@inproceedings{bb103800,
AUTHOR = "Cheng, H. and Xiao, E. and Yang, J.Y. and Cao, J.H. and Zhang, Q. and Zhang, J. and Xu, K.D. and Gu, J.D. and Xu, R.",
TITLE = "Not Just Text: Uncovering Vision Modality Typographic Threats in
Image Generation Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2997-3007",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100513"}
@inproceedings{bb103801,
AUTHOR = "Zhang, J.J. and Huang, Q.Y. and Liu, J.J. and Guo, X. and Huang, D.",
TITLE = "Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent
Diffusion Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23464-23473",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100514"}
@inproceedings{bb103802,
AUTHOR = "Kong, L.J. and Wu, K. and Xu, C.M. and Hu, X.B. and Han, W.H. and Peng, J.L. and Luo, D.H. and Li, M.T. and Zhang, J.N. and Wang, C.J. and Fu, Y.W.",
TITLE = "CustAny: Customizing Anything from A Single Example",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "20916-20925",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100515"}
@inproceedings{bb103803,
AUTHOR = "Na, S. and Kim, Y. and Lee, H.",
TITLE = "Boost Your Human Image Generation Model via Direct Preference
Optimization",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23551-23562",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100516"}
@inproceedings{bb103804,
AUTHOR = "Wang, X.D. and Zhou, X.Y. and Fathi, A. and Darrell, T.J. and Schmid, C.",
TITLE = "Visual Lexicon: Rich Image Features in Language Space",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "19736-19747",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100517"}
@inproceedings{bb103805,
AUTHOR = "Zhu, J.P. and Yang, C. and Zheng, K. and Xu, Y.H. and Shi, Z. and Zhang, Y.F. and Chen, Q.F. and Shen, Y.J.",
TITLE = "Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18411-18423",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100518"}
@inproceedings{bb103806,
AUTHOR = "Yun, T. and Zhang, D. and Park, J. and Pan, L.",
TITLE = "Learning to Sample Effective and Diverse Prompts for Text-to-Image
Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23625-23635",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100519"}
@inproceedings{bb103807,
AUTHOR = "Um, S. and Ye, J.C.",
TITLE = "Minority-Focused Text-to-Image Generation via Prompt Optimization",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "20926-20936",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100520"}
@inproceedings{bb103808,
AUTHOR = "Han, W. and Lee, Y. and Kim, C. and Park, K. and Hwang, S.J.",
TITLE = "Spatial Transport Optimization by Repositioning Attention Map for
Training-Free Text-to-Image Synthesis",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18401-18410",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100521"}
@inproceedings{bb103809,
AUTHOR = "Xing, X.Y. and Saha, A. and He, J.F. and Hao, S. and Vicol, P. and Ryu, M. and Li, G. and Singla, S. and Young, S. and Li, Y.X. and Yang, F. and Ramachandran, D.",
TITLE = "Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18486-18496",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100522"}
@inproceedings{bb103810,
AUTHOR = "Liang, D. and Jia, J.Y. and Liu, Y.H. and Ke, Z.H. and Fu, H.B. and Lau, R.W.H.",
TITLE = "VODiff: Controlling Object Visibility Order in Text-to-Image
Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "18379-18389",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100523"}
@inproceedings{bb103811,
AUTHOR = "Jo, K. and Yun, J. and Choo, J.",
TITLE = "Devil is in the Detail: Towards Injecting Fine Details of Image
Prompt in Image Generation via Conflict-free Guidance and Stratified
Attention",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23595-23603",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100524"}
@inproceedings{bb103812,
AUTHOR = "Zhang, Z.C. and Kou, T.C. and Wang, S. and Li, C.Y. and Sun, W. and Wang, W. and Li, X.Y. and Wang, Z.Y. and Cao, X.Z. and Min, X.K. and Liu, X.H. and Zhai, G.T.",
TITLE = "Q-Eval-100K: Evaluating Visual Quality and Alignment Level for
