Sauradip Nag comments

Results 22 comments of


                                            Sauradip Nag

Unable to download pretrained model

Hey @nikita0511 @Pay20Y can you guys send me model to me too ? Email : [email protected]

Unable to download pretrained model

Yes, mee too , i didnt get the attachment *Sauradip Nag* Project Associate , Visualization and Perception Lab, IIT Madras 7003394465 | [email protected] Skype: sauradip2 Chennai - 600036 , TamilNadu...

Reproducing the results on ActivityNet

> Hi @Pilhyeon, thanks for your great work! Now I'm following your BMUE and have some trouble in reproducing the results on ActivityNet dataset. > > I have tried to...

Difference between train_semi_full and train_semi

Thank you for clearing my doubt ! I have one additional doubt : https://github.com/wangxiang1230/SSTAP/blob/b8a55c98151ecb6a0e25a3160dfdee855ab60b42/main.py#L261 What is this thing doing ? I did not get the threshold choice of 0.6 and...

Difference between train_semi_full and train_semi

Hi ! Thank you for clarification ! Last question I have is in the inference you have shown the inference_BMN() , inference_BMN_ema() , so for generating the results in table...

if action_end - action_start > 1 and gt_label in lbl_dict

In our masking free approach, we check if action_Start and action_end atleast point to two different snippets, that is why we keep one snippet gap between the two. This is...

gt bar is not equal to predict bar

Thanks we will correct it out. Can you show some examples where this happened, will be easy to fix

Low mAP on Activitynet-1.3

Can you paste the config file here ? Otherwise it is difficult for me to judge ! And also did you maintain the same environment as mentioned in the Readme...

Low mAP on Activitynet-1.3

"gsm_best_score.json" should be renamed to "spot_best_score.json". I will correct it. Thanks for spotting

Low mAP on Activitynet-1.3

We follow the same technique as SSTAP. The post-processing in most of the TAD approaches irrespective of classifier is still the same