Figure1

Figure 1. A brief illumination of the proposed method. Inspired by the reading habit of "Book-Chapter-Content", a heuristic strategy is adopted to first model global contextual awareness and then focus on local gloss understanding, enhancing the distinction between sign language gloss types. The data used in this figure is obtained from the EvCSLR open-source dataset, which is available at https://github.com/diamondxx/EvCSLR.