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: 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.

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: There is disclosed a method for using a computer to enable correction of misclassified labels in a database. The computer initially applies a dataset (including labels pointing respectively to categories) to a first classifier, which includes a first loss function. Pursuant to the initial application, the computer determines that one or more labels have been misclassified. Responsive to such determination, the computer changes the first loss function to a second loss function to form a second classifier including the second loss function. The computer then applies the dataset to the second classifier for enabling correction of the one or more misclassified labels.

Abstract: A training system includes: a model; and a training module configured to: construct a first pair of images of at least a first portion of a first human captured at different times; construct a second pair of images of at least a second portion of a second human captured at the same time from different points of view; input the first and second pairs of images to the model; the model configured to: generate first and second reconstructed images of the at least the first portion of the first human based on the first and second pairs, respectively, and the training module is configured to selectively adjust one or more parameters of the model based on: the first reconstructed image and the second reconstructed image.

Abstract: A method and system for tracking an object in an input video using online training includes a step for training a classifier model by using global pattern matching, and a step for classifying and tracking each target through online training including the classifier model.

Abstract: A method includes: performing unsupervised pre-training of a model, the model including and a decoder including: obtaining a first image and a second image under different conditions or from different viewpoints; encoding, by the encoder, the first image into a representation of the first image and the second image into a representation of the second image; transforming the representation of the first image into a transformed representation; decoding, by the decoder, the transformed representation into a reconstructed image, where the transforming of the representation of the first image and the decoding of the transformed representation is based on the representation of the first image and the representation of the second image; and adjusting one or more parameters of at least one of the encoder and the decoder based on minimizing a loss; and fine-tuning the model, initialized with a set of task specific encoder parameters, for a geometric vision task.

Abstract: A motion generation system includes: a model configured to generate latent indices for a sequence of images including an entity performing an action based on an action label and a duration of the sequence; and a decoder module configured to: decode the latent indices and to generate the sequence of images including the entity performing the action based on the latent indices; and output the sequence of images including the entity performing the action to a display control module configured to display the sequence of images including the entity performing the action sequentially on a display.

Abstract: An information retrieval training system includes: a training dataset including training data having a feature space; the training data including multiple different types of elements, wherein no labels are provided with the training data; a training module configured to: maintain fixed a pre-trained model configured to receive features of queries; learn sets of pseudo-labels based on the training data; train parameters of adaptor modules for each of the sets of pseudo-labels, respectively, the adaptor modules configured to receive outputs of the pre-trained model, respectively; and train parameters of fusion modules based on neighboring pairs of the training data, the fusion modules configured to fuse together outputs of the adaptor modules, respectively.

Abstract: A system includes: a depth module including an encoder and a decoder and configured to: receive a first image from a first time from a camera; and based on the first image, generate a depth map including depths between the camera and objects in the first image; a pose module configured to: generate a first pose of the camera based on the first image; generate a second pose of the camera for a second time based on a second image; and generate a third pose of the camera for a third time based on a third image; and a motion module configured to: determine a first motion of the camera between the second and first times based on the first and second poses; and determine a second motion of the camera between the second and third times based on the second and third poses.

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 a computer system for transmitting audio content to realize a user-customized being-there and a method thereof. The computer system may be configured to detect audio files that are generated for a plurality of objects at a venue, respectively, and metadata including spatial features that are set for the objects at the venue, respectively, and to transmit the audio files and the metadata for a user. An electronic device of the user may realize a being-there at the venue by rendering the audio files based on the spatial features in the metadata. That is, the user may feel a user-customized being-there as if the user directly listens to audio signals generated from corresponding objects at a venue in which the objects are provided.

Abstract: A question answering system includes: a neural network tokenizer module configured to determine a token representation of a question to be answered and token representations of candidate paragraphs of a present reasoning path for the question, respectively; a neural network module configured to: transform the token representation of the question and the token representations of the candidate paragraphs of the present reasoning path into vector representations; and append a first variable to the vector representations to produce a second variable; a search module configured to: select the candidate paragraphs from a knowledge database to extend a present reasoning path based on lexical relevance of the candidate paragraphs to the question; and selectively add ones of the candidate paragraphs to the present reasoning path; and an answer inference network module configured to selectively determine an answer to the question based on multiple different portions of the present reasoning path.

Abstract: A computer-implemented method of determining a position of a portable electronic device in an indoor environment includes: at a first rate, updating an absolute position of a portable electronic device within the indoor environment based on at least one of radio signal data and magnetic field data captured using the portable electronic device; at a second rate that is different than the first rate, selectively updating an estimated displacement of the portable electronic device within the indoor environment, the updating the estimated displacement comprising generating an estimated displacement, by a neural network module, based on inertial sensor data of the portable electronic device; and determining a present position of the portable electronic device within the indoor environment by updating a previous position based on at least one of (a) the estimated displacement and (b) the absolute position.

Abstract: Provided are a computer system for producing audio content for realizing a user-customized being-there and a method thereof. The computer system may be configured to generate audio files based on respective audio signals that are respectively generated from a plurality of objects at a venue, set spatial features at the venue for the objects, respectively, using a production tool, and generate metadata for the audio files based on the spatial features. An electronic device may realize a being-there at the venue by rendering the audio files based on the spatial features in the metadata. That is, a user of the electronic device may feel a user-customized being-there as if the user directly listens to audio signals generated from corresponding objects at a venue in which the objects are provided.

Abstract: A method by a computer system including generating audio files based on respective audio signals, the audio signals having been respectively generated from a plurality of objects at a venue, generating metadata including spatial features at the venue that are respectively set for the objects, and transmitting the audio files and the metadata for the objects to a first electronic device to cause the first electronic device to realize a being-there at the venue by rendering the audio files based on the spatial features in the metadata may be provided.