{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:40:35Z","timestamp":1753602035656,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031446955"},{"type":"electronic","value":"9783031446962"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44696-2_39","type":"book-chapter","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T09:03:59Z","timestamp":1696669439000},"page":"494-506","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["ZeroGen: Zero-Shot Multimodal Controllable Text Generation with\u00a0Multiple Oracles"],"prefix":"10.1007","author":[{"given":"Haoqin","family":"Tu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianfeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,8]]},"reference":[{"key":"39_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":"39_CR2","unstructured":"Anderson, P., Gould, S., Johnson, M.: Partially-supervised image captioning. In: NeurIPS (2018)"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. arXiv:2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"39_CR4","unstructured":"Dathathri, S., Madotto, A., et al.: Plug and play language models: a simple approach to controlled text generation. arXiv:1912.02164 (2019)"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: WSMT (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Ficler, J., Goldberg, Y.: Controlling linguistic style aspects in neural language generation. In: EMNLP (2017)","DOI":"10.18653\/v1\/W17-4912"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Gan, C., Gan, Z., He, X., Gao, J., Deng, L.: Stylenet: generating attractive visual captions with styles. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.108"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Gehrmann, S., Strobelt, H., Rush, A.M.: Gltr: statistical detection and visualization of generated text. In: ACL: System Demonstrations (2019)","DOI":"10.18653\/v1\/P19-3019"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Gu, Y., Feng, X., Ma, S., Wu, J., Gong, H., Qin, B.: Improving controllable text generation with position-aware weighted decoding. In: Findings of the ACL (2022)","DOI":"10.18653\/v1\/2022.findings-acl.272"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Honda, U., Ushiku, Y., et al.: Removing word-level spurious alignment between images and pseudo-captions in unsupervised image captioning. In: EACL (2021)","DOI":"10.18653\/v1\/2021.eacl-main.323"},{"key":"39_CR11","unstructured":"Houlsby, N., Giurgiu, A., et al.: Parameter-efficient transfer learning for nlp. In: ICML (2019)"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"39_CR13","unstructured":"Keskar, N.S., McCann, B., Varshney, L.R., Xiong, C., Socher, R.: Ctrl: a conditional transformer language model for controllable generation. arXiv:1909.05858 (2019)"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Krause, B., et al.: Gedi: generative discriminator guided sequence generation. In: Findings of the ACL (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.424"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Navab, N.: Towards unsupervised image captioning with shared multimodal embeddings. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00751"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Galley, M., Brockett, C., Gao, J., Dolan, B.: A diversity-promoting objective function for neural conversation models. arXiv:1510.03055 (2015)","DOI":"10.18653\/v1\/N16-1014"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Och, F.J.: Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: ACL (2004)","DOI":"10.3115\/1218955.1219032"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Liu, F., Wang, Y., Wang, T., Ordonez, V.: Visual news: benchmark and challenges in news image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.542"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Mai, F., Pappas, N., Montero, I., Smith, N.A., Henderson, J.: Plug and play autoencoders for conditional text generation. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.491"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Nukrai, D., Mokady, R., Globerson, A.: Text-only training for image captioning using noise-injected clip. arXiv:2211.00575 (2022)","DOI":"10.18653\/v1\/2022.findings-emnlp.299"},{"key":"39_CR22","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 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Pascual, D., Egressy, B., Meister, C., Cotterell, R., Wattenhofer, R.: A plug-and-play method for controlled text generation. In: Findings of the ACL (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.334"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"39_CR25","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: ICLR (2021)"},{"key":"39_CR26","unstructured":"Su, Y., et al.: Language models can see: plugging visual controls in text generation. arXiv:2205.02655"},{"key":"39_CR27","unstructured":"Su, Y., Lan, T., Wang, Y., Yogatama, D., Kong, L., Collier, N.: A contrastive framework for neural text generation. arXiv:2202.06417 (2022)"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Tewel, Y., Shalev, Y., Schwartz, I., Wolf, L.: Zerocap: zero-shot image-to-text generation for visual-semantic arithmetic. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Tu, H., Yang, Z., Yang, J., et al.: Pcae: a framework of plug-in conditional auto-encoder for controllable text generation. In: Knowledge-Based Systems (2022)","DOI":"10.1016\/j.knosys.2022.109766"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. arXiv:1411.5726 (2014)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Zhang, H., Wang, Z., Lu, R., Wang, D., Chen, B.: Conzic: controllable zero-shot image captioning by sampling-based polishing. arXiv:2303.02437 (2023)","DOI":"10.1109\/CVPR52729.2023.02247"},{"key":"39_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wu, X., Zhang, X.: Memcap: Memorizing style knowledge for image captioning. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6998"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44696-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T09:09:45Z","timestamp":1696669785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44696-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031446955","9783031446962"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44696-2_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Foshan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2023\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"478","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"143","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}