Routing algorithm to compute personalized itineraries in a multimodal network based on custom transfer speed and maximum transfer duration. The customization is done at query time. The method modifies the pruning phase and the search phase of the Trip Based Public Transit Routing algorithm to obtain Pareto front for minimizing arrival time and number of transfers, along with one optimal solution per value in the Pareto front.

Abstract: In a mechanical system with an object having a set of two or more contacts, methods are disclosed for determining object motion by computing the tangential generalized reaction impulse and force. The methods includes receiving input values that include an initial generalized position and an initial generalized velocity of the object at time t, and computing a generalized force. The methods further includes computing, respectively for the reaction impulse and force: a generalized reaction impulse and force, and a tangential generalized reaction impulse and force. The methods use the tangential generalized reaction impulse and force to, respectively, compute an end-of-interval generalized position and velocity, and a generalized acceleration, which are output for use by an application.

Abstract: A method for processing an audio signal includes setting target loudness; receiving metadata of an audio signal from a server; and adjusting the loudness of the audio signal by using the received metadata, so that the loudness of the audio signal corresponds to the set target loudness.

Abstract: A gravity compensation assembly including a main frame having one side connected to a weight body to be supported, and the other side where an inner rotation portion and an outer rotation portion spaced apart from each other and having rotation axis in an x-axis direction are coupled, an auxiliary frame having one side rotatably connected to the inner rotation portion of the main frame, and the other side where an auxiliary rotation portion having a rotation axis in the x-axis direction is coupled, and an elastic force providing having one side rotatably connected to the outer rotation portion of the main frame, and the other side coupled to the auxiliary rotation portion of the auxiliary frame, and configured to perform load compensation by an elastic force when a center of gravity changes as a relative angle of the main frame and the auxiliary frame changes may be provided.

Abstract: In a method for generating a normalized sequential model using a processor, a sequential energy-based model computed by a parameterized neural network is provided. The sequential energy-based model defines an unnormalized probability distribution over a target sequence for a context source. The normalized sequential model is generated by projecting the sequential energy-based model onto a target autoregressive model that approximates a normalized distribution associated with the sequential energy-based model.

Abstract: Security check methods and systems over a user on a vehicle may be provided. The security check method including checking an allowed security right to a destination of a vehicle for entry, detecting a security right of a user on the vehicle, and performing a security process related to getting off the vehicle, based on the security right of the user and the allowed security right may be provided.

Abstract: A chatroom providing method includes searching for a consultation product corresponding to a user request; processing payment for the consultation product selected from the result of the search; and providing a one-to-one conversation by activating a chatroom between a user and an expert who has registered the consultation product for which the payment has been completed. A guide information associated with the consultation product is configured and provided in the chatroom as a chatbot message.

Abstract: A semantic image segmentation (SIS) system includes: a semantic segmentation module trained to segment objects belonging to predetermined classes in input images using training images; and a learning module configured to selectively update at least one parameter of each of a localizer module, an encoder module, and a decoder module of the semantic segmentation module to identify objects having a new class that is not one of the predetermined classes: based on an image level class for a learning image including an object having the new class that is not one of the predetermined classes; and without a pixel-level annotation for the learning image.

Abstract: A semantic image segmentation (SIS) system includes: a neural network module trained to generate semantic image segmentation maps based on input images, the semantic image segmentation maps grouping pixels of the input images under respective class labels, respectively; a minimum entropy module configured to, at a first time, determine first minimum entropies of pixels, respectively, in the semantic image segmentation maps generated for a received image and N images received before the received image, where N is an integer greater than or equal to 1; and an adaptation module configured to selectively adjust parameters of the neural network module based on optimization of a loss function that minimizes the first minimum entropies.

Abstract: A computer-implemented method for training a neural end-to-end aspect based sentiment analysis (ABSA) system includes: inputting a batch of samples of a dataset into the neural end-to-end ABSA system, where the neural end-to-end ABSA system includes: a contextual language encoder configured to embed tokens with context; a first self-attention network configured to, based on an output of the contextual language encoder, detect an aspect term and provide a first output corresponding to the aspect term; and a second self-attention network configured to, based on the output of the contextual language encoder, detect the aspect term and provide a second output corresponding to the aspect term; and based on the inputted batch of samples and a consistency loss function, selectively adjusting weights of the neural end-to-end ABSA system based on consistent aspect term detection by the first self-attention network and the second self-attention network.

Abstract: A training system includes: an encoder module configured to receive a query image and to generate a first vector representative of one or more features in the query image using an encoder; a mixing module configured to generate a second vector by mixing a third vector, representative of one or more features in a second image that is classified as a negative relative to the query image, with a fourth vector; and an adjustment module configured to train the encoder by selectively adjusting one or more parameters of the encoder based on the first vector and the second vector.

Abstract: There is provided an apparatus for navigating a pedestrian tour including a processor circuit, a memory and a screen. The pedestrian tour includes a starting point, a first pedestrian tour zone and a second pedestrian tour zone, all of which are connected by a series of connecting paths. First and second suggested travel constraints, corresponding respectively with the first and second pedestrian tour zones, are stored in the memory. Responsive to determining that the pedestrian's actual travel within the first pedestrian tour zone will vary from the first suggested travel constraint, the processor circuit dynamically revises the second suggested travel constraint to permit the pedestrian user to execute the pedestrian tour in accordance with a preset target travel constraint for the pedestrian tour.

Abstract: Provided are an electronic device for removing an advertisement thumbnail from a display screen for providing a list of sports and an operating method of the electronic device that may retrieve an image thumbnail extracted from a game video being broadcast live, determine whether the image thumbnail is a game thumbnail or an advertisement thumbnail using a pre-trained deep learning model, and display the game thumbnail on a display screen when the image thumbnail is the game thumbnail and remove the advertisement thumbnail on the display screen when the image thumbnail is the advertisement thumbnail.

Abstract: A video transmission control method for adaptive data transmission includes predicting a network state through machine learning using information related to video transmission as a feature in a real-time video streaming environment; and determining an option for controlling video transmission on the basis of the predicted network state.

Abstract: An operating method of an electronic device includes detecting a reference timing point and a reference location within text broadcasting data and a sports play video, respectively, by mapping the text broadcasting data and the sports play video based on events occurring during sports play, detecting a target location from the reference location in the sports play video using a time interval between the reference timing point and target timing point within the text broadcasting data, and providing a target video based on the target location within the sports play video.