Abstract:
Disclosed is an apparatus and method for extracting topics. The apparatus for extracting topics extracts an initial topic from a document using an LDA (latent Dirichlet allocation) and corrects topics which are duplicated and extracted or mixed through a similarity comparison between words included in the extracted initial topic, thereby extracting a final topic of the document.
Abstract:
Disclosed are an apparatus and method for classifying a product type. The apparatus for classifying the product type calculates a utilitarian and hedonic index, a word similarity, or an emotion index which is an objective index capable of determining a type of a product using a word that appears in reviews of the product, and classifies the type of a corresponding product using the calculated utilitarian and hedonic index, word similarity, or emotion index.
Abstract:
The present invention relates to an activity recognition apparatus and method in sports videos using CGAM. According to the present invention, the apparatus for recognizing an activity in a sports video using CGAM (cross granularity accumulation module) comprises an object feature extraction unit that receives a video to be analyzed into a temporal attention module (TAM) in frame units to distinguish importance between frames, sequentially inputs the frames distinguished by importance into a plurality of convolution blocks and each spatial attention module (CBAM) placed between convolution blocks to output a first feature value, outputs a second feature value by a CGAM that generates an object representation by compressing different object information output from each spatial attention module, and extracts an object feature value by multiplying the first feature value and the second feature value; and an activity feature extraction unit that sequentially inputs the extracted object feature values into a recurrent neural network (RNN) and a fully-connected (FC) layer and classifies a final activity from a probability value for each activity estimated using a sigmoid function.
Abstract:
A curling analysis method includes a step of providing a game information input interface for inputting game information in an order of progress of a curling game, a step of outputting analysis information according to the input game information based on stored accumulative curling game information, and a step of visually displaying the output analysis information. Accordingly, an interface that takes into account of convenience of a user is provided and an efficient curling analysis result is provided to assist in improvement of curling performance.
Abstract:
A mobile terminal for displaying curling game information is provided. The mobile terminal includes a first screen configured to receive and display the curling game information, a second screen configured to display statistical information based on pre-stored statistical analysis information according to the curling game information which is input by a user, and a computing component coupled to both of the first screen and the second screen. When a first team and a second team are in a curling game, the pre-stored statistical analysis information include at least one of the followings delivery information as to which team delivers a first stone of each end of the curling game, score distribution information, delivery type information, performance information for each delivery, winning rate information for each team as to the each end of the curling game, and game record information.