Text-to-Vision Content",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "10621-10631",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100525"}
@inproceedings{bb103813,
AUTHOR = "Jung, S. and Oesterling, A. and Verdun, C.M. and Vithana, S. and Moon, T. and Calmon, F.P.",
TITLE = "Multi-Group Proportional Representation for Text-to-Image Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23744-23754",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100526"}
@inproceedings{bb103814,
AUTHOR = "Xiao, S.T. and Wang, Y.Z. and Zhou, J.J. and Yuan, H. and Xing, X. and Yan, R. and Li, C.F. and Wang, S.T. and Huang, T.J. and Liu, Z.",
TITLE = "OmniGen: Unified Image Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13294-13304",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100527"}
@inproceedings{bb103815,
AUTHOR = "Chen, J. and Hu, D.T. and Huang, X.J. and Coskun, H. and Sahni, A. and Gupta, A. and Goyal, A. and Lahiri, D. and Singh, R. and Idelbayev, Y. and Cao, J.L. and Li, Y.Y. and Cheng, K.T. and Chan, S.H.G. and Gong, M.M. and Tulyakov, S. and Kag, A. and Xu, Y. and Ren, J.",
TITLE = "SnapGen: Taming High-Resolution Text-To-Image Models for Mobile
Devices with Efficient Architectures and Training",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "7997-8008",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100528"}
@inproceedings{bb103816,
AUTHOR = "Franchi, G. and Belkhir, N. and Trong, D.N. and Xia, G.X. and Pilzer, A.",
TITLE = "Towards Understanding and Quantifying Uncertainty for Text-to-Image
Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "8062-8072",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100529"}
@inproceedings{bb103817,
AUTHOR = "Jia, C.Y. and Xia, C.L. and Dang, Z.H. and Wu, W.J. and Qian, H.W. and Luo, M.",
TITLE = "ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13284-13293",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100530"}
@inproceedings{bb103818,
AUTHOR = "Baumann, S.A. and Krause, F. and Neumayr, M. and Stracke, N. and Sevi, M. and Hu, V.T. and Ommer, B.",
TITLE = "Continuous, Subject-Specific Attribute Control in T2I Models by
Identifying Semantic Directions",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13231-13241",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100531"}
@inproceedings{bb103819,
AUTHOR = "Binyamin, L. and Tewel, Y. and Segev, H. and Hirsch, E. and Rassin, R. and Chechik, G.",
TITLE = "Make It Count: Text-to-Image Generation with an Accurate Number of
Objects",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13242-13251",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100532"}
@inproceedings{bb103820,
AUTHOR = "Li, F.F. and Zhang, M. and Sun, Y.M. and Yang, M.",
TITLE = "Detect-and-Guide: Self-regulation of Diffusion Models for Safe
Text-to-Image Generation via Guideline Token Optimization",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "13252-13262",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100533"}
@inproceedings{bb103821,
AUTHOR = "Wang, Z. and Wei, Y.X. and Li, F. and Pei, R. and Xu, H. and Zuo, W.M.",
TITLE = "ACE: Anti-Editing Concept Erasure in Text-to-Image Models",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "23505-23515",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100534"}
@inproceedings{bb103822,
AUTHOR = "Azam, B. and Akhtar, N.",
TITLE = "Plug-and-Play Interpretable Responsible Text-to-Image Generation via
Dual-Space Multi-facet Concept Control",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2976-2985",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100535"}
@inproceedings{bb103823,
AUTHOR = "Zhao, R. and Mao, W.J. and Shou, M.Z.",
TITLE = "DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in
Multimodal Cycles",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "2835-2846",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100536"}
@inproceedings{bb103824,
AUTHOR = "Zhou, P.F. and Peng, X.P. and Song, J.J. and Li, C. and Xu, Z. and Yang, Y. and Guo, Z. and Zhang, H. and Lin, Y.Q. and He, Y.F. and Zhao, L. and Liu, S. and Li, T.H. and Xie, Y.X. and Chang, X.J. and Qiao, Y. and Shao, W.Q. and Zhang, K.",
