KArSL is the largest video dataset for Word-Level Arabic sign language (ArSL). The database consists of 502 isolated sign words collected using Microsoft Kinect V2. Each sign of the database is performed by three professional signers. Each signer repeated each sign 50 times which resulted in a total of 75,300 samples of the whole database (502 x 3 x 50).
read more| Train | Test | |
|---|---|---|
| Signer 01 | 001-070 , 071-170 , 171-190 | 001-070 , 071-170 , 171-190 |
| Signer 02 | 001-070 , 071-170 , 171-190 | 001-070 , 071-170 , 171-190 |
| Signer 03 | 001-070 , 071-170 , 171-190 | 001-070 , 071-170 , 171-190 |
* To download the labels of the dataset's signs, please follow this link.
** For signer-independent experiments, you will test the model on all the signs of the corresponding signer (train + test signs).