@inproceedings{bb99500,
AUTHOR = "Zeng, Y. and Patel, V.M. and Wang, H.C. and Huang, X. and Wang, T.C. and Liu, M.Y. and Balaji, Y.",
TITLE = "JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized
Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6786-6795",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96262"}
@inproceedings{bb99501,
AUTHOR = "Gong, B. and Huang, S. and Feng, Y.T. and Zhang, S.W. and Li, Y. and Liu, Y.",
TITLE = "Check, Locate, Rectify: A Training-Free Layout Calibration System for
Text- to- Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6624-6634",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96263"}
@inproceedings{bb99502,
AUTHOR = "Hoe, J.T. and Jiang, X.D. and Chan, C.S. and Tan, Y.P. and Hu, W.P.",
TITLE = "InteractDiffusion: Interaction Control in Text-to-Image Diffusion
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6180-6189",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96264"}
@inproceedings{bb99503,
AUTHOR = "Menon, S. and Misra, I. and Girdhar, R.",
TITLE = "Generating Illustrated Instructions",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6274-6284",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96265"}
@inproceedings{bb99504,
AUTHOR = "Yang, J.Y. and Feng, J.W. and Huang, H.",
TITLE = "EmoGen: Emotional Image Content Generation with Text-to-Image
Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6358-6368",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96266"}
@inproceedings{bb99505,
AUTHOR = "Yang, Y.J. and Gao, R. and Wang, X. and Ho, T.Y. and Xu, N. and xu, Q.",
TITLE = "MMA-Diffusion: MultiModal Attack on Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7737-7746",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96267"}
@inproceedings{bb99506,
AUTHOR = "Hedlin, E. and Sharma, G. and Mahajan, S. and He, X.Z. and Isack, H. and Kar, A. and Rhodin, H. and Tagliasacchi, A. and Yi, K.M.",
TITLE = "Unsupervised Keypoints from Pretrained Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22820-22830",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96268"}
@inproceedings{bb99507,
AUTHOR = "Sato, T. and Yue, J. and Chen, N. and Wang, N. and Chen, Q.A.",
TITLE = "Intriguing Properties of Diffusion Models: An Empirical Study of the
Natural Attack Capability in Text-to-Image Generative Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "24635-24644",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96269"}
@inproceedings{bb99508,
AUTHOR = "Gandikota, K.V. and Chandramouli, P.",
TITLE = "Text-Guided Explorable Image Super-Resolution",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "25900-25911",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96270"}
@inproceedings{bb99509,
AUTHOR = "Mo, W. and Zhang, T.Y. and Bai, Y. and Su, B. and Wen, J.R. and Yang, Q.",
TITLE = "Dynamic Prompt Optimizing for Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "26617-26626",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96271"}
@inproceedings{bb99510,
AUTHOR = "Smith, J.S. and Hsu, Y.C. and Kira, Z. and Shen, Y.L. and Jin, H.X.",
TITLE = "Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters",
BOOKTITLE = WhatNext24,
YEAR = "2024",
PAGES = "1744-1754",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96272"}
@inproceedings{bb99511,
AUTHOR = "Zhang, G. and Wang, K. and Xu, X.Q. and Wang, Z.Y. and Shi, H.",
TITLE = "Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models",
BOOKTITLE = WhatNext24,
YEAR = "2024",
PAGES = "1755-1764",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96273"}
@inproceedings{bb99512,
AUTHOR = "Tudosiu, P.D. and Yang, Y.X. and Zhang, S.F. and Chen, F. and McDonagh, S. and Lampouras, G. and Iacobacci, I. and Parisot, S.",
TITLE = "MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image
Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22413-22422",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96274"}
@inproceedings{bb99513,
AUTHOR = "Wang, F.F. and Tan, Z.T. and Wei, T.Y. and Wu, Y. and Huang, Q.D.",
TITLE = "SimAC: A Simple Anti-Customization Method for Protecting Face Privacy
Against Text-to-Image Synthesis of Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12047-12056",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96275"}
@inproceedings{bb99514,
AUTHOR = "Pang, L. and Yin, J. and Xie, H.R. and Wang, Q. and Li, Q. and Mao, X.D.",
