Comments (4)
That's right. In my exploration to find the original steps, I found this https://github.com/SinDongHwan/pytorch-vsumm-reinforce/blob/master/utils/generate_dataset.py which is the most similar. I relied on that last one to replicate and I think I did. At least, in the shape of the vectors they are similar (TVSum and Summe) but the "points of change" depend on the vector of characteristics that was applied, so I got different values. This also happens with the gtscore. This is my repository https://github.com/StevRamos/video_summarization
from msva.
I think, that the data used in this repo weren't produced by the authors here, but they are the "same" data used in almost every work (produced by Kaiyang Zhou). That being said, I tried many times and with different KTS parameters, but couldn't replicate the same shot segmentation. The data also appeared in Video Summarization with Long Short-term Memory, where in the Supplementary Material they note, and I quote The resulting intervals are around 5 seconds on average.
Even with this info, I was unable to replicate them, but I wish you a better luck!
from msva.
That's right. In my exploration to find the original steps, I found this https://github.com/SinDongHwan/pytorch-vsumm-reinforce/blob/master/utils/generate_dataset.py which is the most similar. I relied on that last one to replicate and I think I did. At least, in the shape of the vectors they are similar (TVSum and Summe) but the "points of change" depend on the vector of characteristics that was applied, so I got different values. This also happens with the gtscore. This is my repository https://github.com/StevRamos/video_summarization
Thank you,I tried that
from msva.
I think, that the data used in this repo weren't produced by the authors here, but they are the "same" data used in almost every work (produced by Kaiyang Zhou). That being said, I tried many times and with different KTS parameters, but couldn't replicate the same shot segmentation. The data also appeared in Video Summarization with Long Short-term Memory, where in the Supplementary Material they note, and I quote
The resulting intervals are around 5 seconds on average.
Even with this info, I was unable to replicate them, but I wish you a better luck!
Thank you,I tried that
from msva.
Related Issues (14)
- Extracted features for the datasets HOT 1
- extract object features HOT 6
- How did you extract the motion features for the datasets? HOT 2
- Which F1-Score is reported in the paper? HOT 1
- how to import i3d, i can not install by pip or conda HOT 1
- Request for changes in `train.py` and `knapsack.py`
- NOT able to reproduce spearman and kendall tau as reported in the paper.
- Test my video
- Issue regarding the last step of self attention (weighted sum step) HOT 3
- problem about code,the coefficient of Spearman’s and Kendall’s in Tvsum are 0.5849 and 0.6403 HOT 5
- can't reproduce the f1 results, and coefficient results also seems unusual HOT 3
- Trained Model's F-score is different from the score stated in the paper. HOT 1
- how can I get the attribute 'gtscore' of SumMe?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from msva.