Canon Kabushiki Kaisha

Hirotaka Hachiya

Masakazu Matsugu

Yusuke Mitarai

Masami Kato

Shunsuke Sato

An output value of a first neural network for input data is obtained in correspondence with each category. An output value of a second neural network generated by changing a designated unit in the first neural network is obtained for the input data in correspondence with each category. For each category, change information representing a change in the output value is obtained. Information representing contribution of the designated unit are output to a display device based on the change information.

Information processing apparatus, information processing method, and non-transitory computer-readable storage medium

An apparatus acquires a video image from a surveillance cameraand displays an image based on the video image on a display. The apparatusrecords the video image acquired from the surveillance camerain a recording unit. The apparatusincludes an abnormality detection unitconfigured to detect an abnormality from the video image, an attention period determination unitconfigured to determine an attention period based on a period from a start to an end of a detected abnormality, and a displaying unitconfigured to display a video image acquired from the surveillance cameraas it is on a displayuntil the abnormality being detected ends, and, when the abnormality being detected ends, acquire, from a recording unit, a recorded video image recorded in a period corresponding to the attention period and play back the acquired recorded video image.

Surveillance apparatus, surveillance method, and storage medium

A recognition training apparatus according to the present invention includes a generation unit configured to generate relevance between a specific domain and a candidate of a recognition target based on ontology information expressing a concept structure of the specific domain, a selection unit configured to select the recognition target from the candidate of the recognition target based on the relevance generated by the generation unit, and a training unit configured to train a recognizer using training data regarding the recognition target selected by the selection unit.

Recognition training apparatus, recognition training method, and storage medium

A plurality of random number sequences are generated using a plurality of random number seeds stored in a memory, and a plurality of base vectors are generated based on the plurality of random number sequences. A transformation source vector is transformed into a lower-dimensional vector by performing random projection for the transformation source vector using the plurality of generated base vectors.

Growing community of inventors

Yokohama, Japan

Hirotaka Hachiya