TITLE = "OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved
Image-Text Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "56-66",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100537"}
@inproceedings{bb103825,
AUTHOR = "Qiu, Y.N. and Wang, A.D. and Li, C. and Huang, H.N. and Zhou, G.X. and Zhao, Q.",
TITLE = "STEPS: Sequential Probability Tensor Estimation for Text-to-Image
Hard Prompt Search",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28640-28650",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100538"}
@inproceedings{bb103826,
AUTHOR = "Poesina, E. and Costache, A.V. and Chifu, A.G. and Mothe, J. and Ionescu, R.T.",
TITLE = "PQPP: A Joint Benchmark for Text-to-Image Prompt and Query
Performance Prediction",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28651-28661",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100539"}
@inproceedings{bb103827,
AUTHOR = "Wang, A.Z. and Ge, S.W. and Karras, T. and Liu, M.Y. and Balaji, Y.",
TITLE = "A Comprehensive Study of Decoder-Only LLMs for Text-to-Image
Generation",
BOOKTITLE = CVPR25,
YEAR = "2025",
PAGES = "28575-28585",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100540"}
@inproceedings{bb103828,
AUTHOR = "Lakhanpal, S. and Chopra, S. and Jain, V. and Chadha, A. and Luo, M.",
TITLE = "Refining Text-to-Image Generation: Towards Accurate Training-Free
Glyph-Enhanced Image Generation",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4372-4381",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100541"}
@inproceedings{bb103829,
AUTHOR = "Agarwal, A. and Karanam, S. and Srinivasan, B.V.",
TITLE = "AlignIT: Enhancing Prompt Alignment in Customization of Text-to-Image
Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4882-4890",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100542"}
@inproceedings{bb103830,
AUTHOR = "Agarwal, A. and Karanam, S. and Shukla, T. and Srinivasan, B.V.",
TITLE = "An Image is Worth Multiple Words: Multi-Attribute Inversion for
Constrained Text-To-Image Synthesis",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "6053-6062",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100543"}
@inproceedings{bb103831,
AUTHOR = "Corneanu, C.A. and Feng, Q.L. and Martinez, A.M.",
TITLE = "Structured Human Assessment of Text-to-Image Generative Models",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "4481-4490",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100544"}
@inproceedings{bb103832,
AUTHOR = "Choi, H. and Kasahara, I. and Engin, S. and Graule, M.A. and Chavan Dafle, N. and Isler, V.",
TITLE = "FineControlNet: Fine-level Text Control for Image Generation with
Spatially Aligned Text Control Injection",
BOOKTITLE = WACV25,
YEAR = "2025",
PAGES = "3975-3984",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100545"}
@inproceedings{bb103833,
AUTHOR = "Ban, Y.H. and Wang, R.C. and Zhou, T.Y. and Cheng, M. and Gong, B.Q. and Hsieh, C.J.",
TITLE = "Understanding the Impact of Negative Prompts: When and How Do They Take
Effect?",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXIX: 190-206",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100546"}
@inproceedings{bb103834,
AUTHOR = "Stracke, N. and Baumann, S.A. and Susskind, J. and Bautista, M.A. and Ommer, B.",
TITLE = "CTRLorALTer: Conditional LorALTer for Efficient 0-shot Control and
Altering of T2I Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVIII: 87-103",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100547"}
@inproceedings{bb103835,
AUTHOR = "Hemmat, R.A. and Hall, M. and Sun, A. and Ross, C. and Drozdzal, M. and Romero Soriano, A.",
TITLE = "Improving Geo-diversity of Generated Images with Contextualized Vendi
Score Guidance",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVII: 213-229",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100548"}
@inproceedings{bb103836,
AUTHOR = "Li, P.Z. and Nie, Q. and Chen, Y. and Jiang, X. and Wu, K. and Lin, Y. and Liu, Y. and Peng, J.L. and Wang, C.J. and Zheng, F.",
TITLE = "Tuning-Free Image Customization with Image and Text Guidance",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXVI: 233-250",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100549"}
