weirme

This function generates a summary from summary of 20 users in the dataset.

Chapter 3.1 of this paper: [Diverse sequential subset selection for supervised video summarization](http://www.cs.utexas.edu/~grauman/papers/nips14_seqdpp.pdf). In my implementation, the greedy algorithm selects the frame marked by the most users each time.

In my implementation, initialize oracle summary as [0, 0, 0, 0, 0], and then pick the most selected frame (here the third), now the oracle summary will be [0, 0,...

This method is mentioned in supplementary materials of paper [Video Summarization with Long Short-term Memory](https://arxiv.org/pdf/1605.08110.pdf).

Have you print the final F-score between generated oracle summary and user summary?

> https://github.com/KaiyangZhou/pytorch-vsumm-reinforce/blob/fdd03be93f090278424af789c120531e49aefa40/main.py#L164 > > I found that tvsum use avg but summe use max when evaluating. > After I change summe to max, my result gets better. > > But...

> Could you share the tvsum video on your google drive? > [tvsum](https://webscope.sandbox.yahoo.com/catalog.php?datatype=i&did=72) needs authorization.... Wait a moment, I'm now uploading it...

Here is the [link](https://drive.google.com/open?id=14tcW0T6ps9FQmbqmtHW3OG5lqodCeg78).

May be it is a default setting in evaluation? I also think it's strange... And I noticed that selected key frames of videos in summe differ greatly from each user,...

I have not read this paper yet, its architecture looks complicated.