{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T00:46:05Z","timestamp":1753922765508,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031226946"},{"type":"electronic","value":"9783031226953"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-22695-3_2","type":"book-chapter","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T15:11:58Z","timestamp":1669993918000},"page":"15-28","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Vision Transformer Based Model for\u00a0Describing a\u00a0Set of\u00a0Images as\u00a0a\u00a0Story"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6980-0992","authenticated-orcid":false,"given":"Zainy M.","family":"Malakan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6636-8807","authenticated-orcid":false,"given":"Ghulam Mubashar","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5206-3842","authenticated-orcid":false,"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,3]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Al Nahian, M.S., Tasrin, T., Gandhi, S., Gaines, R., Harrison, B.: A hierarchical approach for visual storytelling using image description. In: International Conference on Interactive Digital Storytelling, pp. 304\u2013317. Springer (2019)","DOI":"10.1007\/978-3-030-33894-7_30"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"do Carmo Nogueira, T., Vinhal, C.D.N., da Cruz J\u00fanior, G., Ullmann, M.R.D.: Reference-based model using multimodal gated recurrent units for image captioning. Multimedia Tools Appl. 79(41), 30615\u201330635 (2020)","DOI":"10.1007\/s11042-020-09539-5"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chen, H., Huang, Y., Takamura, H., Nakayama, H.: Commonsense knowledge aware concept selection for diverse and informative visual storytelling. arXiv preprint arXiv:2102.02963 (2021)","DOI":"10.1609\/aaai.v35i2.16184"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Cho, K., Van Merri\u00ebnboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)","DOI":"10.3115\/v1\/W14-4012"},{"key":"2_CR5","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.patrec.2019.03.021","volume":"123","author":"S Ding","year":"2019","unstructured":"Ding, S., Qu, S., Xi, Y., Sangaiah, A.K., Wan, S.: Image caption generation with high-level image features. Pattern Recogn. Lett. 123, 89\u201395 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"2_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: Transformers for image recognition at scale (2020). 10.48550\/arxiv.2010.11929"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Fei, Z., Yan, X., Wang, S., Tian, Q.: Deecap: dynamic early exiting for efficient image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12216\u201312226 (2022)","DOI":"10.1109\/CVPR52688.2022.01190"},{"issue":"1","key":"2_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13640-020-00543-1","volume":"2021","author":"Y Guo","year":"2021","unstructured":"Guo, Y., Wu, H., Zhang, X.: Steganographic visual story with mutual-perceived joint attention. EURASIP J. Image Video Process. 2021(1), 1\u201314 (2021). https:\/\/doi.org\/10.1186\/s13640-020-00543-1","journal-title":"EURASIP J. Image Video Process."},{"issue":"8","key":"2_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Hu, J., Cheng, Y., Gan, Z., Liu, J., Gao, J., Neubig, G.: What makes a good story? designing composite rewards for visual storytelling. In: AAAI, pp. 7969\u20137976 (2020)","DOI":"10.1609\/aaai.v34i05.6305"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Huang, L., Wang, W., Chen, J., Wei, X.Y.: Attention on attention for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4634\u20134643 (2019)","DOI":"10.1109\/ICCV.2019.00473"},{"key":"2_CR12","unstructured":"Huang, T.H., et al.: Visual storytelling. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1233\u20131239 (2016)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, W., Zhou, W., Hu, H.: Double-stream position learning transformer network for image captioning. IEEE Trans. Circ. Syst. Video Technol. (2022)","DOI":"10.1109\/TCSVT.2022.3181490"},{"key":"2_CR14","unstructured":"Kim, T., Heo, M.O., Son, S., Park, K.W., Zhang, B.T.: Glac net: Glocal attention cascading networks for multi-image cued story generation. arXiv preprint arXiv:1805.10973 (2018)"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Li, G., Zhu, L., Liu, P., Yang, Y.: Entangled transformer for image captioning. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8928\u20138937 (2019)","DOI":"10.1109\/ICCV.2019.00902"},{"key":"2_CR16","doi-asserted-by":"publisher","first-page":"2726","DOI":"10.1109\/TIP.2022.3158546","volume":"31","author":"L Li","year":"2022","unstructured":"Li, L., Gao, X., Deng, J., Tu, Y., Zha, Z.J., Huang, Q.: Long short-term relation transformer with global gating for video captioning. IEEE Transactions on Image Processing 31, 2726\u20132738 (2022)","journal-title":"IEEE Transactions on Image Processing"},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"Li, Y., Pan, Y., Yao, T., Mei, T.: Comprehending and ordering semantics for image captioning. