{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:30:07Z","timestamp":1778081407085,"version":"3.51.4"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729973","type":"print"},{"value":"9783031729980","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72998-0_18","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:01:58Z","timestamp":1727632918000},"page":"310-328","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Mismatch Quest: Visual and\u00a0Textual Feedback for\u00a0Image-Text Misalignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3016-3690","authenticated-orcid":false,"given":"Brian","family":"Gordon","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1185-6838","authenticated-orcid":false,"given":"Yonatan","family":"Bitton","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5068-9124","authenticated-orcid":false,"given":"Yonatan","family":"Shafir","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3343-9226","authenticated-orcid":false,"given":"Roopal","family":"Garg","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1581-4627","authenticated-orcid":false,"given":"Xi","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6191-0361","authenticated-orcid":false,"given":"Dani","family":"Lischinski","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6777-7445","authenticated-orcid":false,"given":"Daniel","family":"Cohen-Or","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2746-4027","authenticated-orcid":false,"given":"Idan","family":"Szpektor","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"18_CR1","unstructured":"Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"18_CR2","unstructured":"Adobe: Adobe firefly. https:\/\/www.adobe.com\/sensei\/generative-ai\/firefly.html"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: Spice: semantic propositional image caption evaluation (2016)","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"18_CR4","unstructured":"Anil, R., et al.: Palm 2 technical report (2023)"},{"key":"18_CR5","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: ACL Workshop on Evaluation Measures for MT and Summarization (2005)"},{"key":"18_CR6","unstructured":"Betker, J., et al.: Improving image generation with better captions (2023). https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"18_CR7","doi-asserted-by":"publisher","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graph. 42(4) (2023). https:\/\/doi.org\/10.1145\/3592116","DOI":"10.1145\/3592116"},{"key":"18_CR8","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"18_CR9","unstructured":"Chen, X., et al.: PaLI-X: on scaling up a multilingual vision and language model. arXiv abs\/2305.18565 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258967670"},{"key":"18_CR10","unstructured":"Chen, X., et al.: PaLI-3 vision language models: smaller, faster, stronger (2023)"},{"key":"18_CR11","unstructured":"Chen, X., et al.: PaLI: a jointly-scaled multilingual language-image model (2023). https:\/\/arxiv.org\/abs\/2209.06794"},{"key":"18_CR12","unstructured":"Cho, J., et al.: Davidsonian scene graph: improving reliability in fine-grained evaluation for text-to-image generation. arXiv:2310.18235 (2023)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Cho, J., Lu, J., Schwenk, D., Hajishirzi, H., Kembhavi, A.: X-LXMERT: paint, caption and answer questions with multi-modal transformers. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Cho, J., Zala, A., Bansal, M.: DALL-Eval: probing the reasoning skills and social biases of text-to-image generative transformers (2022)","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"18_CR15","unstructured":"Cho, J., Zala, A., Bansal, M.: Visual programming for text-to-image generation and evaluation. In: NeurIPS (2023)"},{"key":"18_CR16","series-title":"IFIP Advances in Information and Communication Technology","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-642-35142-6_14","volume-title":"Shaping the Future of ICT Research. Methods and Approaches","author":"K Crowston","year":"2012","unstructured":"Crowston, K.: Amazon mechanical Turk: a research tool for organizations and information systems scholars. In: Bhattacherjee, A., Fitzgerald, B. (eds.) IS &O 2012. IAICT, vol. 389, pp. 210\u2013221. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35142-6_14"},{"issue":"1","key":"18_CR17","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1017\/S1351324909990234","volume":"16","author":"I Dagan","year":"2010","unstructured":"Dagan, I., Dolan, B., Magnini, B., Roth, D.: Recognizing textual entailment: rational, evaluation and approaches-erratum. Nat. Lang. Eng. 16(1), 105 (2010)","journal-title":"Nat. Lang. Eng."