no code implementations • 27 Oct 2023 • Shuang Li, Jiaxu Leng, Ji Gan, Mengjingcheng Mo, Xinbo Gao
One pertains to the dependence on auxiliary models for shape feature extraction in the inference phase, along with the errors in generated infrared shapes due to the intrinsic modality disparity.
no code implementations • 24 Oct 2023 • Feng Gao, Jiaxu Leng, Ji Gan, Xinbo Gao
Moreover, to train the rank prediction head better, we propose Soft Gradient L1 Loss.
no code implementations • 20 Apr 2020 • Ji Gan, Weiqiang Wang, Ke Lu
Chinese is one of the most widely used languages in the world, yet online handwritten Chinese character recognition (OLHCCR) remains challenging.