Zhuoyao Liu — accepted AI-conference papers

2026

PCSR: Pseudo-label Consistency-Guided Sample Refinement for Noisy Correspondence Learning

Zhuoyao Liu, Yang Liu, Wentao Feng, Shudong Huang

AAAI 2026technical

Cross-modal retrieval aims to align different modalities via semantic similarity. However, existing methods often assume that image-text pairs are perfectly aligned, overlooking Noisy Correspondences in real data. These misaligned pairs misguide similarity learning and degrade retrieval performance.

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Aligning Information Capacity Between Vision and Language via Dense-to-Sparse Feature Distillation for Image-Text Matching

Yang Liu, Wentao Feng, Zhuoyao Liu, Shudong Huang, Jiancheng Lv

ICCV 2025poster

Enabling Visual Semantic Models to effectively handle multi-view description matching has been a longstanding challenge. Existing methods typically learn a set of embeddings to find the optimal match for each view's text and compute similarity. However, the visual and text embeddings learned through…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