TITLE = "Cross Initialization for Face Personalization of Text-to-Image Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8393-8403",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96276"}
@inproceedings{bb99515,
AUTHOR = "Xu, X.Q. and Guo, J.Y. and Wang, Z.Y. and Huang, G. and Essa, I. and Shi, H.",
TITLE = "Prompt-Free Diffusion: Taking 'Text' Out of Text-to-Image Diffusion
Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8682-8692",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96277"}
@inproceedings{bb99516,
AUTHOR = "Qi, T.H. and Fang, S.C. and Wu, Y. and Xie, H.T. and Liu, J.W. and Chen, L. and He, Q. and Zhang, Y.D.",
TITLE = "DEADiff: An Efficient Stylization Diffusion Model with Disentangled
Representations",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8693-8702",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96278"}
@inproceedings{bb99517,
AUTHOR = "Brack, M. and Friedrich, F. and Kornmeier, K. and Tsaban, L. and Schramowski, P. and Kersting, K. and Passos, A.",
TITLE = "LEDITS++: Limitless Image Editing Using Text-to-Image Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8861-8870",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96279"}
@inproceedings{bb99518,
AUTHOR = "Li, H. and Shen, C.Z. and Torr, P. and Tresp, V. and Gu, J.D.",
TITLE = "Self-Discovering Interpretable Diffusion Latent Directions for
Responsible Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12006-12016",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96280"}
@inproceedings{bb99519,
AUTHOR = "Li, H. and Zou, Y. and Wang, Y. and Majumder, O. and Xie, Y.S. and Manmatha, R. and Swaminathan, A. and Tu, Z.W. and Ermon, S. and Soatto, S.",
TITLE = "On the Scalability of Diffusion-based Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9400-9409",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96281"}
@inproceedings{bb99520,
AUTHOR = "Guo, X. and Liu, J.L. and Cui, M.M. and Li, J. and Yang, H.Y. and Huang, D.",
TITLE = "Initno: Boosting Text-to-Image Diffusion Models via Initial Noise
Optimization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9380-9389",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96282"}
@inproceedings{bb99521,
AUTHOR = "Shen, D. and Song, G.L. and Xue, Z. and Wang, F.Y. and Liu, Y.",
TITLE = "Rethinking the Spatial Inconsistency in Classifier-Free Diffusion
Guidance",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9370-9379",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96283"}
@inproceedings{bb99522,
AUTHOR = "Zhou, Y.F. and Zhang, R. and Gu, J.X. and Sun, T.",
TITLE = "Customization Assistant for Text-to-image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9182-9191",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96284"}
@inproceedings{bb99523,
AUTHOR = "Patel, M. and Kim, C. and Cheng, S. and Baral, C. and Yang, Y.Z.",
TITLE = "ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image
Generations",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9069-9078",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96285"}
@inproceedings{bb99524,
AUTHOR = "Meral, T.H.S. and Simsar, E. and Tombari, F. and Yanardag, P.",
TITLE = "CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image
Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9005-9014",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96286"}
@inproceedings{bb99525,
AUTHOR = "Jiang, Z.Z. and Mao, C.J. and Pan, Y.L. and Han, Z. and Zhang, J.F.",
TITLE = "SCEdit: Efficient and Controllable Image Diffusion Generation via
Skip Connection Editing",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8995-9004",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96287"}
@inproceedings{bb99526,
AUTHOR = "Kim, C. and Min, K. and Patel, M. and Cheng, S. and Yang, Y.Z.",
TITLE = "WOUAF: Weight Modulation for User Attribution and Fingerprinting in
Text-to-Image Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8974-8983",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96288"}
@inproceedings{bb99527,
AUTHOR = "Shirakawa, T. and Uchida, S.",
TITLE = "NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on
Noise Cropping and Merging",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8921-8930",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96289"}
@inproceedings{bb99528,
AUTHOR = "Kwon, G. and Jenni, S. and Li, D.Z. and Lee, J.Y. and Ye, J.C. and Heilbron, F.C.",
