Bingjie Xu — accepted AI-conference papers

2026

Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization

Jiawei Mao, Xiaoke Huang, Yunfei Xie, Yuanqi Chang, Mude Hui, Bingjie Xu +4

ICLR 2026poster

This paper introduces **Story-Iter**, a new training-free iterative paradigm to enhance long-story generation. Unlike existing methods that rely on fixed reference images to construct a complete story, our approach features a novel external **iterative paradigm**, extending beyond the internal itera…

Cited by 0 Source ↗code ↗Scholar ↗

2019

Learning to Detect Human-Object Interactions With Knowledge

Bingjie Xu, Yongkang Wong, Junnan Li, Qi Zhao, Mohan S. Kankanhalli

CVPR 2019poster

The recent advances in instance-level detection tasks lay a strong foundation for automated visual scenes understanding. However, the ability to fully comprehend a social scene still eludes us. In this work, we focus on detecting human-object interactions (HOIs) in images, an essential step towards…

Cited by 191 PDF ↗Scholar ↗