Abstract: To generate and present effective information for making and determining a product design, this product design generation support device includes: an acquisition unit; a design classification unit; and an output unit. The acquisition unit acquires design information of each of a plurality of designs of the subject product that are different to each other and line-of-sight information of the subject person for those designs. The design classification unit classifies the plurality of designs into a plurality of groups according to the acquired design information and line-of-sight information. The output unit outputs the classification results.

Abstract: In order to generate and present information that is effective for preparing and determining a product design, a product-design generation support device according to the present invention is provided with an acquisition unit, a classification unit, and an output unit. The acquisition unit acquires design information representing a target design for a target product, as well as gaze information of a plurality of target persons in relation to the target design. The classification unit classifies the plurality of target persons into a plurality of groups on the basis of the acquired design information and gaze information. The output unit outputs the result of the classification.

Abstract: A purchasing factor estimation device includes: an acquisition unit that acquires person attribute information relating to a first person and product attribute information relating to a first product; an estimation unit that, on the basis of the person attribute information and the product attribute information, uses an estimation model to estimate the first person's degree of interest in the first product; and an output unit that outputs the first person's estimated degree of interest and an estimation reason therefor. The factors behind the purchase of a product by a customer are determined as a result of generating the estimation model by learning the relationship among person attribute information relating to a second person, product attribute information relating to a second product, line of sight information of the second person in relation to the second product, and the second person's degree of interest in the second product.

Abstract: A method for automatic optimization of a system includes randomly generating a plurality of input parameter configurations for the system. Using a trained neural network, a plurality of throughputs of the system are simulated using each of the randomly generated input parameter configurations. Each of the randomly generated input parameter configurations are scored based on the simulated throughputs and data stored in a training database. An input parameter configuration is selected from the randomly generated plurality of input parameter configurations based on the scoring. The selected input parameter configuration is sent to an actuator for executing the system using the selected input parameter configuration.

Abstract: A method for partial planar point cloud matching includes collecting partial point clouds and full point clouds. A graph is generated from the partial point clouds and a graph is generated from the full point clouds. A point cloud graph network is trained to predict a matching matrix using the graphs.

Abstract: A method for minimizing information loss in set neural networks includes determining an information loss term for a set neural network that internally uses virtual tokens, such that the information loss term minimizes a divergence between two distributions. The set neural network is trained with training data from a data source that is expressed as sets using the information loss term.

Abstract: A method for learning representations from clouds of points data includes encoding clouds of points data into at least one representation by creating at least one tensor representation out of the clouds of points data. The method further includes using a loss function that utilizes a noisy reconstruction for reducing overfitting.

Abstract: Systems and methods for contextualizing automatic image segmentation and/or regression including defining an hourglass neural network model, which includes defining an encoder configured to generate compression layers, including a bottleneck layer, and defining a decoder including a contextual convolution operation and configured to generate one or more reconstruction layers. The contextual convolution operation includes establishing, for each of the one or more reconstruction layers, a skip connection between the reconstruction layer and prior layer(s) of different spatial dimension, e.g., between the bottleneck layer and the reconstruction layer and/or between reconstruction layers.

Abstract: A method for generating a product recommendation in a retail system includes collecting a dataset containing a plurality of entities and attributes for the entities. Relationships between the plurality of entities are generated. The plurality of entities, attributes and relationships are stored in a knowledge graph. A representation of the plurality of entities, attributes and relationships stored in the knowledge graph is learned. Zero-shot learning is performed for a new entity and attributes for the new entity. The new entity and attributes for the new entity are stored in the knowledge graph. A recommendation for a user is generated based on the knowledge graph.

Abstract: A method for providing recommendations to users includes obtaining stored data structure triples and actual ratings associated with the data structure triples; training a machine learning model using the stored data structure triples and associated actual ratings, wherein training the machine learning model includes generating user, product, and review representations based on the stored data structure triples and their associated ratings; predicting, by the machine learning model, ratings using the generated user, product, and review representations; and making recommendations based on the predicted ratings.

Abstract: A method for object density monitoring includes receiving, by a processing server, an input image captured by an image sensor. The method further includes providing an annotated dataset with a target object to be identified in the input image, and providing, by the processing server as output, an object density map generated from the input image. The processing server provides the object density map by using a deep neural network having one or more pairs of a compression layer and a decompression layer connected by gated shortcuts.

Abstract: Systems and methods for contextualizing automatic image segmentation and/or regression including defining an hourglass neural network model, which includes defining an encoder configured to generate compression layers, including a bottleneck layer, and defining a decoder including a contextual convolution operation and configured to generate one or more reconstruction layers. The contextual convolution operation includes establishing, for each of the one or more reconstruction layers, a skip connection between the reconstruction layer and prior layer(s) of different spatial dimension, e.g., between the bottleneck layer and the reconstruction layer and/or between reconstruction layers.

Abstract: A method for generating a product recommendation in a retail system includes collecting a dataset containing a plurality of entities and attributes for the entities. Relationships between the plurality of entities are generated. The plurality of entities, attributes and relationships are stored in a knowledge graph. A representation of the plurality of entities, attributes and relationships stored in the knowledge graph is learned. Zero-shot learning is performed for a new entity and attributes for the new entity. The new entity and attributes for the new entity are stored in the knowledge graph. A recommendation for a user is generated based on the knowledge graph.

Abstract: A method for object density monitoring includes receiving, by a processing server, an input image captured by an image sensor. The method further includes providing an annotated dataset with a target object to be identified in the input image, and providing, by the processing server as output, an object density map generated from the input image. The processing server provides the object density map by using a deep neural network having one or more pairs of a compression layer and a decompression layer connected by gated shortcuts.

Abstract: A method for providing recommendations to users includes obtaining stored data structure triples and actual ratings associated with the data structure triples; training a machine learning model using the stored data structure triples and associated actual ratings, wherein training the machine learning model includes generating user, product, and review representations based on the stored data structure triples and their associated ratings; predicting, by the machine learning model, ratings using the generated user, product, and review representations; and making recommendations based on the predicted ratings.