Open Solayman-Emon opened 4 years ago
This has been discussed in #7 and there is not (yet) implementation of it provided by the authors. With my team we have been working on an implementation of various video summarization models here and we plan to incorporate the supervised version of this model.
We implemented the supervision loss here: https://github.com/sylvainma/Summarizer/blob/b83635f022641765729cc29af4de95bac7f1cdc1/summarizer/models/dsn.py#L101
It would be nice to have the authors confirming this is correct.
@sylvainma Thank you very much. I have tested this & it seems to give a good result.
How I can generate the supervised version of DR-DSN ? Can anyone provide any code implementation of that. Thanks in advance.