Open cleong110 opened 1 week ago
Possibly relevant here:
@inproceedings{huangFastHighQualitySign2021,
title = {Towards {{Fast}} and {{High-Quality Sign Language Production}}},
booktitle = {Proceedings of the 29th {{ACM International Conference}} on {{Multimedia}}},
author = {Huang, Wencan and Pan, Wenwen and Zhao, Zhou and Tian, Qi},
year = {2021},
month = oct,
series = {{{MM}} '21},
pages = {3172--3181},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
doi = {10.1145/3474085.3475463},
url = {https://doi.org/10.1145/3474085.3475463},
urldate = {2024-06-19},
isbn = {978-1-4503-8651-7}
}
has this to say:
Which seems to suggest that the method is:
With the theory being that as you generate better, the SLT should get more accurate.
They don't train a backtranslation model themselves, that's independent
maybe also need a note about back translation: that people use it (progressive transformers, sign llm), but the outputs are incoherent. this is because people train the backtranslation models on the translation model outputs, and not independently, as one should.
_Originally posted by @AmitMY in https://github.com/sign-language-processing/sign-language-processing.github.io/pull/77#discussion_r1641255726_