@inproceedings{bb103837,
AUTHOR = "Xue, X.T. and Wu, J.S. and Kong, Y.Y. and Senhadji, L. and Shu, H.Z.",
TITLE = "ST-LDM: A Universal Framework for Text-grounded Object Generation in
Real Images",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XLVI: 145-162",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100550"}
@inproceedings{bb103838,
AUTHOR = "Wu, Z.F. and Huang, L.H. and Wang, W. and Wei, Y.H. and Liu, Y.",
TITLE = "MultiGen: Zero-Shot Image Generation from Multi-Modal Prompts",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "VIII: 297-313",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100551"}
@inproceedings{bb103839,
AUTHOR = "Sun, Q. and Zhou, H. and Zhou, W.G. and Li, L. and Li, H.Q.",
TITLE = "Forest2seq: Revitalizing Order Prior for Sequential Indoor Scene
Synthesis",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXV: 251-268",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100552"}
@inproceedings{bb103840,
AUTHOR = "Lee, S.H. and Li, Y.X. and Ke, J.J. and Yoo, I. and Zhang, H. and Yu, J.H. and Wang, Q.F. and Deng, F. and Entis, G. and He, J.F. and Li, G. and Kim, S. and Essa, I. and Yang, F.",
TITLE = "Parrot: Pareto-optimal Multi-reward Reinforcement Learning Framework
for Text-to-image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXVIII: 462-478",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100553"}
@inproceedings{bb103841,
AUTHOR = "Zheng, A.Y.J. and Yeh, R.A.",
TITLE = "IMMA: Immunizing Text-to-image Models Against Malicious Adaptation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXXIX: 458-475",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100554"}
@inproceedings{bb103842,
AUTHOR = "Chatterjee, A. and Ben Melech Stan, G. and Aflalo, E. and Paul, S. and Ghosh, D. and Gokhale, T. and Schmidt, L. and Hajishirzi, H. and Lal, V. and Baral, C. and Yang, Y.Z.",
TITLE = "Getting it Right: Improving Spatial Consistency in Text-to-image Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXII: 204-222",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100555"}
@inproceedings{bb103843,
AUTHOR = "Liu, R.T. and Khakzar, A. and Gu, J.D. and Chen, Q.F. and Torr, P.H.S. and Pizzati, F.",
TITLE = "Latent Guard: A Safety Framework for Text-to-image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXVI: 93-109",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100556"}
@inproceedings{bb103844,
AUTHOR = "Li, H.T. and Niu, H.J. and Zhao, F.",
TITLE = "Stable Preference: Redefining Training Paradigm of Human Preference
Model for Text-to-image Synthesis",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XXVIII: 250-266",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100557"}
@inproceedings{bb103845,
AUTHOR = "Dahary, O. and Patashnik, O. and Aberman, K. and Cohen Or, D.",
TITLE = "Be Yourself: Bounded Attention for Multi-subject Text-to-image
Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XIV: 432-448",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100558"}
@inproceedings{bb103846,
AUTHOR = "Xiong, P.X. and Kozuch, M. and Jain, N.",
TITLE = "Textual-visual Logic Challenge:
Understanding and Reasoning in Text-to-image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "V: 318-334",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100559"}
@inproceedings{bb103847,
AUTHOR = "Sun, Y. and Liu, Y.C. and Tang, Y.H. and Pei, W.J. and Chen, K.",
TITLE = "Anycontrol: Create Your Artwork with Versatile Control on Text-to-image
Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "XI: 92-109",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100560"}
@inproceedings{bb103848,
AUTHOR = "Lu, C.Y. and Agarwal, S. and Tanjim, M.M. and Mahadik, K. and Rao, A. and Mitra, S. and Saini, S.K. and Bagchi, S. and Chaterji, S.",
TITLE = "Recon: Training-free Acceleration for Text-to-image Synthesis with
Retrieval of Concept Prompt Trajectories",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LIX: 288-306",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100561"}
@inproceedings{bb103849,
AUTHOR = "Zhao, S.H. and Hao, S. and Zi, B. and Xu, H.Z. and Wong, K.Y.K.",
