Felix Yim Binh Sze

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
We develop a real-time, robust and accurate sign language recognition system leveraging deep convolutional neural networks(DCNN). Our framework is able to prevent common problems such as error accumulation of existing frameworks and it outperforms state-of-the-art frameworks in terms of accuracy, recognition time and usability.
This paper investigates the development of discourse referencing in spoken Cantonese of fifteen deaf/hard-of-hearing children studying in a sign bilingual and co-enrollment education programme in a mainstream setting in Hong Kong. A comparison of their elicited narratives with those of the hearing children and adults shows that, despite a delay in acquiring(More)
We propose a novel spatial-temporal feature set for sign language recognition, wherein we construct explicit spatial and temporal features that capture both hand movement and hand shape. Experimental results show that the proposed solution outperforms existing one in terms of accuracy.
  • 1