bellos1203/stpn

STPN - Weakly Supervised Action Localization by Sparse Temporal Pooling Network

stpn's Issues

THUMOS2014 Features

Good job, and can you publish the feature files(.npy) uesd by i3d for extracting RGB and optical flow? thx : )

issue about the evaluation code

Hello, I observe that when using the evaluation code from the official ActivityNet repo, the performance can be higher than the one from the official THUMOS14 repo nearly 2% under iou=0.5 and 6% under iou=0.1. I really think it maybe unfair to some extent for comparison with other sota...

Issues about the test video list and the evaluation result

Hello.
First of all, thanks for your good reproducing of STPN.
I have two issues.
One is about the test video list, and the other is about the evaluation result.

1. In the THUMOS'14 test split, there are 213 videos. After removing two videos(270, 1496), there will be 211 videos. However there are 210 videos in your test split file. I found that the difference is existence of number "1292". Is there any reason for not including that video?
   p.s. When I included that video, the performance decreased.

2. I think I perfectly followed your instruction. But there is slight difference between my evaluation result and yours. My result is like below:
   | 0.1 | 0.2 | 0.3 | 0.4 | 0.5 | 0.6 | 0.7 | 0.8 | 0.9 | mAP |
   | 0.5220 | 0.4356 | 0.3331 | 0.2449 | 0.1675 | 0.0987 | 00474 | 0.0126 | 0.0009 | 0.2070 |
   I used your code and ckpt files.
   Is there any factor of making differences? (randomness, different hyper-parameter, etc.)

Thanks for your good work, again.

download problem

I can't clone the repository successfully. How can I do?

Need more details on feature extraction

I will be needing more details on the feature extraction part. What particular codebase you used for optical flow extraction?