Kai WANG

Kai WANG

Kai WANG

Titulaire d'une HDR obtenue en 2022

Personnel CNRS Permanent

Site Ampère

Bureau : B138

Téléphone : 04 76 82 62 63

Département Science des Données
PICSA

Biographie

(à compléter)

Publications / Travaux


58 documents

Articles dans une revue22 documents

  • Ji Li, Kai Wang. Building a Universal Detector of AI‐Generated Images Without Training on Them. International Journal of Intelligent Systems, 2025, 2025 (Special Issue: Active Defense and Forensics Against Deepfake), Article ID 8530953, 23 p. ⟨10.1155/int/8530953⟩. ⟨hal-05294996⟩
  • Yacine Bouhamidi, Kai Wang. Simple Methods for Improving the Forensic Classification between Computer-Graphics Images and Natural Images. Forensic Sciences, 2024, 4 (1), pp.164-183. ⟨10.3390/forensicsci4010010⟩. ⟨hal-04570386⟩
  • Weize Quan, Pengfei Deng, Kai Wang, Dong-Ming Yan. CGFormer: ViT-Based Network for Identifying Computer-Generated Images with Token Labeling. IEEE Transactions on Information Forensics and Security, 2024, 19, pp.235-250. ⟨10.1109/TIFS.2023.3322083⟩. ⟨hal-04270809⟩
  • Kai Wang. Self-Supervised Learning for the Distinction between Computer-Graphics Images and Natural Images. Applied Sciences, 2023, 13 (3), pp.1887. ⟨10.3390/app13031887⟩. ⟨hal-04088842⟩
  • Ivan Castillo Camacho, Kai Wang. Convolutional neural network initialization approaches for image manipulation detection. Digital Signal Processing, 2022, 122 (April), pp.103376. ⟨10.1016/j.dsp.2021.103376⟩. ⟨hal-03513870⟩
  • Ludovic Darmet, Kai Wang, François Cayre. Disentangling Copy-Moved Source and Target Areas. Applied Soft Computing, 2021, 109, pp.107536:1-10. ⟨10.1016/j.asoc.2021.107536⟩. ⟨hal-03242196⟩
  • Ivan Castillo Camacho, Kai Wang. A Comprehensive Review of Deep-Learning-Based Methods for Image Forensics. Journal of Imaging, 2021, Special Issue Image and Video Forensics, 7 (4), pp.69:1-39. ⟨10.3390/jimaging7040069⟩. ⟨hal-03237610⟩
  • Weize Quan, Kai Wang, Dong-Ming Yan, Xiaopeng Zhang, Denis Pellerin. Learn with Diversity and from Harder Samples: Improving the Generalization of CNN-Based Detection of Computer-Generated Images. Forensic Science International: Digital Investigation, 2020, 35, pp.301023:1-12. ⟨10.1016/j.fsidi.2020.301023⟩. ⟨hal-02929038⟩
  • Ludovic Darmet, Kai Wang, François Cayre. GRAFT: Unsupervised Adaptation to Resizing for Detection of Image Manipulation. IEEE Access, 2020, 8, pp.55619 – 55632. ⟨10.1109/ACCESS.2020.2980992⟩. ⟨hal-02519535⟩
  • Weize Quan, Kai Wang, Dong-Ming Yan, Xiaopeng Zhang. Distinguishing Between Natural and Computer-Generated Images Using Convolutional Neural Networks. IEEE Transactions on Information Forensics and Security, 2018, 13 (11), pp.2772-2787. ⟨10.1109/TIFS.2018.2834147⟩. ⟨hal-01789442⟩
