{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:25:26Z","timestamp":1771953926914,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727740","type":"print"},{"value":"9783031727757","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\/978-3-031-72775-7_21","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"365-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["DECap: Towards Generalized Explicit Caption Editing via\u00a0Diffusion Mechanism"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"21_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: CVPR, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"21_CR3","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., Van Den\u00a0Berg, R.: Structured denoising diffusion models in discrete state-spaces. In: NeurIPS, vol.\u00a034, pp. 17981\u201317993 (2021)"},{"key":"21_CR4","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: ACL Workshop, pp. 65\u201372 (2005)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Jiang, Z., Xiao, J., Liu, W.: Human-like controllable image captioning with verb-specific semantic roles. In: CVPR, pp. 16846\u201316856 (2021)","DOI":"10.1109\/CVPR46437.2021.01657"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: SCA-CNN: spatial and channel-wise attention in convolutional networks for image captioning. In: CVPR, pp. 5659\u20135667 (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"21_CR7","unstructured":"Chen, T., Zhang, R., Hinton, G.: Analog bits: generating discrete data using diffusion models with self-conditioning. arXiv (2022)"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Cucchiara, R.: Show, control and tell: a framework for generating controllable and grounded captions. In: CVPR, pp. 8307\u20138316 (2019)","DOI":"10.1109\/CVPR.2019.00850"},{"key":"21_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1007\/978-3-030-58601-0_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Deng","year":"2020","unstructured":"Deng, C., Ding, N., Tan, M., Wu, Q.: Length-controllable image captioning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 712\u2013729. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_42"},{"key":"21_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv (2018)"},{"key":"21_CR11","unstructured":"He, Y., Cai, Z., Gan, X., Chang, B.: DiffCap: exploring continuous diffusion on image captioning. arXiv (2023)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"He, Z., Sun, T., Wang, K., Huang, X., Qiu, X.: DiffusionBERT: improving generative masked language models with diffusion models. arXiv (2022)","DOI":"10.18653\/v1\/2023.acl-long.248"},{"key":"21_CR13","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"21_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. arXiv (2022)"},{"key":"21_CR15","unstructured":"Li, X., Thickstun, J., Gulrajani, I., Liang, P.S., Hashimoto, T.B.: Diffusion-LM improves controllable text generation. In: NeurIPS, vol.\u00a035, pp. 4328\u20134343 (2022)"},{"key":"21_CR16","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: ACL Workshop, pp. 74\u201381 (2004)"},{"key":"21_CR17","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":"21_CR18","doi-asserted-by":"crossref","unstructured":"Luo, J., et al.: Semantic-conditional diffusion networks for image captioning. In: CVPR, pp. 23359\u201323368 (2023)","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Mallinson, J., Severyn, A., Malmi, E., Garrido, G.: FELIX: flexible text editing through tagging and insertion. arXiv (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.111"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Mao, Y., et al.: Rethinking the reference-based distinctive image captioning. In: ACM MM, pp. 4374\u20134384 (2022)","DOI":"10.1145\/3503161.3548358"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Reid, M., Neubig, G.: Learning to model editing processes. arXiv (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.280"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: ACL, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"21_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol.\u00a030 (2017)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: CVPR, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"21_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-3-031-20059-5_7","volume-title":"ECCV 2022","author":"Z Wang","year":"2022","unstructured":"Wang, Z., et al.: Explicit image caption editing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 113\u2013129. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_7"},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xiao, J., Zhuang, Y., Gao, F., Shao, J., Chen, L.: Learning combinatorial prompts for universal controllable image captioning. IJCV, 1\u201322 (2024)","DOI":"10.1007\/s11263-024-02179-4"},{"key":"21_CR30","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML, pp. 2048\u20132057 (2015)"},{"key":"21_CR31","unstructured":"Xu, Y., Wang, Z., Xiao, J., Liu, W., Chen, L.: FreeTuner: any subject in any style with training-free diffusion. arXiv preprint arXiv:2405.14201 (2024)"},{"key":"21_CR32","unstructured":"Zhu, Z., et al.: Exploring discrete diffusion models for image captioning. arXiv (2022)"}],"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\/978-3-031-72775-7_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:42:56Z","timestamp":1727595776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72775-7_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727740","9783031727757"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72775-7_21","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"}}]}}