6 papers
EmoGenie: Benchmarking and Evaluating Expressed and Evoked Emotion in T2I Generation with MLLMs
Zixuan Xing, Lancheng Gao, Shengyan Li +4
Rapid advances in artificial intelligence-generated content (AIGC) have significantly promoted using text-to-image (T2I) models to generate images with specific affective intention…
Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection
Zhaolin Cai, Huiyu Duan, Liu Yang +5
Human-object interaction (HOI) detection aims to localize human-object pairs and recognize their interactions. Traditional supervised methods perform strongly but rely on task-spec…
ELIQ: A Label-Free Framework for Quality Assessment of Evolving AI-Generated Images
Xinyue Li, Zhiming Xu, Min Tang +5
Generative text-to-image models are advancing at an unprecedented pace, continuously shifting the perceptual quality ceiling and rendering previously collected labels unreliable fo…
Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs
Ningyu Sun, Zhaolin Cai, Zitong Xu +5
Text-guided human pose editing has gained significant traction in AIGC applications. However,it remains plagued by structural anomalies and generative artifacts. Existing evaluatio…
Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs
Zhaolin Cai, Huiyu Duan, Zitong Xu +6
Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them. Existing methods operate under a closed-world assumption, treating t…
ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
Zitong Xu, Huiyu Duan, Xiaoyu Wang +6
With the rapid advancement of generative models, powerful image editing methods now enable diverse and highly realistic image manipulations that far surpass traditional deepfake te…