  • Kai Wang. A simple and effective image-statistics-based approach to detecting recaptured images from LCD screens. Digital Investigation, 2017, 23, pp.75-87. ⟨10.1016/j.diin.2017.10.001⟩. ⟨hal-01617168⟩
  • Georges Nader, Kai Wang, Franck Hétroy-Wheeler, Florent Dupont. Just Noticeable Distortion Profile for Flat-Shaded 3D Mesh Surfaces. IEEE Transactions on Visualization and Computer Graphics, 2016, 22 (11), pp.2423-2436. ⟨10.1109/TVCG.2015.2507578⟩. ⟨hal-01242271⟩
  • Georges Nader, Kai Wang, Franck Hétroy-Wheeler, Florent Dupont. Visual Contrast Sensitivity and Discrimination for 3D Meshes and their Applications. Computer Graphics Forum, 2016, 35 (7), pp.497-506. ⟨10.1111/cgf.13046⟩. ⟨hal-01376275⟩
  • Wei Fan, Kai Wang, François Cayre, Zhang Xiong. Median Filtered Image Quality Enhancement and Anti-Forensics via Variational Deconvolution. IEEE Transactions on Information Forensics and Security, 2015, 10 (5), pp.1076-1091. ⟨10.1109/TIFS.2015.2398362⟩. ⟨hal-01165592⟩
  • Fakhri Torkhani, Kai Wang, Jean-Marc Chassery. Perceptual quality assessment of 3D dynamic meshes: Subjective and objective studies. Signal Processing: Image Communication, 2015, 31 (2), pp.185-204. ⟨10.1016/j.image.2014.12.008⟩. ⟨hal-01118984⟩
  • Wei Fan, Kai Wang, François Cayre, Zhang Xiong. JPEG anti-forensics with improved tradeoff between forensic undetectability and image quality. IEEE Transactions on Information Forensics and Security, 2014, 9 (8), pp.1211-1226. ⟨10.1109/TIFS.2014.2317949⟩. ⟨hal-01048725⟩
  • Fakhri Torkhani, Kai Wang, Jean-Marc Chassery. A curvature-tensor-based perceptual quality metric for 3D triangular meshes. Machine Graphics & Vision, 2014, 23 (12), pp.59-82. ⟨10.22630/MGV.2014.23.1.4⟩. ⟨hal-00995716⟩
  • Massimiliano Corsini, Mohamed-Chaker Larabi, Guillaume Lavoué, Oldrich Petrík, Libor Vása, et al.. Perceptual metrics for static and dynamic triangle meshes. Computer Graphics Forum, 2013, 32 (1), pp.101-125. ⟨10.1111/cgf.12001⟩. ⟨hal-00784901⟩
  • Kai Wang, Fakhri Torkhani, Annick Montanvert. A fast roughness-based approach to the assessment of 3D mesh visual quality. Computers and Graphics, 2012, 36 (7), pp.808-818. ⟨10.1016/j.cag.2012.06.004⟩. ⟨hal-00734726⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. Robust and blind mesh watermarking based on volume moments. Computers and Graphics, 2011, 35 (1), pp.1-19. ⟨hal-00958591⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. A comprehensive survey on three-dimensional mesh watermarking. IEEE Transactions on Multimedia, 2008, 8, 10, pp.1513-1527. ⟨hal-01531229⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. Hierarchical watermarking of semiregular meshes based on wavelet transform. IEEE Transactions on Information Forensics and Security, 2008, 4, 3, pp.620-634. ⟨hal-01531216⟩

