Abstract: A method and system for editing a video on the basis of a context obtained using artificial intelligence. According to an embodiment of the present invention, the method for editing a video may comprise the steps of: establishing a plurality of contexts for an input video by analyzing the video through an artificial intelligence model, and taking, from the video, a plurality of clips corresponding to the established plurality of contexts; generating a user interface through which to receive a certain context selected from the plurality of contexts; providing, through the generated user interface, a plurality of clips that has been taken from the video for the context selected from the plurality of contexts through the generated user interface; and generating a highlight image for the selected context for the video by merging clips together that have been selected from the plurality of clips provided through the user interface.

Abstract: A method for automatically generating, in real-time, for display on a display, a simplified network layout from an initial network layout including one or more lines each connecting a plurality of nodes. Graph information is provided indicating vertices representing geographic positions of the nodes and edges representing connections between the nodes. The nodes are repositioned to optimize an objective function based on readability of the simplified network layout. Nodes and edges are discretized using interpolation to align a plurality of the nodes and connect the aligned nodes using simplified k-linear segments, where k-linear segments are parallel to one of k equidistant orientations whose angles are multiples of 180/k degrees, with k larger or equal to two. The simplified network layout is provided for a display.

Abstract: A training system includes: a training dataset including first objects of a first modality and second objects of a second modality that are associated with the first objects, respectively; 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: based on similarities between ones of the second objects, generate a third matrix by selectively adding first additional relevance values to the first matrix; based on the similarities between the ones of the second objects, generate a fourth matrix by selectively adding second additional relevance values to the second matrix; and store the third and fourth matrices in memory of a search module for cross-modal retrieval in response to receipt of search queries.

Abstract: Method and apparatus for analyzing an online behavior of a user accessing a web server include: collecting, when a user terminal accesses a web server and forms a session, log data corresponding to a behavior performed by the user terminal in the session in real time; detecting log data corresponding to a trigger log among the log data; extracting, when the trigger log is detected, log data cumulated up to a detection time point of the trigger log from a start time point of the session and generating cumulative log data; and performing pattern analysis on the cumulative log data and generating behavior information corresponding to the behavior of the user terminal.

Abstract: Provided are a method and apparatus for generating a bundle invitation link. The method includes obtaining a plurality of invitation links from a first user terminal, each of the plurality of invitation links being connected to at least one community, generating a bundle invitation link connected to a detail page, the detail page including the plurality of invitation links, transmitting the bundle invitation link to a second user terminal, causing a display of the second user terminal to display the detail page in response to receiving, from the second user terminal, an input corresponding to the bundle invitation link, and receiving a data pair from the second user terminal, the data pair including at least one invitation link and an identification value of the second user terminal, and the at least one invitation link being selected from among the plurality of invitation links included in the detail page.

Abstract: An autonomous system includes: a first semantic segmentation model trained based on a training dataset including images and labels for the images, the first semantic segmentation model configured to generate a first segmentation map based on an image from a camera; a second semantic segmentation model of the same type of semantic segmentation model as the first semantic segmentation model, the second semantic segmentation model configured to generate a second segmentation map based on the image from the camera; an adaptation module configured to selectively adjust one or more first parameters of the second semantic segmentation model; and a reset module configured to: determine a first total number of unique classifications included in the first segmentation map; determine a second total number of unique classifications included in the first segmentation map; and selectively reset the first parameters to previous parameters, respectively, based on the first and second total numbers.

Abstract: A summarization system includes: K embedding modules configured to: receive K blocks of text, respectively, of a document to be summarized; and generate K first representations based on the K blocks of text, respectively, where K is an integer greater than 2; a first propagation module configured to generate second representations based on the K first representations; a second propagation module configured to generate third representations based on the second representations; an output module configured to select ones of the K blocks based on the third representations; and a summary module configured to generate a summary of the document from text of the selected ones of the K blocks.

Abstract: A speed estimation system includes: a detection module configured to determine bounding boxes of an object moving on a surface in images, respectively, captured using a camera; a solver module configured to, based on the bounding boxes, determine a homography of the surface by solving an optimization problem, where the solver module is not trained; and a speed module configured to, using the homography, determine a speed that the object is moving on the surface.

Abstract: A computer-implemented method of recognition of actions performed by individuals includes: by one or more processors, obtaining images including at least a portion of an individual by the one or more processors, based on the images, generating implicit representations of poses of the individual in the images; and by the one or more processors, determining an action performed by the individual and captured in the images by classifying the implicit representations of the poses of the individual.

Abstract: A method and system for preprocessing and query stages for a trip-based public transit routing algorithm, which is used for multimodal routing computations, clusters the public transit network and computes relevant network parts when transiting between different clusters in order to prune the search at query time. The processing phase is modified to use only a subset of the network, depending on the clusters associated to the origin and destination locations.

