wangxiang1230

> 请问关于PRN的代码是否可以获得？ Thank you for your attention, sorry, PRN is not open source, you can refer to our report for some details.

> PRN代码是PRN论文的主要工作，作者可以分享一下嘛，万分谢谢！ Thank you for your attention to PRN. Sorry, we have no intention to open source at present. In this repo, we shared the slowfast101 features used in the...

Thanks you for your attention to SSTAP. When the number of labels is 10%~90% (i.e. less than 100%), we use train_BMN_Semi. When the label is 100%, we use train_BMN_Semi_Full (that...

> 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...

> num_prop Thanks for your attention to SSTAP, I3D features are in the format of "Length*Channel", where 100 is the temporal length and 2048 is the channel dimension. Similarly, for...

> 谢谢，我重新训练下模型，但是在数据处理时出现iou的问题呢,我的start，end time 归一化后是0.675 0.85625,在计算 iou_with_anchors时（代码dataset.py的100行：tmp_gt_iou_map = [iou_with_anchors）] ） 出现匹配不上，最后gt_iou_map的size为0，报错了 Sorry, maybe I don't quite understand your question? It should be noted that the difference between TSN and I3D features...

We opened this repo when we were preparing the camera-ready paper, and the paper was released on arXiv today. We will open source the code in mid-June, so stay tuned,...

> Hi, thanks for the efforts in making the code public. Could you please provide any updates on the code release? Thanks! Thank you for your attention to SSTAP, we...

> Thanks for your work! Could you share the code about thumos dataset. Hi, for THUMOS14 dataset, you can refer to [GTAD](https://github.com/frostinassiky/gtad). In terms of data processing, x% of 200...

> 作者您好，首先感谢您的论文给我带来了启发。在看您论文源码时，有些疑问想请教您。 我注意到您使用了csv_mean_100这个文件夹下的csv文件，请问这19228个csv文件是源视频数据集经过预训练后得到的特征文件嘛？ 也就是说对应于论文图二中，经过 Encoding后得到的f1（即csv_mean_100这个文件夹下的csv文件分别对应了19228个视频样本的f1 特征）？ Hi, thanks for your attention to SSTAP. Yes, we used frozen encoder to get features.