TITLE = "Bridging Different Language Models and Generative Vision Models for
Text-to-image Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXI: 70-86",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100562"}
@inproceedings{bb103850,
AUTHOR = "Tan, Z.Y. and Yang, M.P. and Qin, L. and Yang, H. and Qian, Y. and Zhou, Q. and Zhang, C. and Li, H.",
TITLE = "An Empirical Study and Analysis of Text-to-image Generation Using Large
Language Model-powered Textual Representation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXX: 472-489",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100563"}
@inproceedings{bb103851,
AUTHOR = "Chinchure, A. and Shukla, P. and Bhatt, G. and Salij, K. and Hosanagar, K. and Sigal, L. and Turk, M.",
TITLE = "Tibet: Identifying and Evaluating Biases in Text-to-image Generative
Models",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXIX: 429-446",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100564"}
@inproceedings{bb103852,
AUTHOR = "Mittal, S. and Sudan, A. and Vatsa, M. and Singh, R. and Glaser, T. and Hassner, T.",
TITLE = "Navigating Text-to-image Generative Bias Across Indic Languages",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVIII: 53-67",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100565"}
@inproceedings{bb103853,
AUTHOR = "Chang, Y.S. and Zhang, Y. and Fang, Z.Y. and Wu, Y.N. and Bisk, Y. and Gao, F.",
TITLE = "Skews in the Phenomenon Space Hinder Generalization in Text-to-image
Generation",
BOOKTITLE = ECCV24,
YEAR = "2024",
PAGES = "LXXXVII: 422-439",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100566"}
@inproceedings{bb103854,
AUTHOR = "Yang, Y.Q. and Moremada, C. and Deligiannis, N.",
TITLE = "On the Detection of Images Generated from Text",
BOOKTITLE = ICIP24,
YEAR = "2024",
PAGES = "3792-3798",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100567"}
@inproceedings{bb103855,
AUTHOR = "Liu, Z.X. and Schaldenbrand, P. and Okogwu, B.C. and Peng, W.X. and Peng, W.X. and Yun, Y. and Hundt, A. and Kim, J. and Oh, J.",
TITLE = "SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "10822-10832",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100568"}
@inproceedings{bb103856,
AUTHOR = "Zhang, Y.X. and Song, Y.R. and Liu, J.M. and Wang, R. and Yu, J.P. and Tang, H. and Li, H.X. and Tang, X. and Hu, Y. and Pan, H. and Jing, Z.L.",
TITLE = "SSR-Encoder: Encoding Selective Subject Representation for
Subject-Driven Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8069-8078",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100569"}
@inproceedings{bb103857,
AUTHOR = "Lee, J. and Lee, S. and Jo, C. and Im, W.B. and Seon, J. and Yoon, S.E.",
TITLE = "SemCity: Semantic Scene Generation with Triplane Diffusion",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "28337-28347",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100570"}
@inproceedings{bb103858,
AUTHOR = "Raistrick, A. and Mei, L.J. and Kayan, K. and Yan, D. and Zuo, Y.M. and Han, B. and Wen, H.Y. and Parakh, M. and Alexandropoulos, S. and Lipson, L. and Ma, Z. and Deng, J.",
TITLE = "Infinigen Indoors: Photorealistic Indoor Scenes using Procedural
Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "21783-21794",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100571"}
@inproceedings{bb103859,
AUTHOR = "Ji, P.L. and Liu, J.C.",
TITLE = "TlTScore: Towards Long-Tail Effects in Text-to-Visual Evaluation with
Generative Foundation Models",
BOOKTITLE = GenerativeFM24,
YEAR = "2024",
PAGES = "5302-5313",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100572"}
@inproceedings{bb103860,
AUTHOR = "Zhao, S.Y. and Zhao, L. and Kumar, B.G.V. and Suh, Y.M. and Metaxas, D.N. and Chandraker, M. and Schulter, S.",
TITLE = "Generating Enhanced Negatives for Training Language-Based Object
Detectors",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13592-13602",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100573"}
@inproceedings{bb103861,
AUTHOR = "Fan, L.J. and Chen, K. and Krishnan, D. and Katabi, D. and Isola, P. and Tian, Y.L.",
