Dongxu Wu — accepted AI-conference papers

2026

Beyond Cosine Similarity: Magnitude-Aware CLIP for No-Reference Image Quality Assessment

Zhicheng Liao, Dongxu Wu, Zhenshan Shi, Sijie Mai, Hanwei Zhu, Lingyu Zhu +2

AAAI 2026technical

Recent efforts have repurposed the Contrastive Language-Image Pre-training (CLIP) model for No-Reference Image Quality Assessment (NR-IQA) by measuring the cosine similarity between the image embedding and textual prompts such as "a good photo" or "a bad photo." However, this semantic similarity ove

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Mitigating Perception Bias: A Training-Free Approach to Enhance LMM for Image Quality Assessment

Baoliang Chen, Siyi Pan, Dongxu Wu, Liang Xie, Xiangjie Sui, Lingyu Zhu +1

AAAI 2026technical

Despite the impressive performance of large multimodal models (LMMs) in high-level visual tasks, their capacity for image quality assessment (IQA) remains limited. One main reason is that LMMs are primarily trained for high-level tasks (e.g., image captioning), emphasizing unified image semantics ex

Cited by 0 Source ↗PDF ↗Scholar ↗