4 papers
Query-Driven Multimodal Information Extraction from Long Documents
Yikai Gao, Ding Xia, Xi Yang
In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like D…
Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation
Jianing Zhang, Runan Li, Honglin Pang +5
Deciphering ancient Chinese Oracle Bone Script (OBS) is a challenging task that offers insights into the beliefs, systems, and culture of the ancient era. Existing approaches treat…
PairingNet: A Learning-based Pair-searching and -matching Network for Image Fragments
Rixin Zhou, Ding Xia, Yi Zhang +3
In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods…
SpaceEditing: Integrating Human Knowledge into Deep Neural Networks via Interactive Latent Space Editing
Jiafu Wei, Ding Xia, Haoran Xie +3
We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classif…