TITLE = "Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8880-8889",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96290"}
@inproceedings{bb99529,
AUTHOR = "Sueyoshi, K. and Matsubara, T.",
TITLE = "Predicated Diffusion: Predicate Logic-Based Attention Guidance for
Text-to-Image Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8651-8660",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96291"}
@inproceedings{bb99530,
AUTHOR = "Wang, Z. and Sha, Z.Z. and Ding, Z. and Wang, Y.L. and Tu, Z.W.",
TITLE = "TokenCompose: Text-to-Image Diffusion with Token-Level Supervision",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8553-8564",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96292"}
@inproceedings{bb99531,
AUTHOR = "Kim, J. and Park, J. and Rhee, W.",
TITLE = "Selectively Informative Description can Reduce Undesired Embedding
Entanglements in Text-to-Image Personalization",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8312-8322",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96293"}
@inproceedings{bb99532,
AUTHOR = "Koley, S. and Bhunia, A.K. and Sain, A. and Chowdhury, P.N. and Xiang, T. and Song, Y.Z.",
TITLE = "Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16826-16837",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96294"}
@inproceedings{bb99533,
AUTHOR = "Zhao, L. and Zhao, T.C. and Lin, Z. and Ning, X.F. and Dai, G.H. and Yang, H.Z. and Wang, Y.",
TITLE = "FlashEval: Towards Fast and Accurate Evaluation of Text-to-Image
Diffusion Generative Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "16122-16131",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96295"}
@inproceedings{bb99534,
AUTHOR = "Liu, H. and Sun, Z.C. and Mu, Y.D.",
TITLE = "Countering Personalized Text-to-Image Generation with Influence
Watermarks",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12257-12267",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96296"}
@inproceedings{bb99535,
AUTHOR = "Azarian, K. and Das, D. and Hou, Q.Q. and Porikli, F.M.",
TITLE = "Segmentation-Free Guidance for Text-to-Image Diffusion Models",
BOOKTITLE = GCV24,
YEAR = "2024",
PAGES = "7520-7529",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96297"}
@inproceedings{bb99536,
AUTHOR = "Li, C. and Qi, Y. and Zeng, Q. and Lu, L.",
TITLE = "Comparison of Image Generation methods based on Diffusion Models",
BOOKTITLE = CVIDL23,
YEAR = "2023",
PAGES = "1-4",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96298"}
@inproceedings{bb99537,
AUTHOR = "Xu, Y. and Zhao, Y. and Xiao, Z.S. and Hou, T.B.",
TITLE = "UFOGen: You Forward Once Large Scale Text-to-Image Generation via
Diffusion GANs",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8196-8206",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96299"}
@inproceedings{bb99538,
AUTHOR = "Huang, R.H. and Han, J.H. and Lu, G.S. and Liang, X.D. and Zeng, Y. and Zhang, W. and Xu, H.",
TITLE = "DiffDis: Empowering Generative Diffusion Model with Cross-Modal
Discrimination Capability",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15667-15677",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96300"}
@inproceedings{bb99539,
AUTHOR = "Yang, X.Y. and Wang, X.C.",
TITLE = "Diffusion Model as Representation Learner",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "18892-18903",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96301"}
@inproceedings{bb99540,
AUTHOR = "Nair, N.G. and Cherian, A. and Lohit, S. and Wang, Y. and Koike Akino, T. and Patel, V.M. and Marks, T.K.",
TITLE = "Steered Diffusion: A Generalized Framework for Plug-and-Play
Conditional Image Synthesis",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "20793-20803",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96302"}
@inproceedings{bb99541,
AUTHOR = "Wang, Z.D. and Bao, J.M. and Zhou, W.G. and Wang, W. and Hu, H. and Chen, H. and Li, H.Q.",
TITLE = "DIRE for Diffusion-Generated Image Detection",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22388-22398",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96303"}
@inproceedings{bb99542,
AUTHOR = "Hong, S. and Lee, G. and Jang, W. and Kim, S.",
TITLE = "Improving Sample Quality of Diffusion Models Using Self-Attention
Guidance",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7428-7437",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96304"}