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17969\u201317978 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01746","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Lin, K., et al.: Swinbert: end-to-end transformers with sparse attention for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17949\u201317958 (2022)","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"2_CR19","doi-asserted-by":"publisher","unstructured":"Liu, Y., Fu, J., Mei, T., Chen, C.W.: Let your photos talk: generating narrative paragraph for photo stream via bidirectional attention recurrent neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1 (2017). https:\/\/doi.org\/10.1609\/aaai.v31i1.10760,https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/10760","DOI":"10.1609\/aaai.v31i1.10760,"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Malakan., Z., Aafaq., N., Hassan., G., Mian., A.: Contextualise, attend, modulate and tell: Visual storytelling. In: Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, pp. 196\u2013205. INSTICC, SciTePress (2021).https:\/\/doi.org\/10.5220\/0010314301960205","DOI":"10.5220\/0010314301960205"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Malakan, Z.M., Hassan, G.M., Jalwana, M.A.A.K., Aafaq, N., Mian, A.: Semantic attribute enriched storytelling from a sequence of images. In: 2021 Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u20138 (2021). https:\/\/doi.org\/10.1109\/DICTA52665.2021.9647213","DOI":"10.1109\/DICTA52665.2021.9647213"},{"key":"2_CR22","unstructured":"Melis, G., Ko\u010disk\u00fd, T., Blunsom, P.: Mogrifier lstm. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=SJe5P6EYvS"},{"key":"2_CR23","unstructured":"Mogadala, A., Shen, X., Klakow, D.: Integrating image captioning with rule-based entity masking. arXiv preprint arXiv:2007.11690 (2020)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Pan, B., et al.: Spatio-temporal graph for video captioning with knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10870\u201310879 (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Pang, S., Chen, Z., Yin, F.: Video super-resolution using a hierarchical recurrent multireceptive-field integration network. Digital Sign. Process. 122, 103352 (2022)","DOI":"10.1016\/j.dsp.2021.103352"},{"key":"2_CR26","unstructured":"Park, C.C., Kim, G.: Expressing an image stream with a sequence of natural sentences. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Phukan, B.B., Panda, A.R.: An efficient technique for image captioning using deep neural network. arXiv preprint arXiv:2009.02565 (2020)","DOI":"10.1007\/978-981-16-1056-1_38"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Seo, P.H., Nagrani, A., Arnab, A., Schmid, C.: End-to-end generative pretraining for multimodal video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17959\u201317968 (2022)","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Shen, X., Liu, B., Zhou, Y., Zhao, J., Liu, M.: Remote sensing image captioning via variational autoencoder and reinforcement learning. Knowl.-Based Syst. 105920 (2020)","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Wang, J., Fu, J., Tang, J., Li, Z., Mei, T.: Show, reward and tell: Automatic generation of narrative paragraph from photo stream by adversarial training. In: The AAAI Conference on Artificial Intelligence (AAAI), vol. 32, no. 10 (2018)","DOI":"10.1609\/aaai.v32i1.12318"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, W., Wang, L., Wang, Z., Feng, D.D., Tan, T.: Learning visual relationship and context-aware attention for image captioning. Pattern Recogn. 98, 107075 (2020)","DOI":"10.1016\/j.patcog.2019.107075"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, W., Wang, Y.F., Wang, W.Y.: No metrics are perfect: adversarial reward learning for visual storytelling. arXiv preprint arXiv:1804.09160 (2018)","DOI":"10.18653\/v1\/P18-1083"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.: End-to-end dense video captioning with masked transformer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8739\u20138748 (2018)","DOI":"10.1109\/CVPR.2018.00911"}],"container-title":["Lecture Notes in Computer Science","AI 2022: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22695-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:20:41Z","timestamp":1710256841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22695-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031226946","9783031226953"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22695-3_2","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":"3 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Perth, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"5 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2022.org\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"90","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":"56","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":"62% - 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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}