Xiaoliang Xu — accepted AI-conference papers

2025

Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learning

Yuxia Geng, Runkai Zhu, Jiaoyan Chen, Jintai Chen, Xiang Chen, Zhuo Chen +4

ACL 2025finding

Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL). However, due to the feature divergence of an attribute (resp. object) when combined with different objects (resp. attributes), it is challenging t…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint

Mengzhao Wang, Lingwei Lv, Xiaoliang Xu, Yuxiang Wang, Qiang Yue, Jiongkang Ni

NeurIPS 2023poster

This paper introduces an efficient and robust framework for hybrid query (HQ) processing, which combines approximate nearest neighbor search (ANNS) with attribute constraint. HQ aims to find objects that are similar to a feature vector and match some structured attributes. Existing methods handle AN…

Cited by 11 Source ↗PDF ↗Scholar ↗