no code implementations • 1 Sep 2022 • Zhangzi Zhu, Chuhui Xue, Yu Hao, Wenqing Zhang, Song Bai
Our oCLIP-based model achieves 28. 59\% in h-mean which ranks 1st in end-to-end OOV word recognition track of OOV Challenge in ECCV2022 TiE Workshop.
no code implementations • 4 Aug 2022 • Zhangzi Zhu, Yu Hao, Wenqing Zhang, Chuhui Xue, Song Bai
This report presents our 2nd place solution to ECCV 2022 challenge on Out-of-Vocabulary Scene Text Understanding (OOV-ST) : Cropped Word Recognition.
no code implementations • 7 Jun 2022 • Zhangzi Zhu, Hong Qu
In the dataset of image captioning, each image is aligned with several descriptions.
no code implementations • 16 Oct 2021 • Zhangzi Zhu, Tianlei Wang, Hong Qu
In this paper, we propose a novel reinforcement training method for structure-related control signals: Self-Annotated Training (SAT), to improve both the accuracy and controllability of CIC models.
no code implementations • 20 Jan 2021 • Zhangzi Zhu, Tianlei Wang, Hong Qu
With such a control signal, the controllability and diversity of existing captioning models are enhanced.