Communications dans un congrès33 documents

  • Nathan Chanez, Douglas Mateus Machado, Kai Wang, Pascal Urard, Severin Trochut. A Unified Heterogeneous Graph Representation for Multi-Circuit and Voltage-Temperature-Aware Surrogate Modeling of Analog Circuits. ICPECA 2026 – IEEE 6th International Conference on Power, Electronics and Computer Applications (ICPECA 2026), Jan 2026, Shenyang, China. ⟨hal-05666120⟩
  • Zhipeng Yuan, Kai Wang, Weize Quan, Dong-Ming Yan, Tieru Wu. CLIP-Flow: A Universal Discriminator for AI-Generated Images Inspired by Anomaly Detection. DFF 2025 – 1st Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media (DFF 2025), Oct 2025, Dublin, Ireland. pp.1-9, ⟨10.1145/3746265.3759663⟩. ⟨hal-05296631⟩
  • Nathan Chanez, Pascal Urard, Severin Trochut, Roberto Guizzetti, Kai Wang, et al.. Cyber Wolf: A Hybrid Optimization Framework Leveraging Heterogeneous Graphs and Multimodal Surrogate Simulators for Fast Analog Sizing. AEET 2025 – International Conference on Applied Electrical Engineering and Technology, Aug 2025, Taiyuan, China. pp.1-5. ⟨hal-05295885⟩
  • Yacine Bouhamidi, Kai Wang, José-Ernesto Gomez-Balderas. An Efficient Method to Detect both Insertion and Removal Attacks in 3D LiDAR Point Clouds for Autonomous Vehicle Security. IWSSIP 2025 – 32nd International Conference on Systems, Signals and Image Processing, Jun 2025, Skopje, Macedonia. pp.1-5, ⟨10.1109/IWSSIP66997.2025.11151898⟩. ⟨hal-05294984⟩
  • Ji Li, Kai Wang. Detecting Computer-Generated Images by Using Only Real Images. ICMV 2024 – 17th International Conference on Machine Vision, Oct 2024, Edinburgh, United Kingdom. ⟨hal-04751823⟩
  • Ivan Castillo Camacho, Kai Wang. Data-dependent scaling of CNN’s first layer for improved image manipulation detection. IWDW 2020 – 19th International Workshop on Digital-forensics and Watermarking, Nov 2020, Melbourne (online), Australia. pp.208-223, ⟨10.1007/978-3-030-69449-4_16⟩. ⟨hal-03000629⟩
  • Ludovic Darmet, Kai Wang, François Cayre. Weakly Supervised Adaptation to Re-sizing for Image Manipulation Detection on Small Patches. IWDW 2019 – 18th International Workshop on Digital-forensics and Watermarking, Nov 2019, Chengdu, China. ⟨hal-02335866⟩
  • Weize Quan, Kai Wang, Dong-Ming Yan, Denis Pellerin, Xiaopeng Zhang. Impact of Data Preparation and CNN’s First Layer on Performance of Image Forensics: A Case Study of Detecting Colorized Images. WI ’19 Companion IEEE/WIC/ACM International Conference on Web Intelligence, Oct 2019, Thessaloniki, Greece. pp.127-131, ⟨10.1145/3358695.3360890⟩. ⟨hal-02321146⟩
  • Weize Quan, Kai Wang, Dong-Ming Yan, Denis Pellerin, Xiaopeng Zhang. Improving the generalization of colorized image detection with enhanced training of CNN. ISPA 2019 – 11th International Symposium on Image and Signal Processing and Analysis, Sep 2019, Dubrovnik, Croatia. pp.246-252. ⟨hal-02306547⟩
  • Ludovic Darmet, Kai Wang, François Cayre. GRAFT : Adaptation non-supervisée au re-dimensionnement pour la détection de manipulation d’image. GRETSI 2019 – XXVIIème Colloque Francophone de Traitement du Signal et des Images, Aug 2019, Lille, France. ⟨hal-02335837⟩
  • Ivan Castillo Camacho, Kai Wang. A simple and effective initialization of CNN for forensics of image processing operations. IH&MMSEC 2019 – 7th ACM Workshop on Information Hiding and Multimedia Security, Jul 2019, Paris, France. ⟨hal-02149109⟩
  • Yiqun Wang, Jianwei Guo, Dong-Ming Yan, Kai Wang, Xiaopeng Zhang. A robust local spectral descriptor for matching non-rigid shapes with incompatible shape structures. CVPR 2019 – IEEE Conference on Computer Vision and Pattern Recognition, Jun 2019, Long Beach, CA, United States. ⟨hal-02149076⟩
  • Joseph Baudrillard, Sebastien Guillon, Jean-Marc Chassery, Michèle Rombaut, Kai Wang. Parameterization of polylines in unorganized cross-sections and open surface reconstruction. CS 2018 – 9th International Conference on Curves and Surfaces, Jun 2018, Arcachon, France. ⟨hal-01774804⟩
  • Joseph Baudrillard, Sébastien Guillon, Jean-Marc Chassery, Michèle Rombaut, Kai Wang. Reconstruction of piecewise-explicit surfaces from three-dimensional polylines. International Conference on Geographical Information Systems Theory, Applications and Management (Doctoral Consortium), Mar 2018, Funchal, Madeira, Portugal. ⟨hal-01720662⟩
  • Anh Thu Phan Ho, Kai Wang, François Cayre. An effective histogram-based approach to JPEG-100 forensics. IPTA 2016 – 6th International Conference on Image Processing Theory, Tools and Applications (IPTA’16), Dec 2016, Oulu, Finland. ⟨hal-01406265⟩
