Blind image quality assessment (BIQA) is essential for evaluating and optimizing visual experience. Existing BIQA methods typically aggregate features from multiple backbone stages without accounting for their unequal contributions to quality prediction. Furthermore, uniformly supervising all experts may constrain thei...
Long Tang, Guo-Quan Zheng, Hui-Yu Duan et al.· 0 citations
Rendering clear and accurate text is a critical capability of text-to-image (T2I) models. Despite rapid advances in T2I generation, the systematic and human-aligned evaluation of text rendering remains underexplored. Existing benchmarks often suffer from limited scenario coverage, a lack of bilingual support, and an ov...
Zhi-Chao Ma, Jia-Rui Wang, Xiong-Kuo Min· Proceedings of the 34th ACM...· 0 citations
Rendering clear and accurate text is a critical capability of text-to-image (T2I) models. Despite rapid advances in T2I generation, the systematic and human-aligned evaluation of text rendering remains underexplored. Existing benchmarks often suffer from limited scenario coverage, a lack of bilingual support, and an ov...
Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform strongly but rely on task-specific training. Recent multimodal large language models (MLLMs) offer a promising route to training-free HOI detection through their broad vi...
Zhao-Lin Cai, Hui-Yu Duan, Liu Yang et al.· 0 citations
AI video generation has advanced rapidly and entered widespread commercial use. As a result, quality differences among videos produced by state-of-the-art AI video generation models~(AIVGMs) have become increasingly difficult to discern using conventional evaluation criteria, such as visual fidelity and semantic instru...
Zi-Heng Jia, Jia-Ying Qian, Zi-Cheng Zhang et al.· 0 citations
This work introduces SQUARE-Bench, a comprehensive benchmark that systematically evaluates LMM capabilities as evaluators of AI-generated images across four aspects: Semantics, Quality, Authenticity, and Responsibility, and conducts a proof-of-concept study of LMM-guided iterative editing.
This work proposes LLaVA-Assessor, a unified data construction and model training system for LMM-based machine vision, and introduces a simple yet effective prompt disentanglement strategy to alleviate training-objective confusion in multi-task learning, thereby enabling stable and coherent joint training.
Zi-Heng Jia, Zi-Cheng Zhang, Jia-Ying Qian et al.· 0 citations
TREND-10K is introduced, a next-generation comprehensive VQA dataset consisting of the trend-driven part and the static part, containing $10,000$ videos across a wide spectrum of content types, and presents a robust framework for advancing VQA, addressing challenges caused by the temporal evolution of user perceptual h...
Zi-Heng Jia, Zi-Cheng Zhang, Jun-Qi Zhang et al.· 0 citations
This work extends the previous dataset HVEval with pairwise preference annotations and proposes MoE-Rater, a Mixture-of-Experts (MoE)-inspired and multimodal large language model (MLLM)-based all-in-one method that supports multi-dimensional quality rating, multi-dimensional pairwise comparison, and category-specific q...
Si-Jing Wu, Yun-Hao Li, Hui-Yu Duan et al.· IEEE transactions on circuit...· 4 citations
MIE-Bench is introduced, the first large-scale multiple image editing benchmark with fine-grained human preference annotations and MIEScore, a multimodal large language model (MLLM)-based evaluation model enhanced with skill optimization and multi-dimensional supervised fine-tuning, to provide human-aligned feedback fo...
Zi-Tong Xu, Huiyu Duan, Xinyu Zhang et al.· 0 citations
This model leverages different layers of the large language model (LLM) decoder, treating them as multiple detectors that perform synchronous distortion detection using multi-level features, which helps mitigate the ambiguous foreground-background separation commonly encountered in the S2A problem.
Zi-Heng Jia, Yingji Liang, Jia-Ying Qian et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.