},{"key":"18_CR18","unstructured":"Dai, W., et al.: InstructBLIP: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"18_CR19","unstructured":"Gokhale, T., et al.: Benchmarking spatial relationships in text-to-image generation. arXiv preprint arXiv:2212.10015 (2022)"},{"key":"18_CR20","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol.\u00a027. Curran Associates, Inc. (2014). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"18_CR22","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a1d694707eb0fefe65871369074926d-Paper.pdf"},{"key":"18_CR23","unstructured":"Hinz, T., Heinrich, S., Wermter, S.: Semantic object accuracy for generative text-to-image synthesis. arXiv preprint arXiv:1910.13321 (2019)"},{"key":"18_CR24","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications (2021). https:\/\/openreview.net\/forum?id=qw8AKxfYbI"},{"key":"18_CR25","doi-asserted-by":"publisher","unstructured":"Honnibal, M., Montani, I., Van\u00a0Landeghem, S., Boyd, A.: Spacy: industrial-strength natural language processing in python (2020). https:\/\/doi.org\/10.5281\/zenodo.1212303. https:\/\/github.com\/explosion\/spaCy\/tree\/master","DOI":"10.5281\/zenodo.1212303"},{"key":"18_CR26","doi-asserted-by":"publisher","unstructured":"Honovich, O., et al.: TRUE: re-evaluating factual consistency evaluation. In: Carpuat, M., de\u00a0Marneffe, M.C., Meza\u00a0Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, USA, pp. 3905\u20133920. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.287. https:\/\/aclanthology.org\/2022.naacl-main.287","DOI":"10.18653\/v1\/2022.naacl-main.287"},{"key":"18_CR27","doi-asserted-by":"publisher","unstructured":"Honovich, O., Choshen, L., Aharoni, R., Neeman, E., Szpektor, I., Abend, O.: $${Q}^{2}$$: evaluating factual consistency in knowledge-grounded dialogues via question generation and question answering. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7856\u20137870. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.619. https:\/\/aclanthology.org\/2021.emnlp-main.619","DOI":"10.18653\/v1\/2021.emnlp-main.619"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: TIFA: accurate and interpretable text-to-image faithfulness evaluation with question answering. arXiv preprint arXiv:2303.11897 (2023)","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"18_CR29","unstructured":"Kirstain, Y., Polyak, A., Singer, U., Matiana, S., Penna, J., Levy, O.: Pick-a-pic: an open dataset of user preferences for text-to-image generation (2023)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. IJCV (2020)","DOI":"10.1007\/s11263-020-01316-z"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"18_CR32","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"18_CR34","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. Text Summarization Branches Out (2004)"},{"key":"18_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"18_CR37","unstructured":"Liu, N., Li, S., Du, Y., Tenenbaum, J., Torralba, A.: Learning to compose visual relations. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034, pp. 23166\u201323178. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/c3008b2c6f5370b744850a98a95b73ad-Paper.pdf"},{"key":"18_CR38","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1007\/978-3-031-19790-1_26","volume-title":"ECCV 2022","author":"N Liu","year":"2022","unstructured":"Liu, N., Li, S., Du, Y., Torralba, A., Tenenbaum, J.B.: Compositional visual generation with composable diffusion models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 423\u2013439. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_26"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR40","unstructured":"Mansimov, E., Parisotto, E., Ba, J., Salakhutdinov, R.: Generating images from captions with attention. In: ICLR (2016)"},{"key":"18_CR41","unstructured":"Marcus, G., Davis, E., Aaronson, S.: A very preliminary analysis of DALL-E 2 (2022)"},{"key":"18_CR42","unstructured":"OpenAI: ChatGPT (2022). https:\/\/openai.com\/blog\/chatgpt"},{"key":"18_CR43","unstructured":"OpenAI: GPT-4 technical report. arXiv abs\/2303.08774 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257532815"},{"key":"18_CR44","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, Pennsylvania, USA, pp. 311\u2013318. Association for Computational Linguistics (2002). https:\/\/doi.org\/10.3115\/1073083.1073135. https:\/\/aclanthology.org\/P02-1040","DOI":"10.3115\/1073083.1073135"},{"key":"18_CR45","unstructured":"Park, D.H., Azadi, S., Liu, X., Darrell, T., Rohrbach, A.: Benchmark for compositional text-to-image synthesis. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1) (2021). https:\/\/openreview.net\/forum?id=bKBhQhPeKaF"},{"key":"18_CR46","unstructured":"Petsiuk, V., et al.: Human evaluation of text-to-image models on a multi-task benchmark (2022)"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. Int. J. Comput. Vis. 123, 74\u201393 (2015). https:\/\/api.semanticscholar.org\/CorpusID:6941275","DOI":"10.1007\/s11263-016-0965-7"},{"key":"18_CR48","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"18_CR49","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/978-3-030-58558-7_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Pont-Tuset","year":"2020","unstructured":"Pont-Tuset, J., Uijlings, J., Changpinyo, S., Soricut, R., Ferrari, V.: Connecting vision and language with localized narratives. