no code implementations • ECCV 2020 • Xiao Shi, Chenxue Yang, Xue Xia, Xiujuan Chai
We present an animal facial feature fusion module to treat the features of the lower half face as additional information, which improves the proposed RiseNet performance.
no code implementations • European Conference on Computer Vision 2022 • Yuecong Min, Peiqi Jiao, Yanan Li, Xiaotao Wang, Lei Lei, Xiujuan Chai, Xilin Chen
The blank class of CTC plays a crucial role in the alignment process and is often considered responsible for the peaky behavior of CTC.
2 code implementations • ICCV 2021 • Yuecong Min, Aiming Hao, Xiujuan Chai, Xilin Chen
Specifically, the proposed VAC comprises two auxiliary losses: one focuses on visual features only, and the other enforces prediction alignment between the feature extractor and the alignment module.
Ranked #10 on Sign Language Recognition on RWTH-PHOENIX-Weather 2014