Storage medium, specifying method, and information processing device

A specifying method for a computer to execute a process comprising:

• acquiring a video that includes an object;
• narrowing down, by inputting the acquired video to a machine learning model that refers to reference source data in which attributes of objects are associated with each of a plurality of hierarchies, attributes of the object included in the video among attributes of objects of a first hierarchy;
• identifying attributes of objects of a second hierarchy under the first hierarchy by using the attributes of the object obtained by the narrowing down;
• and
• specifying, by inputting the acquired video to the machine learning model, an attribute of the object included in the video among the attributes of the objects of the second hierarchy, wherein
• the narrowing down includes:
• inputting the video to an image encoder included in the machine learning model,
• inputting texts for respective attributes of the objects of the first hierarchy to a text encoder included in the machine learning model, and
• narrowing down the attributes of the object included in the video among the attributes of the objects of the first hierarchy based on similarity between a vector of the video output from the image encoder and vectors of the texts output from the text encoder,
• wherein the specifying includes:
• inputting the video to the image encoder,
• inputting texts that correspond to the attributes of the objects of the second hierarchy to the text encoder, and
• specifying the attribute of the object included in the video among the attributes of the objects of the second hierarchy based on similarity between the vector of the video output from the image encoder and vectors of the texts output from the text encoder.

An information processing device comprising:

• one or more memories;
• and
• one or more processors coupled to the one or more memories and the one or more processors configured to:
• acquire a video that includes an object,
• narrow down, by inputting the acquired video to a machine learning model that refers to reference source data in which attributes of objects are associated with each of a plurality of hierarchies, attributes of the object included in the video among attributes of objects of a first hierarchy,
• identify attributes of objects of a second hierarchy under the first hierarchy by using the attributes of the object obtained by the narrowing down, and
• specify, by inputting the acquired video to the machine learning model, an attribute of the object included in the video among the attributes of the objects of the second hierarchy, wherein
• the narrowing down includes:
• inputting the video to an image encoder included in the machine learning model,
• inputting texts for respective attributes of the objects of the first hierarchy to a text encoder included in the machine learning model, and
• narrowing down the attributes of the object included in the video among the attributes of the objects of the first hierarchy based on similarity between a vector of the video output from the image encoder and vectors of the texts output from the text encoder,
• wherein the specifying includes:
• inputting the video to the image encoder,
• inputting texts that correspond to the attributes of the objects of the second hierarchy to the text encoder, and
• specifying the attribute of the object included in the video among the attributes of the objects of the second hierarchy based on similarity between the vector of the video output from the image encoder and vectors of the texts output from the text encoder.