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 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 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 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: 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: 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.

Abstract: A robot joint device including first and second plates positioned in parallel, links each having a first end connected to the first plate and a second end connected to the second plate, connecting members configured to connect the two first and second ends of each of the links and the first and second plates, respectively, so that angles and rotations of the links are adjustable relative to the first and second plates, a rotary shaft having two ends penetrating the first and second plates and rotatably installed, a gear reduction unit installed in the first plate and connected to the first end of the rotary shaft, and a pulley connected to the second end of the rotary shaft and configured to transmit driving power to the rotary shaft may be provided.

Abstract: A system for generating whole body poses includes: a body regression module configured to generate a first pose of a body of an animal in an input image by regressing from a stored body anchor pose; a face regression module configured to generate a second pose of a face of the animal in the input image by regressing from a stored face anchor pose; an extremity regression module configured to generate a third pose of an extremity of the animal in the input image by regressing from a stored extremity anchor pose; and a pose module configured to generate a whole body pose of the animal in the input image based on the first pose, the second pose, and the third pose.

Abstract: Provided is a method and system for an information providing interface based on new user experience. An information providing interface method includes providing a home board including a search box as an initial interface screen for providing information; providing a first content board according to movement from the home board in a first direction or a second content board according to movement in a second direction that is opposite to the first direction in response to an input event on the home board; and visually displaying a shortcut icon for each board and a currently staying board through a partial area of a screen in response to movement from the first content board or the second content board. Each of the first and the second content boards includes a plurality of subpages and each of the subpages includes a different type of content and movement between subpages is allowed.

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: An audio record management method includes linking an app dedicated for audio record management installed in a first device and a website dedicated for audio record management connected to a second device; displaying an audio file being recorded or being played back in the app on a file list on the website through linkage between the app and the website; and providing a memo creation screen for the audio file on the website in response to a selection of the audio file from the file list.

Abstract: A training system includes: a neural network model configured to determine three-dimensional coordinates of joints, respectively, representing poses of animals in images, where the neural network model is trained using a first training dataset including: images including animals; and coordinates of joints of the animals in the images, respectively; and a training module configured to, after the training of the neural network model using the first training dataset, train the neural network model using a second training dataset including motion capture data, where the motion capture data does not include images of animals and includes measured coordinates at points, respectively, on animals.

Abstract: Disclosed is a method and system, the method including extracting similar and dissimilar document pair sets from a document database, the similar document pair set including similar document pairs having a common attribute, and the dissimilar document pair set including dissimilar document pairs extracted randomly, calculating a mathematical similarity for each of the similar and dissimilar document pairs using a mathematical measure to obtain a first and second mathematical similarities, calculating a semantic similarity for each of the similar and dissimilar document pairs to obtain a first and second semantic similarities, the first semantic similarities being higher than the first mathematical similarities, and the second semantic similarities being lower than the second mathematical similarities, training a similarity model based on the similar and dissimilar document pairs, and the first and second semantic similarities to obtain a trained similarity model, and detecting a duplicate document using the t

Abstract: There is disclosed a computer-implemented method for detecting machine-generated documents in a collection of documents including machine-generated and human-authored documents. The computer-implemented method includes computing a set of long-repeated substrings (such as super-maximal repeats) with respect to the collection of documents and using a subset of the long-repeated substrings to designate documents containing the subset of the repeated substrings as machine-generated. The documents designated as machine-generated serve as positive examples of machine-generated documents and a set of documents including at least one human-authored document serves as negative examples of machine-generated documents. A plurality of classifiers are trained with a dataset including both the positive and negative examples of machine-generated documents. Classified output of the classifiers is then used to detect an extent to which a given document of the dataset is machine-generated.

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.