{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:35:51Z","timestamp":1743057351308,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031171888"},{"type":"electronic","value":"9783031171895"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-17189-5_15","type":"book-chapter","created":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T23:20:50Z","timestamp":1663975250000},"page":"179-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation"],"prefix":"10.1007","author":[{"given":"Bin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyu","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shutao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,24]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"De Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., Courville, A.: Guesswhat?! visual object discovery through multi-modal dialogue. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5503\u20135512 (2017)","DOI":"10.1109\/CVPR.2017.475"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Deldjoo, Y., Trippas, J.R., Zamani, H.: Towards multi-modal conversational information seeking. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1577\u20131587 (2021)","DOI":"10.1145\/3404835.3462806"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Roller, S., et al.: Recipes for building an open-domain chatbot. In: Conference of the European Chapter of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.eacl-main.24"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Zhou, H., Huang, M., Zhang, T., Zhu, X., Liu, B.: Emotional chatting machine: emotional conversation generation with internal and external memory. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11325"},{"key":"15_CR5","unstructured":"Su, Y., et al.: Language models can see: plugging visual controls in text generation. arXiv preprint arXiv:2205.02655 (2022)"},{"key":"15_CR6","unstructured":"Wang, Y., Zhao, X., Zhao, D.: NLPCC-2022-Shared-Task-4, May 2022"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"15_CR8","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7W: grounded question answering in images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4995\u20135004 (2016)","DOI":"10.1109\/CVPR.2016.540"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Alamri, H., et al.: Audio visual scene-aware dialog. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7558\u20137567 (2019)","DOI":"10.1109\/CVPR.2019.00774"},{"key":"15_CR11","unstructured":"Fang, H., Xiong, P., Xu, L., Chen, Y.: Clip2Video: mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Li, B., Weng, Y., Sun, B., Li, S.: Towards visual-prompt temporal answering grounding in medical instructional video. arXiv preprint arXiv:2203.06667 (2022)","DOI":"10.36227\/techrxiv.22182736.v1"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"15_CR14","unstructured":"Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"15_CR15","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Sun, R., Chen, B., Zhou, Q., Li, Y., Cao, Y., Zheng, H.-T.: A non-hierarchical attention network with modality dropout for textual response generation in multimodal dialogue systems. arXiv preprint arXiv:2110.09702 (2021)","DOI":"10.1109\/ICASSP43922.2022.9746613"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Li, B., Weng, Y., Xia, F., Sun, B., Li, S.: VPAI_LAB at MedVidQA 2022: a two-stage cross-modal fusion method for medical instructional video classification. In: Proceedings of the 21st Workshop on Biomedical Language Processing, pp. 212\u2013219 (2022)","DOI":"10.18653\/v1\/2022.bionlp-1.21"},{"key":"15_CR20","unstructured":"Luo, H., et al.: UniVL: a unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)"},{"key":"15_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BlIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. arXiv preprint arXiv:2201.12086 (2022)"},{"key":"15_CR22","unstructured":"Wang, Z., et al.: Language models with image descriptors are strong few-shot video-language learners. arXiv preprint arXiv:2205.10747 (2022)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586 (2021)","DOI":"10.1145\/3560815"},{"key":"15_CR24","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Taylor, W.L.: Cloze procedure: a new tool for measuring readability. Journalism Mass Commun. Q. 30 (1953)","DOI":"10.1177\/107769905303000401"},{"key":"15_CR26","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv Computation and Language (2019)"},{"key":"15_CR27","unstructured":"Clark, K., Luong, M.-T., Le, Q.V., Manning, C.D.: Electra: pre-training text encoders as discriminators rather than generators. In: Learning (2020)"},{"key":"15_CR28","unstructured":"He, P., Gao, J., Chen, W.: DeBERtaV 3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing. arXiv Computation and Language (2021)"},{"key":"15_CR29","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1016\/j.tics.2020.09.004","volume":"24","author":"R Hadsell","year":"2020","unstructured":"Hadsell, R., Rao, D., Rusu, A., Pascanu, R.: Embracing change: continual learning in deep neural networks. Trends Cogn. Sci. 24, 1028\u20131040 (2020)","journal-title":"Trends Cogn. Sci."},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Meeting fof the Association or Computational Linguistics (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"issue":"140","key":"15_CR31","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: Zero: memory optimizations toward training trillion parameter models. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020. IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00024"},{"key":"15_CR33","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"}],"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\/978-3-031-17189-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T16:52:04Z","timestamp":1701103924000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-17189-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031171888","9783031171895"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-17189-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"24 September 2022","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":"Guilin","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2022\/","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":"327","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":"73","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":"22% - 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":"1.5","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)"}}]}}