@inproceedings{bb99543,
AUTHOR = "Feng, B.T. and Smith, J. and Rubinstein, M. and Chang, H. and Bouman, K.L. and Freeman, W.T.",
TITLE = "Score-Based Diffusion Models as Principled Priors for Inverse Imaging",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "10486-10497",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96305"}
@inproceedings{bb99544,
AUTHOR = "Yang, B.B. and Luo, Y. and Chen, Z.L. and Wang, G.R. and Liang, X.D. and Lin, L.",
TITLE = "LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22612-22622",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96306"}
@inproceedings{bb99545,
AUTHOR = "Levi, E. and Brosh, E. and Mykhailych, M. and Perez, M.",
TITLE = "DLT: Conditioned layout generation with Joint Discrete-Continuous
Diffusion Layout Transformer",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2106-2115",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96307"}
@inproceedings{bb99546,
AUTHOR = "Couairon, G. and Careil, M. and Cord, M. and Lathuiliere, S. and Verbeek, J.",
TITLE = "Zero-shot spatial layout conditioning for text-to-image diffusion
models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2174-2183",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96308"}
@inproceedings{bb99547,
AUTHOR = "Zhang, L. and Rao, A. and Agrawala, M.",
TITLE = "Adding Conditional Control to Text-to-Image Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3813-3824",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96309"}
@inproceedings{bb99548,
AUTHOR = "Zhao, W.L. and Rao, Y.M. and Liu, Z. and Liu, B. and Zhou, J. and Lu, J.W.",
TITLE = "Unleashing Text-to-Image Diffusion Models for Visual Perception",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5706-5716",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96310"}
@inproceedings{bb99549,
AUTHOR = "Wu, Q.C. and Liu, Y.J. and Zhao, H. and Bui, T. and Lin, Z. and Zhang, Y. and Chang, S.Y.",
TITLE = "Harnessing the Spatial-Temporal Attention of Diffusion Models for
High-Fidelity Text-to-Image Synthesis",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7732-7742",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96311"}
@inproceedings{bb99550,
AUTHOR = "Khachatryan, L. and Movsisyan, A. and Tadevosyan, V. and Henschel, R. and Wang, Z.Y. and Navasardyan, S. and Shi, H.",
TITLE = "Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video
Generators",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15908-15918",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96312"}
@inproceedings{bb99551,
AUTHOR = "Zhao, J. and Zheng, H. and Wang, C. and Lan, L. and Yang, W.J.",
TITLE = "MagicFusion: Boosting Text-to-Image Generation Performance by Fusing
Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22535-22545",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96313"}
@inproceedings{bb99552,
AUTHOR = "Kumari, N. and Zhang, B.L. and Wang, S.Y. and Shechtman, E. and Zhang, R. and Zhu, J.Y.",
TITLE = "Ablating Concepts in Text-to-Image Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22634-22645",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96314"}
@inproceedings{bb99553,
AUTHOR = "Schwartz, I. and Snæbjarnarson, V. and Chefer, H. and Belongie, S. and Wolf, L. and Benaim, S.",
TITLE = "Discriminative Class Tokens for Text-to-Image Diffusion Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22668-22678",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96315"}
@inproceedings{bb99554,
AUTHOR = "Patashnik, O. and Garibi, D. and Azuri, I. and Averbuch Elor, H. and Cohen Or, D.",
TITLE = "Localizing Object-level Shape Variations with Text-to-Image Diffusion
Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "22994-23004",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96316"}
@inproceedings{bb99555,
AUTHOR = "Schramowski, P. and Brack, M. and Deiseroth, B. and Kersting, K.",
TITLE = "Safe Latent Diffusion: Mitigating Inappropriate Degeneration in
Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22522-22531",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96317"}
@inproceedings{bb99556,
AUTHOR = "Chen, C. and Liu, D. and Ma, S.Q. and Nepal, S. and Xu, C.",
TITLE = "Private Image Generation with Dual-Purpose Auxiliary Classifier",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "20361-20370",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96318"}
