Abstract: Regression-based scene text detection methods, which mainly locate text by regressing parameterized curves, have become popular recently. However, parameterized curves typically require a ...

Abstract: Continuous sign language recognition (CSLR) requires fine-grained alignment between visual sequences and gloss annotations under weak supervision, which is challenged by modality ...

You know those millennials who pepper every text with an “lol” or emoji like it’s life support? Anna Gaddis (@annagaddis) is one of those people — and she’s clapping back at the haters. In a recent ...