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 647\u2013664. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_38"},{"key":"18_CR50","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"18_CR51","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018). https:\/\/api.semanticscholar.org\/CorpusID:49313245"},{"key":"18_CR52","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"18_CR53","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022)"},{"key":"18_CR54","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8821\u20138831. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/ramesh21a.html"},{"key":"18_CR55","unstructured":"Rassin, R., Hirsch, E., Glickman, D., Ravfogel, S., Goldberg, Y., Chechik, G.: Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment. arXiv preprint arXiv:2306.08877 (2023)"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Rassin, R., Ravfogel, S., Goldberg, Y.: DALLE-2 is seeing double: flaws in word-to-concept mapping in text2image models (2022)","DOI":"10.18653\/v1\/2022.blackboxnlp-1.28"},{"key":"18_CR57","unstructured":"Reed, S., Akata, Z., Mohan, S., Tenka, S., Schiele, B., Lee, H.: Learning what and where to draw. In: Advances in Neural Information Processing Systems (2016)"},{"key":"18_CR58","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of the 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, New York, New York, USA, vol.\u00a048, pp. 1060\u20131069. PMLR (2016). https:\/\/proceedings.mlr.press\/v48\/reed16.html"},{"key":"18_CR59","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"18_CR60","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"18_CR61","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. arXiv abs\/2205.11487 (2022). https:\/\/api.semanticscholar.org\/CorpusID:248986576"},{"key":"18_CR62","unstructured":"Salimans, T., et al.: Improved techniques for training GANs. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a029. Curran Associates, Inc. (2016). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2016\/file\/8a3363abe792db2d8761d6403605aeb7-Paper.pdf"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR, pp. 4566\u20134575. IEEE Computer Society (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"18_CR64","unstructured":"Wu, C., Yin, S., Qi, W., Wang, X., Tang, Z., Duan, N.: Visual chatGPT: talking, drawing and editing with visual foundation models (2023)"},{"key":"18_CR65","unstructured":"Xie, N., Lai, F., Doran, D., Kadav, A.: Visual entailment task for visually-grounded language learning. arXiv preprint arXiv:1811.10582 (2018)"},{"key":"18_CR66","unstructured":"Xu, J., et al.: ImageReward: learning and evaluating human preferences for text-to-image generation (2023)"},{"key":"18_CR67","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"18_CR68","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"18_CR69","unstructured":"Yang, Z., et al.: MM-REACT: prompting chatGPT for multimodal reasoning and action (2023)"},{"key":"18_CR70","unstructured":"Yarom, M., et al.: What you see is what you read? Improving text-image alignment evaluation. arXiv preprint arXiv:2305.10400 (2023)"},{"key":"18_CR71","unstructured":"Ye, Q., et\u00a0al.: mPLUG-Owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"18_CR72","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation (2022)"},{"key":"18_CR73","doi-asserted-by":"publisher","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6713\u20136724 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00688","DOI":"10.1109\/CVPR.2019.00688"},{"key":"18_CR74","unstructured":"Zhang, K., Mo, L., Chen, W., Sun, H., Su, Y.: MagicBrush: a manually annotated dataset for instruction-guided image editing. In: Advances in Neural Information Processing Systems (2023)"},{"key":"18_CR75","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with BERT. In: ICLR (2020)"},{"key":"18_CR76","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.544"},{"issue":"3","key":"18_CR77","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vis. 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vis."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72998-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:29:26Z","timestamp":1732829366000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72998-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031729973","9783031729980"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72998-0_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}