@inproceedings{bb99557,
AUTHOR = "Ni, H. and Shi, C. and Li, K. and Huang, S.X. and Min, M.R.",
TITLE = "Conditional Image-to-Video Generation with Latent Flow Diffusion
Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18444-18455",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96319"}
@inproceedings{bb99558,
AUTHOR = "Zhang, Q.S. and Song, J. and Huang, X. and Chen, Y.X. and Liu, M.Y.",
TITLE = "DiffCollage: Parallel Generation of Large Content with Diffusion
Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10188-10198",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96320"}
@inproceedings{bb99559,
AUTHOR = "Phung, H. and Dao, Q. and Tran, A.",
TITLE = "Wavelet Diffusion Models are fast and scalable Image Generators",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10199-10208",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96321"}
@inproceedings{bb99560,
AUTHOR = "Kim, S.W. and Brown, B. and Yin, K.X. and Kreis, K. and Schwarz, K. and Li, D. and Rombach, R. and Torralba, A. and Fidler, S.",
TITLE = "NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion
Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "8496-8506",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96322"}
@inproceedings{bb99561,
AUTHOR = "Luo, Z.X. and Chen, D. and Zhang, Y.Y. and Huang, Y. and Wang, L. and Shen, Y.J. and Zhao, D.L. and Zhou, J. and Tan, T.N.",
TITLE = "VideoFusion: Decomposed Diffusion Models for High-Quality Video
Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10209-10218",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96323"}
@inproceedings{bb99562,
AUTHOR = "Ruan, L. and Ma, Y.Y. and Yang, H. and He, H.G. and Liu, B. and Fu, J.L. and Yuan, N.J. and Jin, Q. and Guo, B.",
TITLE = "MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio
and Video Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10219-10228",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96324"}
@inproceedings{bb99563,
AUTHOR = "Zhu, Y.Z. and Li, Z.H. and Wang, T.W. and He, M.C. and Yao, C.",
TITLE = "Conditional Text Image Generation with Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "14235-14244",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96325"}
@inproceedings{bb99564,
AUTHOR = "Zhou, Y.F. and Liu, B.C. and Zhu, Y.Z. and Yang, X. and Chen, C.Y. and Xu, J.H.",
TITLE = "Shifted Diffusion for Text-to-image Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "10157-10166",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96326"}
@inproceedings{bb99565,
AUTHOR = "Li, M.H. and Duan, Y.Q. and Zhou, J. and Lu, J.W.",
TITLE = "Diffusion-SDF: Text-to-Shape via Voxelized Diffusion",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "12642-12651",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96327"}
@inproceedings{bb99566,
AUTHOR = "Chai, S. and Zhuang, L.S. and Yan, F.Y.",
TITLE = "LayoutDM: Transformer-based Diffusion Model for Layout Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "18349-18358",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96328"}
@inproceedings{bb99567,
AUTHOR = "Wu, Q.C. and Liu, Y.J. and Zhao, H. and Kale, A. and Bui, T. and Yu, T. and Lin, Z. and Zhang, Y. and Chang, S.Y.",
TITLE = "Uncovering the Disentanglement Capability in Text-to-Image Diffusion
Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1900-1910",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96329"}
@inproceedings{bb99568,
AUTHOR = "Jain, A. and Xie, A. and Abbeel, P.",
TITLE = "VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1911-1920",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96330"}
@inproceedings{bb99569,
AUTHOR = "Kumari, N. and Zhang, B.L. and Zhang, R. and Shechtman, E. and Zhu, J.Y.",
TITLE = "Multi-Concept Customization of Text-to-Image Diffusion",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1931-1941",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96331"}
@inproceedings{bb99570,
AUTHOR = "Hui, M. and Zhang, Z.Z. and Zhang, X.Y. and Xie, W.X. and Wang, Y.W. and Lu, Y.",
TITLE = "Unifying Layout Generation with a Decoupled Diffusion Model",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "1942-1951",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96332"}
@inproceedings{bb99571,
AUTHOR = "Ruiz, N. and Li, Y.Z. and Jampani, V. and Pritch, Y. and Rubinstein, M. and Aberman, K.",
TITLE = "DreamBooth: Fine Tuning Text-to-Image Diffusion Models for