  • Georges Nader, Kai Wang, Franck Hétroy-Wheeler, Florent Dupont. Modèle Perceptuel pour la Détection du Seuil de Visibilité des Distorsions sur un Maillage 3D. AFIG 2015 – 28èmes journées de l’Association Française en Informatique Graphique, Nov 2015, Lyon, France. ⟨hal-01245373⟩
  • Wei Fan, Kai Wang, François Cayre. General-purpose image forensics using patch likelihood under image statistical models. WIFS 2015 – 7th IEEE International Workshop on Information Forensics and Security (WIFS 2015), IEEE, Nov 2015, Rome, Italy. 6 p. ⟨hal-01240755⟩
  • Fakhri Torkhani, Kai Wang, Jean-Marc Chassery. Métrique de qualité perceptuelle des maillages 3D fondée sur les tenseurs de courbure. GRETSI 2013 – XXIVème Colloque francophone de traitement du signal et des images, Sep 2013, Brest, France. pp.Article ID175. ⟨hal-00874012⟩
  • Wei Fan, Kai Wang, François Cayre, Zhang Xiong. JPEG anti-forensics using non-parametric DCT quantization noise estimation and natural image statistics. IH&MMSEC 2013 – 1st ACM Workshop on Information Hiding and Multimedia Security (IH & MMSEC 2013), Jun 2013, Montpellier, France. pp.117-122. ⟨hal-00836438⟩
  • Wei Fan, Kai Wang, François Cayre, Zhang Xiong. A variational approach to JPEG anti-forensics. ICASSP 2013 – 38th IEEE International Conference on Acoustics, Speech and Signal Processing, May 2013, Vancouver, Canada. pp.3058-3062. ⟨hal-00836437⟩
  • Fakhri Torkhani, Kai Wang, Jean-Marc Chassery. A Curvature Tensor Distance for Mesh Visual Quality Assessment. ICCVG 2012 – International Conference on Computer Vision and Graphics, Sep 2012, Warsaw, Poland. 253-263, 11 p. ⟨hal-00719315⟩
  • Wei Fan, Kai Wang, François Cayre, Zhang Xiong. 3D lighting-based image forgery detection using shape-from-shading. EUSIPCO 2012 – 20th European Signal Processing Conference, Aug 2012, Bucarest, Romania. pp.1777-1781. ⟨hal-00734749⟩
  • Massimiliano Corsini, Mohamed-Chaker Larabi, Guillaume Lavoué, Oldrich Petrík, Libor Vása, et al.. Perceptual metrics for static and dynamic triangle meshes. Eurographics 2012 – 33rd Annual Conference of the European Association for Computer Graphics, May 2012, Cagliari, Italy. pp.135-157, ⟨10.2312/conf/EG2012/stars/135-157⟩. ⟨hal-00719352⟩
  • Fakhri Torkhani, Kai Wang, Annick Montanvert. Towards Perceptual Quality Evaluation of Dynamic Meshes. APGV 2011 – 8th Symposium on Applied Perception in Graphics and Visualization, Aug 2011, Toulouse, France. pp.116. ⟨hal-00628503⟩
  • Dong-Ming Yan, Kai Wang, Bruno Lévy, Laurent Alonso. Computing 2D Periodic Centroidal Voronoi Tessellation. ISVD 2011 – 8th International Symposium on Voronoi Diagrams in Science and Engineering – ISVD2011, Jun 2011, Qingdao, China. ⟨10.1109/ISVD.2011.31⟩. ⟨inria-00605927⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt, Xiyan He. A benchmark for 3D mesh watermarking. Shape Modeling International 2010, Jun 2010, Aix-en-Provence, France. pp.231-235. ⟨hal-00958600⟩
  • Kai Wang, Ming Luo, Adrian G. Bors, Florence Denis. Blind and robust mesh watermarking using manifold harmonics. IEEE International Conference on Image Processing 2009, Nov 2009, Cairo, Egypt. pp.3657-3660. ⟨hal-00958603⟩
  • Ming Luo, Kai Wang, Adrian G. Bors, Guillaume Lavoué. Local patch blind spectral watermarking method for 3D graphics. International Workshop on Digital Watermarking 2009, Aug 2009, Surrey, United Kingdom. pp.211-226. ⟨hal-00958606⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. Tatouage robuste et aveugle de maillages 3D basé sur les moments volumiques. Journées CORESA – COmpression et REprésentation des Signaux Audiovisuels 2009, Mar 2009, Toulouse, France. pp.162-167. ⟨hal-00958607⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. A fragile watermarking scheme for authentication of semi-regular meshes. Eurographics Short Papers, Jul 2008, Crete, Greece, Greece. pp.5-8. ⟨hal-01541598⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. Tatouage hiérarchique et aveugle de maillages tridimensionnels. CORESA’07 : COmpression et REprésentation des Signaux Audiovisuels, Nov 2007, Montpellier, France. pp.139-143. ⟨hal-01502160⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. Hierarchical blind watermarking of 3D triangular meshes. IEEE International Conference on Multimedia & Expo, Jul 2007, Beijing, China, China. pp.1235-1238. ⟨hal-01541593⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. Three-dimensional meshes watermarking: Review and attack-centric investigation. International Workshop on Information Hiding, Jul 2007, Saint-Malo, France, France. pp.50-64. ⟨hal-01541597⟩