TITLE = "Scaling Laws of Synthetic Images for Model Training ... for Now",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7382-7392",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100574"}
@inproceedings{bb103862,
AUTHOR = "Qiao, P.C. and Shang, L. and Liu, C. and Sun, B. and Ji, X.Y. and Chen, J.",
TITLE = "FaceChain-SuDe: Building Derived Class to Inherit Category Attributes
for One-Shot Subject-Driven Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7215-7224",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100575"}
@inproceedings{bb103863,
AUTHOR = "Zhu, J.Y. and Guo, Q. and Juefei Xu, F. and Huang, Y.H. and Liu, Y. and Pu, G.",
TITLE = "Cosalpure: Learning Concept from Group Images for Robust Co-Saliency
Detection",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "3669-3678",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100576"}
@inproceedings{bb103864,
AUTHOR = "Chan, K.C.K. and Zhao, Y. and Jia, X.H. and Yang, M.H. and Wang, H.",
TITLE = "Improving Subject-Driven Image Synthesis with Subject-Agnostic
Guidance",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6733-6742",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100577"}
@inproceedings{bb103865,
AUTHOR = "Haji Ali, M. and Balakrishnan, G. and Ordonez, V.",
TITLE = "ElasticDiffusion: Training-Free Arbitrary Size Image Generation
Through Global-Local Content Separation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6603-6612",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100578"}
@inproceedings{bb103866,
AUTHOR = "Zhang, C. and Wu, Q.Y. and Gambardella, C.C. and Huang, X.S. and Phung, D. and Ouyang, W.L. and Cai, J.F.",
TITLE = "Taming Stable Diffusion for Text to 360° Panorama Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "6347-6357",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100579"}
@inproceedings{bb103867,
AUTHOR = "Hu, H.X. and Chan, K.C.K. and Su, Y.C. and Chen, W. and Li, Y.D. and Sohn, K. and Zhao, Y. and Ben, X. and Gong, B.Q. and Cohen, W. and Chang, M.W. and Jia, X.H.",
TITLE = "Instruct-Imagen: Image Generation with Multi-modal Instruction",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "4754-4763",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100580"}
@inproceedings{bb103868,
AUTHOR = "Kondapaneni, N. and Marks, M. and Knott, M. and Guimaraes, R. and Perona, P.",
TITLE = "Text-Image Alignment for Diffusion-Based Perception",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "13883-13893",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100581"}
@inproceedings{bb103869,
AUTHOR = "Qiao, R. and Yang, L. and Pang, K.Y. and Zhang, H.G.",
TITLE = "Making Visual Sense of Oracle Bones for You and Me",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12656-12665",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100582"}
@inproceedings{bb103870,
AUTHOR = "Shrestha, R. and Zou, Y. and Chen, Q.Y. and Li, Z.H. and Xie, Y.S. and Deng, S.Q.",
TITLE = "FairRAG: Fair Human Generation via Fair Retrieval Augmentation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "11996-12005",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100583"}
@inproceedings{bb103871,
AUTHOR = "Jayasumana, S. and Ramalingam, S. and Veit, A. and Glasner, D. and Chakrabarti, A. and Kumar, S.",
TITLE = "Rethinking FID: Towards a Better Evaluation Metric for Image
Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9307-9315",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100584"}
@inproceedings{bb103872,
AUTHOR = "Po, R. and Yang, G. and Aberman, K. and Wetzstein, G.",
TITLE = "Orthogonal Adaptation for Modular Customization of Diffusion Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7964-7973",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100585"}
@inproceedings{bb103873,
AUTHOR = "Bahmani, S. and Skorokhodov, I. and Rong, V. and Wetzstein, G. and Guibas, L.J. and Wonka, P. and Tulyakov, S. and Park, J.J. and Tagliasacchi, A. and Lindell, D.B.",
TITLE = "4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7996-8006",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100586"}
@inproceedings{bb103874,
AUTHOR = "Zhang, S. and Wang, B. and Wu, J.Q. and Li, Y. and Gao, T.T. and Zhang, D. and Wang, Z.Y.",
