dong-jinkim / actioncooccurrencepriors Goto Github PK

Hi, would you like to provide a script to run the modified baseline?

Hi! Thank you for sharing your work.
I generated a matrix myself for V-COCO dataset, and I wanted to compare to your method to see if it is correct, but I didn't see you mentioned the generation of co-occurrence matrix in your paper.
I also modefied code in mat_to_json.py, my thought is to compare every coordinates of different hoi-classes in an image, if two hoi has same h-o coordinates, they can be regarded as co-occur. But it turns out that there are totally no identical coordinates in different hoi-classes. I wondered it may be the annotations, like[207, 32, 426, 299] and [205, 32, 426, 305] are not identical though they are actually the same box. I modified the identical condition to add a tolerant bias, but my results are not so close to yours.
Can you help me about the issue or give some details about how you generate your matrix?

Thanks for your beautiful work.
I used the appearance features provided by No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques. However, I run the code but got an error of size mismatch.
I find the appearance feature size in your work is set to 1024, while is different with No-Frills (No-Frills appearance feature size is set to 2048). Is it correct?
Thank you again for your attention!

Thanks for sharing your work. Could you tell me how to implement the code on V-COCO dataset?

Thanks for your beautiful work.
I downloaded the pickle file 'co-occurrence_pos.pkl' and read it like this:
with open('co-occurrence_pos(1).pkl', 'rb') as f: data = pickle.load(f)
The output of data is: 119547037146038801333356. Just one single integer. Is it correct? I thought I can have a quick look on the co-occurance matrix