Closed cleong110 closed 1 week ago
For example we have this in SignBERT+
continuous SLR (RWTH-PHOENIX-Weather [@koller2015ContinuousSLR]
In the SignBERT+ paper they cite thus:
For continuous SLR, the evaluation is conducted on two datasets, i.e., RWTH-Phoenix [14] and RWTH-PhoenixT [33]
and 14 is
O. Koller, J. Forster, and H. Ney, “Continuous sign language recognition: Towards large vocabulary statistical recognition systems handling multiple signers,” Computer Vision and Image Understanding (CVIU), vol. 141, pp. 108–125, 2015.
But that's the wrong citation! That citation is not the source of any dataset. It does have analysis...
In this paper, we present extensive results and thorough analysis on, to our knowledge, the currently biggest publicly available corpus of continuous SL (RWTH-PHOENIX-Weather)
and
RWTH-PHOENIX-Weather database 9 signer, 1081 sign vocabulary, 7k sentences
(which is again wrong, the 9 signer version is RWTH-PHOENIX-Weather 2014)
There's also this:
So which one did SignBERT+ use?
SignBERT+ says
For continuous SLR, the evaluation is conducted on two datasets, i.e., RWTH-Phoenix [14] and RWTH-PhoenixT [33]. RWTH-Phoenix [14] is a popular German sign language dataset collected from the weather forecast broadcast. It contains 6,841 samples, with 5,672, 540 and 629 videos for training, validation and testing, respectively.
OK, we can look for those numbers:
So none of the numbers match.
Official RWTH-PHOENIX-WEATHER download site is https://www-i6.informatik.rwth-aachen.de/web/Software/Databases/Signlanguage/details/rwth-phoenix/index.php, which again has no matching numbers
Oh hey, the official RWTH-PHOENIX-WEATHER 2014 website actually DOES want people to cite the Koller 2015 paper.
...why??
And here's the RWTH-PHOENIX-WEATHER 2014 T official site.
OK so anyway, if SignBERT is citing the Koller 2015 paper they must be referring to the 2014 version
OK so if someone cites/uses
use
@dataset:forster-etal-2012-rwth
use
koller2015ContinuousSLR
NOT
dataset:forster2014extensions
use
cihan2018neural
There are a number of places where citations or confusions might need to be double-checked.
Search for "PHOENIX" and confirm we're citing the right ones.
forster-etal-2012-rwth
aka RWTH-PHOENIX-Weather introduction of the dataset.See also #70, no idea why I thought koller2015ContinuousSLR was relevant, possibly some other paper cited it incorrectly?