Nec Corporation

Nippon Steel Corporation

Masahiro Tani

Takeshi Arikuma

Kazufumi Kojima

Keisuke Ikeda

Yoshifumi Onishi

Takafumi Koshinaka

Royston Rodrigues

Ryoma Oami

Hiroyoshi Miyano

Koji Okabe

Makoto Terao

Osamu Houshuyama

Tadashi Emori

Shinichi Fukunaga

Takehiko Toh

Hideki Matsuda

Norimasa Yamasaki

Keisuke Fujisaki

Kiyoshi Wajima

Keiji Tsunenari

Shigeru Sawada

Kazuhisa Tanaka

The training apparatus () performs a first phase training and a second phase training of a discriminator (). The discriminator () acquires a ground-view image and an aerial-view image, and determines whether the acquired ground-view image matches the acquired aerial-view image. The first phase training is performed using a ground-view image and a first level negative example of aerial-view image. The first level negative example of aerial-view image includes scenery of a different type from scenery in the ground-view image. The second phase training is performed using the ground-view image and a second level negative example of aerial-view image. The second level negative example of aerial-view image includes scenery of a same type as scenery in the ground-view image.

Training apparatus, control method, and non-transitory computer-readable storage medium

An information processing apparatus () determines whether a content (-) of a relevant account (-) associated with a target account (-) and a content (-) of a relevant account (-) associated with a target account (-) are similar. When the content (-) and the content (-) are similar, the information processing apparatus () executes predetermined processing related to the target account (-) and the target account (-).

Information processing apparatus, control method, and program

In order to extract, with high accuracy, useful information from contribution information of social media, the present invention provides a processing apparatusincluding: an acquisition unitthat acquires contribution information relating to a target area; a computation unitthat computes a degree of reliability of the contribution information, based on at least two of an activity area of a contributor of the contribution information, a degree of reliability of an estimation result of the activity area, a degree of disclosure of a profile of the contributor, an attribute of the contributor, an attribute of the activity area for the contributor, and a category of a content of the contribution information; and an output unitthat outputs the contribution information in which a degree of reliability of the contribution information is higher than a threshold value.

Processing apparatus, processing method, and non-transitory storage medium

An image augmentation apparatus () performs an image augmentation process on an original training dataset () to generate an augmented training dataset (). The original training dataset () includes an original ground-view image () and an original aerial-view image (). The image augmentation process includes a removal process in which partial regions including objects of a specific type are removed. The image augmentation apparatus () performs the image augmentation process on the original ground-view image () to generate an augmented ground-view image (), on the original aerial-view image () to generate an augmented aerial-view image (), or both.

Image augmentation apparatus, control method, and non-transitory computer-readable storage medium

The image matching apparatus () comprises a ground-view feature extractor (), an aerial-view feature extractor (), and a determination unit (). The ground-view feature extractor () extracts features from the ground-view image () to generate feature maps without attention mechanism and feature maps with attention mechanism. The aerial-view feature extractor () extracts features from the aerial-view image () to generate feature maps without attention mechanism and feature maps with attention mechanism. The determination unit () computes a similarity score, which indicates a degree of similarity between the ground-view image () and the aerial-view image (), based on the generated feature maps. Then, the determination unit () determines whether the ground-view image () matches the aerial-view image () based on the similarity score.

Image matching apparatus, control method, and non-transitory computer-readable storage medium

To reduce a decrease in search accuracy in a technique for comparing feature values acquired by collecting a local feature value by patch unit, the present invention provides an image processing apparatusincluding: an image processing unitthat detects an object region occupied by an object in an image; a patch size decision unitthat decides a patch size, based on a size of the object region; a patch unit feature value-computation unitthat sets a plurality of patches having the patch size described above in the object region, and computes a patch unit feature value acquired by collecting a local feature value in a patch for each patch; and a search unitthat searches for an image similar to a query image from among a plurality of reference images by using the patch unit feature value.

Image processing apparatus, image processing method, and non-transitory storage medium

An image processing apparatus () acquires a video frame (), and detects a person from the acquired video frame (). The image processing apparatus () determines whether the detected person () satisfies a predetermined condition based on a permission list (). The image processing apparatus () performs, on an image region in the video frame () representing the person () determined to satisfy the predetermined condition, first treatment processing of setting the person () in a hardly identified state. The predetermined condition includes a condition that the person () is included in the permission list ().

Image processing apparatus, control method, and non-transitory storage medium

An acquiring unit acquires information of the residence of one or more second users each having a second social media account related to a first user having a first social media account. An estimating unit estimates the residence of the first user from the information of the residence of the second user. A detecting unit detects a posting area at which the first user has posted on social media. A comparing unit compares the detected posting area with the estimated residence of the first user. A determining unit determines whether the posting area is an ordinary activity area or an extraordinary activity area for the first user based on the result of the comparison.

Posting location ordinariness/extraordinariness determination system

Event-related data based on an image that has been captured is generated. Coverage information relating to imaging range is compared to the event-related data. The cameras that can capture an image of the event, based on a comparing result, are listed so that an operator can select one of the listed cameras.

Camera listing based on comparison of imaging range coverage information to event-related data generated based on captured image

A system for monitoring event related data including a sensor data analyzer, an event analyzer and an actuator is disclosed. The sensor data analyzer detects events based on sensor data, the event analyzer couples to the sensor data analyzer and estimates the size of the detected entire events based on event related data of the detected events from the sensor data analyzer, and the actuator couples to the sensor data analyzer and the event analyzer and actuates a predetermined device based on the estimated size of the detected entire events.

System for monitoring event related data

Provided is an estimating device, an estimating method, and an estimating program that each make it possible to estimate the area of activity of a target user with a smaller amount of information. An estimating device includes a first position distribution generating unit configured to generate a first position distribution of a target user on social media based on account information of the target user, a second position distribution generating unit configured to generate a second position distribution of a friend who is friends with the target user on the social media based on account information of the friend, and an estimating unit configured to estimate an area of activity of the target user based on the generated first position distribution and the generated second position distribution.

Estimating device, estimating method, and estimating program

An information processing apparatus capable of accurately specifying identification information whose users are the same user regardless of information registered by users is provided. The information processing apparatus may include at least one memory storing instructions and at least one processor configured to execute the instructions to: acquire positional information associated with at least one piece of related identification information related to each of a plurality of pieces of identification information for identifying users in a communication service; specify hierarchized positional information indicating positional information hierarchized in accordance with a granularity level of a position based on the positional information; calculate a similarity between pieces of identification information using the hierarchized positional information; and specify the pieces of identification information belonging to the same user from among the plurality of pieces of identification information based on the calculated similarity.

Techniques for accurately specifying identification information

A computer-implemented method for determining whether or not an event is going to aggravate using a sensor operationally coupled to a processor is disclosed. The method includes receiving, from the sensor, event information identifying a type of the event and location information identifying a location at which the event is occurring, collecting, from the sensor, information around the location in response to the location information, analyzing, at the processor, the information around the location, and determining whether or not the event is going to aggravate, at the processor, based on a result of the analysis.

Growing community of inventors

Tokyo, Japan

Masahiro Tani