Abstract: A method for a language model applies in-context learning to detect problematic text and reformulate the problematic text to correct problematic text by (a) receiving, in the language model, a user generated text example; (b) determining if the user generated text example is a problematic text having a determined classification; (c) reformulating the user generated text example if the text example is a problematic text having the determined classification; (d) outputting the user generated text example if the text example is determined to be not a problematic text having the determined classification; and (e) outputting the reformulated text example if the text example is determined to be a problematic text having the determined classification.

Abstract: A method of training a hypergraph convolutional network (HGCN) includes: receiving training data including search instances and recommendation instances; constructing a hypergraph from the training data, where each node of the hypergraph represents one of a user profile, a query term, and a content item, and where the hypergraph represents each of the search instances and each of the recommendation instances as a hyperedge linking corresponding ones of the nodes; initializing base embeddings associated with the hypergraph nodes; propagating the base embeddings through one or more convolutional layers of the HGCN to obtain, for each of the convolutional layers, respective embeddings of the nodes of the hypergraph; computing, based on the base embeddings and the respective embeddings obtained from each of the one or more convolutional layers: a first loss; and a second loss; and selectively updating ones of the base embeddings based on the first and second losses.

Abstract: A method of jointly training of a transferable feature extractor network, an ordinal regressor network, and an order classifier network in an ordinal regression unsupervised domain adaption network by providing a source of labeled source images and unlabeled target images; outputting image representations from a transferable feature extractor network by performing a minimax optimization procedure on the source of labeled source images and unlabeled target images; training a domain discriminator network, using the image representations from the transferable feature extractor network, to distinguish between source images and target images; training an ordinal regressor network using a full set of source images from the transferable feature extractor network; and training an order classifier network using a full set of source images from said transferable feature extractor network.

Abstract: A training system includes: a neural network configured to, using trained parameters, generate a first encoding based on an input query and second encodings based on candidate responses for the input query; and a training module configured to: train the trained parameters using hyperparameters; and jointly optimize the hyperparameters using coordinate descent and line searching, the hyperparameters including: a first hyperparameter indicative of a first weight value to apply based on positive interactions of entries of a distance matrix based on encodings; a second hyperparameter indicative of a second weight value to apply based on negative interactions of entries of the distance matrix generated based on the first and second encodings; and a third hyperparameter corresponding to a dimension of the distance matrix generated based on the first and second encodings.

Abstract: Methods for training a neural sequence-to-sequence (seq2seq) model. A processor receives the model and training data comprising a plurality of training source sequences and corresponding training target sequences, and generates corresponding predicted target sequences. Model parameters are updated based on a comparison of predicted target sequences to training target sequences to reduce or minimize both a local loss in the predicted target sequences and an expected loss of one or more global or semantic features or constraints between the predicted target sequences and the training target sequences given the training source sequences. Expected loss is based on global or semantic features or constraints of general target sequences given general source sequences.

Abstract: A method for ranking a set of objects includes: receiving the set of objects to rank, a relevance score for each object, and a set of objective functions; based on the relevance scores for the objects, defining a decision space having n decision variables using a polytope, where n is the number of objects to rank and where vertices of the polytope represent permutations of exposures provided to the objects in the set by corresponding rankings; determining a Pareto-set for the set of objective functions; based on a Pareto-optimal point in the Pareto-set, determining a distribution over rankings for the objects in the set using the decision space, where a proportion is associated with each ranking in the distribution; selecting a sequence of rankings for the objects in the set based on the distribution in accordance with their proportions; and outputting the selected sequence of rankings of the objects.

Abstract: A user tracking method includes collecting cookies in a log according to a user action on the Internet and collecting chain information by Internet communication as third information different from the cookie, and grouping cookies based on the chain information.

Abstract: A method for providing a sports team ranking, including receiving a plurality of sports search terms input from a plurality of user terminals, clustering the plurality of sports search terms into a plurality of events including a first event and a second event, calculating a score for the first event based on a number of searches of each of a first set of sports search terms included in the first event, and associating the first event with a first sports team.

Abstract: A computer-implemented method for training an artificial neural network with training data including samples and corresponding labels for performing a task includes: pre-training the artificial neural network to generate matrix representations that are invariant to a predetermined set of data augmentations applied to a sample, where the artificial neural network includes an encoder module and a projection module configured to generate the matrix representations based on ones of the samples, respectively; and after the pre-training, fine-tune training the artificial neural network using a loss function, wherein fine-tuning the artificial neural network includes adjusting, based on the labels, one or more weights of the projection module while maintaining constant weights of the encoder module, and where the loss function is based on a logit adjustment loss that is based on logits that are adjusted based on a class distribution of the training data.