TITLE = "Learning Multi-Dimensional Human Preference for Text-to-Image
Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "8018-8027",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100587"}
@inproceedings{bb103875,
AUTHOR = "Huang, S. and Gong, B. and Feng, Y.T. and Chen, X. and Fu, Y.Q. and Liu, Y. and Wang, D.L.",
TITLE = "Learning Disentangled Identifiers for Action-Customized Text-to-Image
Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7797-7806",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100588"}
@inproceedings{bb103876,
AUTHOR = "Qu, L.G. and Wang, W.J. and Li, Y.Q. and Zhang, H.W. and Nie, L.Q. and Chua, T.S.",
TITLE = "Discriminative Probing and Tuning for Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "7434-7444",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100589"}
@inproceedings{bb103877,
AUTHOR = "Dao, T.T. and Vu, D.H. and Pham, C. and Tran, A.",
TITLE = "EFHQ: Multi-Purpose ExtremePose-Face-HQ Dataset",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "22605-22615",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100590"}
@inproceedings{bb103878,
AUTHOR = "Cazenavette, G. and Sud, A. and Leung, T. and Usman, B.",
TITLE = "FakeInversion: Learning to Detect Images from Unseen Text-to-Image
Models by Inverting Stable Diffusion",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "10759-10769",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100591"}
@inproceedings{bb103879,
AUTHOR = "Jayasumana, S. and Glasner, D. and Ramalingam, S. and Veit, A. and Chakrabarti, A. and Kumar, S.",
TITLE = "MarkovGen: Structured Prediction for Efficient Text-to-Image
Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "9316-9325",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100592"}
@inproceedings{bb103880,
AUTHOR = "Liang, Y. and He, J.F. and Li, G. and Li, P.Z. and Klimovskiy, A. and Carolan, N. and Sun, J. and Pont Tuset, J. and Young, S. and Yang, F. and Ke, J.J. and Dvijotham, K.D. and Collins, K.M. and Luo, Y.W. and Li, Y. and Kohlhoff, K.J. and Ramachandran, D. and Navalpakkam, V.",
TITLE = "Rich Human Feedback for Text-to-Image Generation",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "19401-19411",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100593"}
@inproceedings{bb103881,
AUTHOR = "Li, X. and Shen, Q.L. and Kawaguchi, K.",
TITLE = "VA3: Virtually Assured Amplification Attack on Probabilistic
Copyright Protection for Text-to-Image Generative Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12363-12373",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100594"}
@inproceedings{bb103882,
AUTHOR = "d'Inca, M. and Peruzzo, E. and Mancini, M. and Xu, D. and Goe, V. and Xu, X.Q. and Wang, Z.Y. and Shi, H. and Sebe, N.",
TITLE = "OpenBias: Open-Set Bias Detection in Text-to-Image Generative Models",
BOOKTITLE = CVPR24,
YEAR = "2024",
PAGES = "12225-12235",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100595"}
@inproceedings{bb103883,
AUTHOR = "Le Coz, A. and Ouertatani, H. and Herbin, S. and Adjed, F.",
TITLE = "Efficient Exploration of Image Classifier Failures with Bayesian
Optimization and Text-to-Image Models",
BOOKTITLE = GCV24,
YEAR = "2024",
PAGES = "7569-7578",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100596"}
@inproceedings{bb103884,
AUTHOR = "Wang, Y.L. and Xu, H.Y. and Zhang, X. and Chen, Z.Y. and Sha, Z.Z. and Wang, Z. and Tu, Z.W.",
TITLE = "OmniControlNet: Dual-stage Integration for Conditional Image
Generation",
BOOKTITLE = GCV24,
YEAR = "2024",
PAGES = "7436-7448",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100597"}
@inproceedings{bb103885,
AUTHOR = "Ganz, R. and Elad, M.",
TITLE = "CLIPAG: Towards Generator-Free Text-to-Image Generation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "3831-3841",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100598"}
@inproceedings{bb103886,
AUTHOR = "Park, S. and Moon, S.H. and Park, S.H. and Kim, J.",
TITLE = "Localization and Manipulation of Immoral Visual Cues for Safe
Text-to-Image Generation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4663-4672",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100599"}
