Copertina

Beyond Semantics: Uncovering the Physics of Fakes via Universal Physical Descriptors for Cross-Modal Synthetic Detection

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Qiu, Mei, Zhao, Jianqiang, Qu, Yanyun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor
di: Lin, Ethan, et al.
Pubblicazione: (2025)

FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection
di: Zhu, Leqi, et al.
Pubblicazione: (2026)

CLIP-FSAC++: Few-Shot Anomaly Classification with Anomaly Descriptor Based on CLIP
di: Zuo, Zuo, et al.
Pubblicazione: (2024)

Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation
di: Wu, Yao, et al.
Pubblicazione: (2024)

PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation
di: Tan, Wenbin, et al.
Pubblicazione: (2026)

Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection
di: Otake, Hina, et al.
Pubblicazione: (2024)

Multi-Channel Cross Modal Detection of Synthetic Face Images
di: Ibsen, M., et al.
Pubblicazione: (2023)

SpatiaLoc: Leveraging Multi-Level Spatial Enhanced Descriptors for Cross-Modal Localization
di: Shang, Tianyi, et al.
Pubblicazione: (2026)

Cross-Domain Semantic Segmentation with Large Language Model-Assisted Descriptor Generation
di: Hughes, Philip, et al.
Pubblicazione: (2025)

Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
di: Li, Jiahao, et al.
Pubblicazione: (2025)

DPL: Cross-quality DeepFake Detection via Dual Progressive Learning
di: Zhang, Dongliang, et al.
Pubblicazione: (2024)

Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
di: Chen, Yujun, et al.
Pubblicazione: (2023)

Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model
di: Zuo, Zuo, et al.
Pubblicazione: (2025)

SP3D: Boosting Sparsely-Supervised 3D Object Detection via Accurate Cross-Modal Semantic Prompts
di: Zhao, Shijia, et al.
Pubblicazione: (2025)

Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
di: Li, Jiahao, et al.
Pubblicazione: (2025)

RASR: Retrieval-Augmented Semantic Reasoning for Fake News Video Detection
di: Li, Hui, et al.
Pubblicazione: (2026)

Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
di: Li, Jiahao, et al.
Pubblicazione: (2026)

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation
di: Wen, Siwei, et al.
Pubblicazione: (2025)

Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
di: Zhou, Hefeng, et al.
Pubblicazione: (2026)

Cross-Modal Scene Semantic Alignment for Image Complexity Assessment
di: Luo, Yuqing, et al.
Pubblicazione: (2025)

Text Modality Oriented Image Feature Extraction for Detecting Diffusion-based DeepFake
di: Yang, Di, et al.
Pubblicazione: (2024)

Beyond Accuracy: Uncovering the Role of Similarity Perception and its Alignment with Semantics in Supervised Learning
di: Filus, Katarzyna, et al.
Pubblicazione: (2025)

Head-wise Modality Specialization within MLLMs for Robust Fake News Detection under Missing Modality
di: Qian, Kai, et al.
Pubblicazione: (2026)

CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation
di: Zuo, Zuo, et al.
Pubblicazione: (2024)

CrossWeaver: Cross-modal Weaving for Arbitrary-Modality Semantic Segmentation
di: Zhang, Zelin, et al.
Pubblicazione: (2026)

Asymmetric Cross-Modal Knowledge Distillation: Bridging Modalities with Weak Semantic Consistency
di: Wei, Riling, et al.
Pubblicazione: (2025)

Exploring Image Representation with Decoupled Classical Visual Descriptors
di: Qu, Chenyuan, et al.
Pubblicazione: (2025)

Learning Semantic Facial Descriptors for Accurate Face Animation
di: Zhu, Lei, et al.
Pubblicazione: (2025)

Building a Strong Pre-Training Baseline for Universal 3D Large-Scale Perception
di: Chen, Haoming, et al.
Pubblicazione: (2024)

PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos
di: Cao, Meng, et al.
Pubblicazione: (2024)

Semantics-Oriented Multitask Learning for DeepFake Detection: A Joint Embedding Approach
di: Zou, Mian, et al.
Pubblicazione: (2024)

AlignGen: Boosting Personalized Image Generation with Cross-Modality Prior Alignment
di: Lin, Yiheng, et al.
Pubblicazione: (2025)

Incomplete Multimodal Industrial Anomaly Detection via Cross-Modal Distillation
di: Sui, Wenbo, et al.
Pubblicazione: (2024)

Semantic-Guided Natural Language and Visual Fusion for Cross-Modal Interaction Based on Tiny Object Detection
di: Huang, Xian-Hong, et al.
Pubblicazione: (2025)

TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection
di: Xiong, Xinqi, et al.
Pubblicazione: (2025)

Multimodal Cancer Survival Analysis via Hypergraph Learning with Cross-Modality Rebalance
di: Qu, Mingcheng, et al.
Pubblicazione: (2025)

FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models
di: Li, Yixuan, et al.
Pubblicazione: (2024)

SGAD: Semantic and Geometric-aware Descriptor for Local Feature Matching
di: Liu, Xiangzeng, et al.
Pubblicazione: (2025)

Self-Enhanced Image Clustering with Cross-Modal Semantic Consistency
di: Li, Zihan, et al.
Pubblicazione: (2025)

Dynamic Cross-Modal Alignment for Robust Semantic Location Prediction
di: Jing, Liu, et al.
Pubblicazione: (2024)