-
Notifications
You must be signed in to change notification settings - Fork 3
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
GBVS360 with equatorial prior #7
Comments
Hi, Thank you for raising this issue. I checked it, and I can confirm that the equatorial prior is not applied... Thank a lot for pointing it out I will spend time on that later today/tomorrow morning. |
Hi, Thank you for the confirmation! We're looking forward to the new release. In the meantime, can we test your models (from the release on 19 Oct 2018) with the following commands to see the effect of the equatorial prior? For example; BMS360 BMS360 with equatorial prior If so, can we also use this argument for the BMS and GBVS360 models? |
Hello, Sorry for the late reply. I now updated the release. You can find it under the name "model-latest.7z". Regarding the usage of the release from Oct 19 2018, you are correct. With that build, you can access the other model like this: BMS BMS with equatorial prior GBVS360 GBVS360 with equatorial prior |
Hi, Thank you for the explanations. I'm sorry to bother you again but I couldn't find "model-latest.7z". Could you please provide a link? Lastly, can we use the same commands above for the new release? |
Hi, No problem. You can find the release there: With this version, you won't have the control over the use of the equatorial prior (eg. the option --equatorial-prior is not available). But you can choose among the different models as listed in the instruction of tha page linked above. |
Hi,
Thank you very much for the nice work and making your models available.
I'm trying to use GBVS360 model with equatorial prior by using the command
salient.exe -i P10.jpg --general-model 2 -o saliency.jpg --legacy-icme-2017
as suggested here : https://github.com/Telecommunication-Telemedia-Assessment/GBVS360-BMS360-ProSal/releases/tag/2.0
However, it looks like the equatorial prior is not effective. When I add the argument for it and run the model with this command it seems fine :
salient.exe -i P10.jpg --general-model 2 -o saliency.jpg --legacy-icme-2017 --equatorial-prior
Here you can find an example image, the output of the first command, and the output of the second command :
![cubemap_0000](https://user-images.githubusercontent.com/16324609/123335735-2ed36e00-d545-11eb-9968-5c078533b84d.png)
![cubemap_0000](https://user-images.githubusercontent.com/16324609/123335684-1f542500-d545-11eb-901d-43960a70e53d.png)
![cubemap_0000](https://user-images.githubusercontent.com/16324609/123335709-25e29c80-d545-11eb-8a80-d16be2f97939.png)
Am I misusing the commands ? Or is there a typo in the given command ? I'd be very happy if you can point out what I am missing. Thanks in advance!
Best,
Bahar
The text was updated successfully, but these errors were encountered: