search

princeton-vl / pose-ae-train

Training code for "Associative Embedding: End-to-End Learning for Joint Detection and Grouping"
BSD 3-Clause "New" or "Revised" License
373 stars 76 forks source link

Multi Person Evaluation on MPII #28

Open ahangchen opened 6 years ago

ahangchen commented 6 years ago

In Section 4 of the paper,

"The groups for MPII Multi-Person are usually a subset of the total people in a particular image, so some information is provided to make sure predictions are made on the correct targets. This includes a general bounding box and scale term used to indicate the occupied region".

However, in mpii test set, there are not bounding box information. Only objpos(person center) and scale(person size, but I can't figure out how it is computed) are provided. Can you explain more about MPII multi person evaluation? How to use these information to make sure predictions are made on the correct targets?

ManiaaJia commented 4 years ago

Hi, @anewell @ahangchen , I have the same doubts about this issue. Have you found out how to get the bounding box of a test image in MPII for correct verification?

I think I figured out that objpos and scale mean center boundaries and average scales of a group, respectively. But when I use a bottom-up approach such as AE, I can't get the correct prediction box perfectly, so I often get unexpected people.

I would be grateful if you could provide me with some help. Thanks！

ManiaaJia commented 4 years ago

Moreover, I want to confirm that, can I use the group border for testing? Could you share more details about your verification? This is deeply helpful to me. Thanks!