@inproceedings{bb103887,
AUTHOR = "Jeanneret, G. and Simon, L. and Jurie, F.",
TITLE = "Text-to-Image Models for Counterfactual Explanations:
A Black-Box Approach",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "4745-4755",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100600"}
@inproceedings{bb103888,
AUTHOR = "Grimal, P. and Borgne, H.L. and Ferret, O. and Tourille, J.",
TITLE = "TIAM - A Metric for Evaluating Alignment in Text-to-Image Generation",
BOOKTITLE = WACV24,
YEAR = "2024",
PAGES = "2878-2887",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100601"}
@inproceedings{bb103889,
AUTHOR = "Qin, C. and Yu, N. and Xing, C. and Zhang, S. and Chen, Z.Y. and Ermon, S. and Fu, Y. and Xiong, C.M. and Xu, R.",
TITLE = "GlueGen: Plug and Play Multi-Modal Encoders for X-to-Image Generation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "23028-23039",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100602"}
@inproceedings{bb103890,
AUTHOR = "Lee, T. and Kang, J. and Kim, H. and Kim, T.",
TITLE = "Generating Realistic Images from In-the-wild Sounds",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7126-7136",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100603"}
@inproceedings{bb103891,
AUTHOR = "Ye Bin, M. and Kim, J. and Kim, H.Y. and Son, K. and Oh, T.H.",
TITLE = "TextManiA: Enriching Visual Feature by Text-driven Manifold Augmentation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2526-2537",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100604"}
@inproceedings{bb103892,
AUTHOR = "Wu, X.S. and Sun, K.Q. and Zhu, F. and Zhao, R. and Li, H.S.",
TITLE = "Human Preference Score: Better Aligning Text-to-image Models with
Human Preference",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2096-2105",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100605"}
@inproceedings{bb103893,
AUTHOR = "Agarwal, A. and Karanam, S. and Joseph, K.J. and Saxena, A. and Goswami, K. and Srinivasan, B.V.",
TITLE = "A-STAR: Test-time Attention Segregation and Retention for
Text-to-image Synthesis",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "2283-2293",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100606"}
@inproceedings{bb103894,
AUTHOR = "Cho, J. and Zala, A. and Bansal, M.",
TITLE = "DALL-EVAL: Probing the Reasoning Skills and Social Biases of
Text-to-Image Generation Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3020-3031",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100607"}
@inproceedings{bb103895,
AUTHOR = "Zhang, C. and Chen, X. and Chai, S.Q. and Wu, C.H. and Lagun, D. and Beeler, T. and de la Torre, F.",
TITLE = "ITI-Gen: Inclusive Text-to-Image Generation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "3946-3957",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100608"}
@inproceedings{bb103896,
AUTHOR = "Struppek, L. and Hintersdorf, D. and Kersting, K.",
TITLE = "Rickrolling the Artist: Injecting Backdoors into Text Encoders for
Text-to-Image Synthesis",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "4561-4573",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100609"}
@inproceedings{bb103897,
AUTHOR = "Basu, A. and Babu, R.V. and Pruthi, D.",
TITLE = "Inspecting the Geographical Representativeness of Images from
Text-to-Image Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "5113-5124",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100610"}
@inproceedings{bb103898,
AUTHOR = "Wang, S.Y. and Efros, A.A. and Zhu, J.Y. and Zhang, R.",
TITLE = "Evaluating Data Attribution for Text-to-Image Models",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "7158-7169",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100611"}
@inproceedings{bb103899,
AUTHOR = "Wei, Y.X. and Zhang, Y. and Ji, Z.L. and Bai, J.F. and Zhang, L. and Zuo, W.M.",
TITLE = "ELITE: Encoding Visual Concepts into Textual Embeddings for
Customized Text-to-Image Generation",
BOOKTITLE = ICCV23,
YEAR = "2023",
PAGES = "15897-15907",
BIBSOURCE = "http://www.visionbib.com/bibliography/describe489t2i3.html#TT100612"}
Last update:Aug 19, 2026 at 13:26:35