Subject-Driven Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22500-22510",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96333"}
@inproceedings{bb99572,
AUTHOR = "Zheng, G.C. and Zhou, X.P. and Li, X.W. and Qi, Z.A. and Shan, Y. and Li, X.",
TITLE = "LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image
Generation",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "22490-22499",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96334"}
@inproceedings{bb99573,
AUTHOR = "Liu, X.H. and Park, D.H. and Azadi, S. and Zhang, G. and Chopikyan, A. and Hu, Y.X. and Shi, H. and Rohrbach, A. and Darrell, T.J.",
TITLE = "More Control for Free! Image Synthesis with Semantic Diffusion
Guidance",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "289-299",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96335"}
@inproceedings{bb99574,
AUTHOR = "Pan, Z.H. and Zhou, X. and Tian, H.",
TITLE = "Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image
Generation",
BOOKTITLE = WACV23,
YEAR = "2023",
PAGES = "4450-4460",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96336"}
@inproceedings{bb99575,
AUTHOR = "Gu, S.Y. and Chen, D. and Bao, J.M. and Wen, F. and Zhang, B. and Chen, D.D. and Yuan, L. and Guo, B.N.",
TITLE = "Vector Quantized Diffusion Model for Text-to-Image Synthesis",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "10686-10696",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96337"}
@inproceedings{bb99576,
AUTHOR = "Jing, B. and Corso, G. and Berlinghieri, R. and Jaakkola, T.",
TITLE = "Subspace Diffusion Generative Models",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXIII:274-289",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96338"}
@inproceedings{bb99577,
AUTHOR = "Han, L.G. and Li, Y.X. and Zhang, H. and Milanfar, P. and Metaxas, D.N. and Yang, F.",
TITLE = "SVDiff: Compact Parameter Space for Diffusion Fine-Tuning",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7289-7300",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96339"}
@inproceedings{bb99578,
AUTHOR = "Nair, N.G. and Bandara, W.G.C. and Patel, V.M.",
TITLE = "Unite and Conquer: Plug and Play Multi-Modal Synthesis Using
Diffusion Models",
BOOKTITLE = CVPR23,
YEAR = "2023",
PAGES = "6070-6079",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96340"}
@inproceedings{bb99579,
AUTHOR = "Benny, Y. and Wolf, L.B.",
TITLE = "Dynamic Dual-Output Diffusion Models",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "11472-11481",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96341"}
@inproceedings{bb99580,
AUTHOR = "Hu, M.H. and Wang, Y.J. and Cham, T.J. and Yang, J.F. and Suganthan, P.N.",
TITLE = "Global Context with Discrete Diffusion in Vector Quantised Modelling
for Image Generation",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "11492-11501",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96342"}
@inproceedings{bb99581,
AUTHOR = "Zheng, G. and Li, S. and Wang, H. and Yao, T.P. and Chen, Y. and Ding, S.H. and Li, X.",
TITLE = "Entropy-Driven Sampling and Training Scheme for Conditional Diffusion
Generation",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XXII:754-769",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96343"}
@inproceedings{bb99582,
AUTHOR = "Liu, N. and Li, S. and Du, Y.L. and Torralba, A. and Tenenbaum, J.B.",
TITLE = "Compositional Visual Generation with Composable Diffusion Models",
BOOKTITLE = ECCV22,
YEAR = "2022",
PAGES = "XVII:423-439",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96344"}
@inproceedings{bb99583,
AUTHOR = "Sehwag, V. and Hazirbas, C. and Gordo, A. and Ozgenel, F. and Ferrer, C.C.",
TITLE = "Generating High Fidelity Data from Low-density Regions using
Diffusion Models",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "11482-11491",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489dift2i4.html#TT96345"}
@article{bb99584,
AUTHOR = "Naveen, S. and Ram Kiran, M.S. and Indupriya, M. and Manikanta, T.V. and Sudeep, P.V.",
TITLE = "Transformer models for enhancing AttnGAN based text to image
generation",
JOURNAL = IVC,
VOLUME = "115",
YEAR = "2021",
PAGES = "104284",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96346"}
@article{bb99585,
AUTHOR = "Dalmaz, O. and Yurt, M. and Cukur, T.",
TITLE = "ResViT: Residual Vision Transformers for Multimodal Medical Image
