I am on a survey about image retrieval datasets. I have found some, such as:
- NUS-WIDE
- Oxford5k
- Oxford105k
- Paris6k
- MSCOCO
I have been way too confused about the detection metrics and the metrics they use inside these datasets for image retrieval purposes. For example:
- AP
- Recall
- Precison
- Mean Average Precision
My question is, how I can identify the metrics that these datasets use for image retrieval purposes.