[1]
Ma, Z., Dai, P., Zhuo, W. and Qin, X. 2026. One2Seq: One-Token Wise Decoder for Efficient Scene Text Recognition. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 10 (Mar. 2026), 7883-7891. DOI:https://doi.org/10.1609/aaai.v40i10.37732.