Xiaosong Han — accepted AI-conference papers

2026

CONQUER: CONTEXT-AWARE REPRESENTATION WITH QUERY ENHANCEMENT FOR TEXT-BASED PERSON SEARCH

ICASSP 2026poster

Text-Based Person Search (TBPS) aims to retrieve pedestrian images from large galleries using natural language descriptions. This task, essential for public safety applications, is hindered by cross-modal discrepancies and ambiguous user queries. We introduce CONQUER, a two-stage framework designed…

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

SpaEF: Spatially Resolved Transcriptomics Data Element-Wise Denoising Framework Powered by Large Models

Zekuan Shang, Xiaosong Han, Liupu Wang, Wei Du, Peng Zhao, Yuanshu Li +3

ICML 2026poster

For denoising Spatially Resolved Transcriptomics (SRT) data, existing methods often construct spot and gene graphs to model inter-spot and inter-gene relationships, respectively. However, these methods often introduce spurious similarity biases among spots when constructing the spot graph and fail t…

Cited by 0 Source ↗Scholar ↗