hello,have you got the I3D feature or the proposal_list for ActivityNet? I'm also working on activitynet dataset. Thank you! My email is [email protected]

Hi, thanks for your sharing of the code. I'd like to know that where the pre-extracted proposals come from. Did you reimplement the paper Boundary Sensitive Network or just use their provided proposals?

thank you for your great work. I have some question wether if I want to apply your work for my own dataset how can i generate the bsn_proposal_list files ? and am I need to train bsn proposal generator with my own dataset ?

thank you so much

I would like to test your model on a new TAL dataset collected by our laboratory. Hence we want to know how should we prepare the dataset directory and ground truth files. Any suggestions will be very helpful!

Hi, thanks a lot for open resource .I'm working on activitynet dataset. Do u have I3D features u used in this project, I'm appreciate it if u can share one copy to me! My email address is [email protected]

Dear author, I have trained the PGCN model on my own data set, but I need to make a prediction on a video (not in the training set nor in the test set), I see that the code needs to generate the corresponding proposal which need corresponding GT information, But the videos I'm testing now don't have tag files. could u tell me how to do it? thanks a lot

Thanks for the brilliant work!

I happen to see an error when the RGB model is directly loaded into the PGCN architecture. The reason seems to be a mismatch of the datatype.

To solve that, I replaced one line of code in pgcn_test.py reg_scores[prop_idx, :] = net((act_batch_var, comp_batch_var), None, None, None) by reg_scores[prop_idx, :] = net((act_batch_var.float(), comp_batch_var.float()), None, None, None)

Do it first if you find a similar error :)

Thanks for your excellent work. I trained the model that you provided and found that the best model's(at the epoch 15) performance is
| IoU thresh | 0.10 | 0.20 | 0.30 | 0.40 | 0.50 | 0.60 | 0.70 | 0.80 | 0.90 | Average | | mean AP | 0.6574 | 0.6382 | 0.6009 | 0.5374 | 0.4578 | 0.3369 | 0.2172 | 0.0903 | 0.0134 | 0.3944 | +------------+--------+--------+--------+--------+--------+--------+--------+--------+--------+--------- And it's lower than results in the paper. Could you provide the pretrained model or explain why this happened ? Thank you

Hey! Great Job! After seeing through your paper, I've got one question. I was wondering how did you process the output feature of GCN model (Nxd) before fc layer. Because you know, you got to get rid of the two dimensions. And I saw the code, found that you just picked the first row of all N features. Did I understand it correctly? If so, could you please explain why would you do that. Why not perform an average pool between the N features? Thanks a lot!

In your paper, it says "We first uniformly divide each input video into 64-frame segments. We then use a two-stream Inflated 3D ConvNet (I3D) model pre-trained on Kinetics [5] to extract the segment features." However, in your code

interval = 8
clip_length = 64
start_unit = int(min(ft_num - 1, np.floor(float(start_ind + off) / interval)))
end_unit = int(min(ft_num - 2, np.ceil(float(end_ind - clip_length) / interval)))

I guess minusing 64 means you do not use the last few frames not divisible by 64, but why should interval=8? Is it means that you divide each input video into 8-frame?

By the way? Could you offer the I3D feature on ActivityNet? It's so time-comsuming to extrat.

Hi,

I am trying to use PGCN on my own dataset. I have annotated the data according to Thumos'14 annotation format and extracted features using I3D. I have also trained and infered a G-TAD model.

1. Can you let me know how I can re-score G-TAD generated output using PGCN?

Your answers to the above questions will clarify a lot of doubts.

Thank you for your time!

when i use numpy to load the data file, only one int data can be loaded. is there any trick for loading the flow i3d anet dataset, or is there anything wrong when i process the data?

I can not find the thumos14's proposals like activitynet. And I also can not understand why the number of features are different between flow and rgb, they also could not match the Proposal_Lists.txt provided for acitvitynet.

I am very confused and I think no one can run the code now using provided features and porposals

Thanks!!!

Hi, With the help of the author and many others, I trained the PGCN model. But I have a question about how to choose inferential proposals. At present, I use GTAD + PGCN to output the prediction results (that is, a certain number of proposals, sorted according to score). However, in actual processing of an unmarked video, a certain number of proposals will be generated through PGCN. Then how can I finally select these proposals as the prediction results?Top100/50 or something like that

I am confused on how to read the proposal list for the dataset to be used in PGCN. Can someone explain how to read each number in one line of the proposal list? Thank you!

There are total 413 videos in this dataset, including training and testing. The number of provided RGB features is 413, but the number of provided flow features is 412. Why there is someone is missing?