DEVICE FOR PREDICTING GAZING REGION OF ADVERTISEMENT VIDEO, METHOD AND PROGRAM

To easily and highly accurately predict a gazing region of an advertisement video.SOLUTION: An analysis device 1 includes a prediction unit 12 which predicts a gazing region of an advertisement video by inputting the advertisement video to a learned model M that has been machine-learned. The learned...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	ONISHI KAZUHIRO, WATANABE TARO
Format:	Patent
Sprache:	eng ; jpn
Schlagworte:	CALCULATING COMPUTING COUNTING DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	To easily and highly accurately predict a gazing region of an advertisement video.SOLUTION: An analysis device 1 includes a prediction unit 12 which predicts a gazing region of an advertisement video by inputting the advertisement video to a learned model M that has been machine-learned. The learned model M is generated by machine-learning a learning data set of an image for learning including a video and a still image and information on the gazing region in each image for learning.SELECTED DRAWING: Figure 1 【課題】広告動画の注視領域を簡便かつ高精度に予測する。【解決手段】解析装置１は、機械学習された学習済モデルＭに広告動画を入力することにより、広告動画の注視領域を予測する予測部１２を備え、学習済モデルＭは、動画および静止画を含む学習用画像と、各学習用画像における注視領域の情報とを学習データセットとして機械学習することにより生成されたものである。【選択図】図１