search

SoccerNet / sn-spotting

Repository containing all necessary codes to get started on the SoccerNet Action Spotting challenge. This repository also contains several benchmark methods.
61 stars 8 forks source link

Wrong Interpretation #4

Closed Tortoise17 closed 2 years ago

Tortoise17 commented 2 years ago

I have to ask one question. I used NetVlad++ model and TempPooling inference results on my own data video test is that accuracy is less than CALF model json. All the events are less than value 0,25 in visibility. Could you give any hint why it could be. I guess that I need correct K_V2 values

Tortoise17 commented 2 years ago

@SilvioGiancola I have to ask for TempPooling in config. Like in CALF is 

# Values of the K parameters (in seconds) in the context-aware loss
K_V2 = torch.FloatTensor([[-100, -98, -20, -40, -96, -5, -8, -93, -99, -31, -75, -10, -97, -75, -20, -84, -18], [-50, -49, -10, -20, -48, -3, -4, -46, -50, -15, -37, -
                                                                                                                 5, -49, -38, -10, -42, -9], [50, 49, 60, 10, 48, 3, 4, 46, 50, 15, 37, 5, 49, 38, 10, 42, 9], [100, 98, 90, 20, 96, 5, 8, 93, 99, 31, 75, 10, 97, 75, 20, 84, 18]]).cuda()

Can I have values for Temporary_Aware_Pooling NetVLAD++ for classes.py in config folder? I guess here I need your help. which values to be replaced for this model. Your kind help is highly appreciated.

SilvioGiancola commented 2 years ago

Hi @Tortoise17 , You actually don't need K_V2 for NetVLAD++. All you need to set is the size of the temporal window you want to pool from. That temporal value is generic for all the actions, my model/code cannot handle multiple values per class.

Now I don't know why the pre-trained model does not work as well as expected in your own video, and if CALF works better, maybe it means that CALF transfers better to your video, I can't tell.

Tortoise17 commented 2 years ago

@SilvioGiancola Thankyou so much. Can you tell me as a guess about the temporal window size ? to decrease or increase?

Tortoise17 commented 2 years ago

at the moment, it is 15

SilvioGiancola commented 2 years ago

The sensitivity analysis on SoccerNet was provided in the paper (Table 2): https://openaccess.thecvf.com/content/CVPR2021W/CVSports/papers/Giancola_Temporally-Aware_Feature_Pooling_for_Action_Spotting_in_Soccer_Broadcasts_CVPRW_2021_paper.pdf

Tortoise17 commented 2 years ago

Thank you so much.