Qiushi Xia — accepted AI-conference papers

2026

Quota-Calibrated Fine-Grained Alignment with Context-Aware Marginals for Text-based Person Retrieval

Dongsheng Li, Xinyuan Guo, Huijie Zhang, Pingting Hao, Qiushi Xia

CVPR 2026

The core challenge in Text-based Person Retrieval (TPR) lies in establishing fine-grained, many-to-many semantic alignment between textual words and visual regions. Existing methods predominantly rely on pointwise similarity or attention mechanisms, implicitly assuming matches are independent and ba

Cited by 0 Source ↗Scholar ↗

2025

An Efficient Pore Annotation Framework for Tight Sandstone Images with Segment Anything Model

Dongsheng Li, Chunyan Zang, Huijie Zhang, Yiming Lin, Qiushi Xia

ICASSP 2025accepted

Analyzing pore structures in tight sandstone thin sections is pivotal for assessing reservoir quality and predicting hydrocarbon migration, providing critical guidance for the formulation of energy extraction strategies. However, the significant variability in pore morphology, scale, and quantity re…

Cited by 0 Source ↗Scholar ↗