Continuous Sign Language Recognition Through Cross-Modal Alignment of Video and Text Embeddings in a Joint-Latent Space
Open paper
Benchmark
Model
Rank
Results
sign-language-recognition-on-rwth-phoenix-weather-2014
CrossModal
–
Word Error Rate (WER): 24.0
sign-language-recognition-on-rwth-phoenix-weather-2014-t
CrossModal
–
Word Error Rate (WER): 24.3
Rank counts only results with a code link.