How2Sign is a large-scale continuous American Sign Language (ASL) dataset. After removing invalid text-video pairs, we retain 31019, 1738, and 2348 available pairs in the...
Continuous sign language recognition (SLR) deals with unaligned video-text pair and uses the word error rate (WER), i.e., edit distance, as the main evaluation metric.
WLASL is the latest ASL dataset with a larger vocabulary size of 2,000. It consists of 14,289, 3,916, and 2,878 samples in the training, dev, and test set, respectively.
MSASL is an American sign language (ASL) dataset with a vocabulary size of 1,000. It consists of 16,054, 5,287, and 4,172 samples in the training, development (dev), and test...
A neuromorphic vision sensing (NVS) device represents visual information as sequences of asynchronous discrete events (a.k.a., “spikes”) in response to changes in scene...
