From sight to insight: A multi-task approach with the visual language decoding model

Wei Huang, Pengfei Yang, Ying Tang, Fan Qin, Hengjiang Li, Diwei Wu, Wei Ren, Sizhuo Wang, Jingpeng Li, Yucheng Zhu, Bo Zhou, Jingyuan Sun, Qiang Li, Kaiwen Cheng, Hongmei Yan, Huafu Chen

Abstract: Highlights•A decoding model that simultaneously decodes three types of visual information.•The model demonstrates high efficiency in decoding across multiple tasks.•The model is expected to lead to a better human-computer interaction experience.