Object recognition method and apparatus, device, and storage medium

A computer device, comprising:

• a memory being configured to store computer-readable instructions;
• and
• at least one processor coupled to the memory configured to execute the computer-readable instructions to perform:
• obtaining a candidate object set having a plurality of candidate objects;
• obtaining a plurality of pieces of candidate object information of the candidate objects on a plurality of dimensions, performing feature extraction on each piece of the candidate object information to obtain candidate object features corresponding to each piece of the candidate object information, fusing the candidate object features to obtain object extraction features corresponding to the candidate objects, and performing object category probability recognition based on the object extraction features to obtain a recognition probability that the candidate objects belong to a target object category;
• clustering the object extraction features corresponding to the candidate objects to obtain sub extraction feature sets corresponding to clustering categories, and forming one sub object set from candidate objects corresponding to the object extraction features in the same sub extraction feature set;
• and
• obtaining, for the sub object sets formed according to the sub extraction feature sets, representative objects by selecting from the sub object sets respectively based on recognition probabilities corresponding to the candidate objects in the sub object sets,
• wherein the object screening model is determined by:
• obtaining a seed object corresponding to the target object category;
• obtaining seed object information corresponding to the seed object, and forming a training sample with the seed object information as a training feature in the training sample and with the target object category as a label in the training sample;
• and
• performing model training based on the training sample to obtain the object screening model.

A non-transitory computer-readable storage medium storing computer-readable instructions executable by at least one processor to perform:

• obtaining a candidate object set having a plurality of candidate objects;
• obtaining a plurality of pieces of candidate object information of the candidate objects on a plurality of dimensions, performing feature extraction on each piece of the candidate object information to obtain candidate object features corresponding to each piece of the candidate object information, fusing the candidate object features to obtain object extraction features corresponding to the candidate objects, and performing object category probability recognition based on the object extraction features to obtain a recognition probability that the candidate objects belong to a target object category;
• clustering the object extraction features corresponding to the candidate objects to obtain sub extraction feature sets corresponding to clustering categories, and forming one sub object set from candidate objects corresponding to the object extraction features in the same sub extraction feature set;
• and
• obtaining, for the sub object sets formed according to the sub extraction feature sets, representative objects by selecting from the sub object sets respectively based on recognition probabilities corresponding to the candidate objects in the sub object sets,
• wherein the object screening model is determined by:
• obtaining a seed object corresponding to the target object category;
• obtaining seed object information corresponding to the seed object, and forming a training sample with the seed object information as a training feature in the training sample and with the target object category as a label in the training sample;
• and
• performing model training based on the training sample to obtain the object screening model.