Synthesis",
JOURNAL = MedImg,
VOLUME = "41",
YEAR = "2022",
NUMBER = "10",
MONTH = "October",
PAGES = "2598-2614",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96347"}
@article{bb99586,
AUTHOR = "Zhang, X. and Jiao, W.T. and Wang, B. and Tian, X.D.",
TITLE = "CT-GAN: A conditional Generative Adversarial Network of transformer
architecture for text-to-image",
JOURNAL = SP:IC,
VOLUME = "115",
YEAR = "2023",
PAGES = "116959",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96348"}
@article{bb99587,
AUTHOR = "Sortino, R. and Palazzo, S. and Rundo, F. and Spampinato, C.",
TITLE = "Transformer-based image generation from scene graphs",
JOURNAL = CVIU,
VOLUME = "233",
YEAR = "2023",
PAGES = "103721",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96349"}
@inproceedings{bb99588,
AUTHOR = "Sortino, R. and Palazzo, S. and Spampinato, C.",
TITLE = "Transforming Image Generation from Scene Graphs",
BOOKTITLE = "ICPR22",
YEAR = "2022",
PAGES = "4118-4124",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96350"}
@inproceedings{bb99589,
AUTHOR = "Wang, Z.C. and Ren, Q. and Wang, J.L. and Yan, C.G. and Jiang, C.J.",
TITLE = "Mush: Multi-scale Hierarchical Feature Extraction for Semantic Image
Synthesis",
BOOKTITLE = ACCV22,
YEAR = "2022",
PAGES = "VII:185-201",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96351"}
@article{bb99590,
AUTHOR = "Wei, Z.P. and Chen, J.J. and Goldblum, M. and Wu, Z.X. and Goldstein, T. and Jiang, Y.G. and Davis, L.S.",
TITLE = "Towards Transferable Adversarial Attacks on Image and Video
Transformers",
JOURNAL = IP,
VOLUME = "32",
YEAR = "2023",
PAGES = "6346-6358",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96352"}
@article{bb99591,
AUTHOR = "Wei, Z.P. and Chen, J.J. and Wu, Z.X. and Jiang, Y.G.",
TITLE = "Adaptive Cross-Modal Transferable Adversarial Attacks From Images to
Videos",
JOURNAL = PAMI,
VOLUME = "46",
YEAR = "2024",
NUMBER = "5",
MONTH = "May",
PAGES = "3772-3783",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96353"}
@inproceedings{bb99592,
AUTHOR = "Wei, Z.P. and Chen, J.J. and Wu, Z.X. and Jiang, Y.G.",
TITLE = "Cross-Modal Transferable Adversarial Attacks from Images to Videos",
BOOKTITLE = CVPR22,
YEAR = "2022",
PAGES = "15044-15053",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96354"}
@article{bb99593,
AUTHOR = "Bahani, M. and El Ouaazizi, A. and Maalmi, K.",
TITLE = "The effectiveness of T5, GPT-2, and BERT on text-to-image generation
task",
JOURNAL = PRL,
VOLUME = "173",
YEAR = "2023",
PAGES = "57-63",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96355"}
@article{bb99594,
AUTHOR = "Su, S. and Zhu, J.C. and Gao, L.L. and Song, J.K.",
TITLE = "Utilizing Greedy Nature for Multimodal Conditional Image Synthesis in
Transformers",
JOURNAL = MultMed,
VOLUME = "26",
YEAR = "2024",
PAGES = "2354-2366",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96356"}
@article{bb99595,
AUTHOR = "Li, Z. and Liu, F.",
TITLE = "Scalable video transformer for full-frame video prediction",
JOURNAL = CVIU,
VOLUME = "249",
YEAR = "2024",
PAGES = "104166",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96357"}
@article{bb99596,
AUTHOR = "Cao, B. and Qi, G.L. and Zhao, J. and Zhu, P.F. and Hu, Q.H. and Gao, X.B.",
TITLE = "RTF: Recursive TransFusion for Multi-Modal Image Synthesis",
JOURNAL = IP,
VOLUME = "34",
YEAR = "2025",
PAGES = "1573-1587",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96358"}
@inproceedings{bb99597,
AUTHOR = "Choudhury, Z.Z. and McCane, B. and Coffey, S.",
TITLE = "Medical Image Synthesis Using Autoencoder with Vision Transformer",
BOOKTITLE = IVCNZ24,
YEAR = "2024",
PAGES = "1-6",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96359"}
@inproceedings{bb99598,
AUTHOR = "Tschannen, M. and Eastwood, C. and Mentzer, F.",
TITLE = "GIVT: Generative Infinite-vocabulary Transformers",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LVII: 292-309",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96360"}
@inproceedings{bb99599,
AUTHOR = "Ni, Z. and Wang, Y.L. and Zhou, R.P. and Lu, R. and Guo, J.Y. and Hu, J.Y. and Liu, Z.Y. and Yao, Y. and Huang, G.",
TITLE = "Adanat: Exploring Adaptive Policy for Token-based Image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XVI: 302-319",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489synvit5.html#TT96361"}
Last update:Jun 18, 2025 at 15:22:01