Skip to content

Commit d54f2c4

Browse files
committed
docs(readme): fix download link for longer pose
1 parent 5abf908 commit d54f2c4

File tree

1 file changed

+22
-2
lines changed

1 file changed

+22
-2
lines changed

README.md

Lines changed: 22 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,8 @@
22

33
Pose segmentation model on both the sentence and sign level
44

5+
Code for the paper [Linguistically Motivated Sign Language Segmentation](https://aclanthology.org/2023.findings-emnlp.846).
6+
57
## Usage
68

79

@@ -10,7 +12,7 @@ pip install git+https://github.com/sign-language-processing/segmentation
1012
```
1113

1214
To create an ELAN file with sign and sentence segments:
13-
(To demo this on a longer file, you can download a large pose file from [here](https://nlp.biu.ac.il/~amit/datasets/poses/holistic/dgs_corpus/1413451-11105600-11163240_a.pose))
15+
(To demo this on a longer file, you can download a large pose file from [here](https://firebasestorage.googleapis.com/v0/b/sign-language-datasets/o/poses%2Fholistic%2Fdgs_corpus%2F1413451-11105600-11163240_a.pose?alt=media&token=432f0b57-3fb9-45ad-a9a4-0b6fae4ffcf7))
1416

1517
```bash
1618
pose_to_segments --pose="sign.pose" --elan="sign.eaf" [--video="sign.mp4"]
@@ -121,4 +123,22 @@ It's also possible to adjust the decoding algorithm by setting the `b_threshold`
121123
python -m sign_language_segmentation.src.train --dataset=dgs_corpus --pose=holistic --fps=25 --hidden_dim=256 --encoder_depth=1 --encoder_bidirectional=true --train=false --checkpoint=./models/E1-1/best.ckpt --b_threshold=50 --o_threshold=50
122124
```
123125

124-
To test on an external dataset, see [evaluate_mediapi.py](https://github.com/sign-language-processing/transcription/blob/main/sign_language_segmentation/src/evaluate_mediapi.py) for an example.
126+
To test on an external dataset, see [evaluate_mediapi.py](https://github.com/sign-language-processing/transcription/blob/main/sign_language_segmentation/src/evaluate_mediapi.py) for an example.
127+
128+
## Cite
129+
130+
```bibtex
131+
@inproceedings{moryossef-etal-2023-linguistically,
132+
title = "Linguistically Motivated Sign Language Segmentation",
133+
author = {Moryossef, Amit and Jiang, Zifan and M{\"u}ller, Mathias and Ebling, Sarah and Goldberg, Yoav},
134+
editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika",
135+
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
136+
month = dec,
137+
year = "2023",
138+
address = "Singapore",
139+
publisher = "Association for Computational Linguistics",
140+
url = "https://aclanthology.org/2023.findings-emnlp.846",
141+
doi = "10.18653/v1/2023.findings-emnlp.846",
142+
pages = "12703--12724",
143+
}
144+
```

0 commit comments

Comments
 (0)