When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Jihyeon, Kim, Sohee, Lee, Soosan, Jung, Souhwan, Rehg, James Matthew, Choi, Hyesong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
di: Li, Xiang, et al.
Pubblicazione: (2025)

In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation
di: Lai, Bolin, et al.
Pubblicazione: (2022)

Supporting Mitosis Detection AI Training with Inter-Observer Eye-Gaze Consistencies
di: Gu, Hongyan, et al.
Pubblicazione: (2024)

DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images
di: Kara, Ozgur, et al.
Pubblicazione: (2025)

The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP
di: Nam, Kahyeon, et al.
Pubblicazione: (2026)

EyeCue: Driver Cognitive Distraction Detection via Gaze-Empowered Egocentric Video Understanding
di: Zhang, Lang, et al.
Pubblicazione: (2026)

FUSE: Unifying Spectral and Semantic Cues for Robust AI-Generated Image Detection
di: Hossain, Md. Zahid, et al.
Pubblicazione: (2025)

MaDis-Stereo: Enhanced Stereo Matching via Distilled Masked Image Modeling
di: Ahn, Jihye, et al.
Pubblicazione: (2024)

Eyes Tell the Truth: GazeVal Highlights Shortcomings of Generative AI in Medical Imaging
di: Wong, David, et al.
Pubblicazione: (2025)

Semantic-Aware Reconstruction Error for Detecting AI-Generated Images
di: Kang, Ju Yeon, et al.
Pubblicazione: (2025)

Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
di: Kim, Jiyeong, et al.
Pubblicazione: (2026)

Improving Generative Pre-Training: An In-depth Study of Masked Image Modeling and Denoising Models
di: Choi, Hyesong, et al.
Pubblicazione: (2024)

Aggregating Diverse Cue Experts for AI-Generated Image Detection
di: Tan, Lei, et al.
Pubblicazione: (2026)

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders
di: Ryan, Fiona, et al.
Pubblicazione: (2024)

STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
di: Kim, Junho, et al.
Pubblicazione: (2026)

UniTT-Stereo: Unified Training of Transformer for Enhanced Stereo Matching
di: Kim, Soomin, et al.
Pubblicazione: (2024)

CoT-Pose: Chain-of-Thought Reasoning for 3D Pose Generation from Abstract Prompts
di: Cha, Junuk, et al.
Pubblicazione: (2025)

When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection
di: Shuai, Chao, et al.
Pubblicazione: (2026)

Gaze Prediction in Virtual Reality Without Eye Tracking Using Visual and Head Motion Cues
di: Petrou, Christos, et al.
Pubblicazione: (2026)

Emerging Property of Masked Token for Effective Pre-training
di: Choi, Hyesong, et al.
Pubblicazione: (2024)

Roll Your Eyes: Gaze Redirection via Explicit 3D Eyeball Rotation
di: Choi, YoungChan, et al.
Pubblicazione: (2025)

Seeing Eye to AI: Comparing Human Gaze and Model Attention in Video Memorability
di: Kumar, Prajneya, et al.
Pubblicazione: (2023)

When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters
di: Lyu, Liangwei, et al.
Pubblicazione: (2026)

Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation
di: Lai, Bolin, et al.
Pubblicazione: (2023)

SG-MIM: Structured Knowledge Guided Efficient Pre-training for Dense Prediction
di: Son, Sumin, et al.
Pubblicazione: (2024)

Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
di: Kim, Gahyeon, et al.
Pubblicazione: (2025)

AAPL: Adding Attributes to Prompt Learning for Vision-Language Models
di: Kim, Gahyeon, et al.
Pubblicazione: (2024)

Symmetry Strikes Back: From Single-Image Symmetry Detection to 3D Generation
di: Li, Xiang, et al.
Pubblicazione: (2024)

SDDGR: Stable Diffusion-based Deep Generative Replay for Class Incremental Object Detection
di: Kim, Junsu, et al.
Pubblicazione: (2024)

Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
di: Wang, Hengfei, et al.
Pubblicazione: (2026)

Three Forensic Cues for JPEG AI Images
di: Bergmann, Sandra, et al.
Pubblicazione: (2025)

Eye Gaze as a Signal for Conveying User Attention in Contextual AI Systems
di: Wilson, Ethan, et al.
Pubblicazione: (2025)

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models
di: Kim, Jeongho, et al.
Pubblicazione: (2024)

GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays
di: Wong, David, et al.
Pubblicazione: (2026)

Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images
di: Tan, Chuangchuang, et al.
Pubblicazione: (2025)

Reciprocal Attention Mixing Transformer for Lightweight Image Restoration
di: Choi, Haram, et al.
Pubblicazione: (2023)

DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization
di: Nam, Jisu, et al.
Pubblicazione: (2024)

Degradation-Consistent Paired Training for Robust AI-Generated Image Detection
di: Yang, Zongyou, et al.
Pubblicazione: (2026)

Rethinking the Use of Vision Transformers for AI-Generated Image Detection
di: Park, NaHyeon, et al.
Pubblicazione: (2025)

Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation
di: Jang, Youngdong, et al.
Pubblicazione: (2026)