Jia-Wei Ma — accepted AI-conference papers

2024

Attention Decoupling for Query-Based Object Detection

Jia-Wei Ma, Min Liang, Haixia Man, Shu Tian, Jingyan Qin, Xu-Cheng Yin

ICASSP 2024accepted

Benefiting from attention mechanisms, query-based detectors have a strong model capacity. They predict classification and regression by utilizing their shared queries and features in the decoder. Inter-task biases cause multi-directional gradients that disturb each other to limit model optimization.…

Cited by 0 Source ↗Scholar ↗

2024

LayoutFormer: Hierarchical Text Detection Towards Scene Text Understanding

Min Liang, Jia-Wei Ma, Xiaobin Zhu, Jingyan Qin, Xu-Cheng Yin

CVPR 2024poster

Existing scene text detectors generally focus on accurately detecting single-level (i.e. word-level line-level or paragraph-level) text entities without exploring the relationships among different levels of text entities. To comprehensively understand scene texts detecting multi-level texts while ex…

Cited by 2 Source ↗PDF ↗Scholar ↗