Chapitres d’ouvrage2 documents

  • Joseph Baudrillard, Sebastien Guillon, Jean-Marc Chassery, Michèle Rombaut, Kai Wang. Reconstruction of piecewise-explicit surfaces from three-dimensional polylines and heightmap fragments. Geographical Information Systems Theory, Applications and Management (4th International Conference, GISTAM 2018, Funchal, Madeira, Portugal, March 17–19, 2018, Revised Selected Papers), pp.1-27, 2019, ⟨10.1007/978-3-030-29948-4_1⟩. ⟨hal-02306545⟩
  • Kai Wang, Guillaume Lavoué, Florence Denis, Atilla Baskurt. Blind watermarking of three-dimensional meshes: Review, recent advances and future opportunities. Advanced Techniques in Multimedia Watermarking: Image, Video and Audio Applications, IGI Global, pp.200-227, 2010. ⟨hal-00958594⟩

Pré-publications, Documents de travail1 document

  • Kai Wang. Quantization-based blind watermarking of three-dimensional meshes. 2009. ⟨hal-01459848⟩

Documents récupérés de l’archive ouverte HAL logo

Contact

field is required
field is required
field is required

Restez Connectés

facebook linkedin youtube
Logo GIOSA-lab Pied de Page

11 rue des Mathématiques             

38402 Saint-Martin-d’Hères

Horaires d'Ouverture

Lun – Ven : 7:30 – 19:00

Téléphone 33 (0)4 76 82 71 31

Liens Utiles

Newsletter du GIPSA-lab

La newsletter GIPSA-lab apporte des informations sur les activités et la vie du laboratoire (À venir).

GIPSA-lab - Service SI-Web © 2026 Tous droits réservés.