{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T10:26:55Z","timestamp":1745317615014,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030661861"},{"type":"electronic","value":"9783030661878"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-66187-8_31","type":"book-chapter","created":{"date-parts":[[2020,12,19]],"date-time":"2020-12-19T06:02:44Z","timestamp":1608357764000},"page":"330-340","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GlosysIC Framework: Transformer for Image Captioning with Sequential Attention"],"prefix":"10.1007","author":[{"given":"Srinivasan","family":"Thanukrishnan","sequence":"first","affiliation":[]},{"given":"R. Sai","family":"Venkatesh","sequence":"additional","affiliation":[]},{"given":"Prasad Rao","family":"Vijay Vignesh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,12,20]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","DOI":"10.1109\/CVPR.2018.00636"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Association for Computational Linguistics (ACL), pp. 311\u2013318. Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"31_CR3","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus based image description evaluation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (20152015)"},{"key":"31_CR4","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS), pp. 6000\u20136010 (2017)"},{"key":"31_CR5","unstructured":"Yao, T., Pan, Y., Li, Y., Qiu, Z., Mei, T.: Boosting image captioning with attributes. In: IEEE International Conference on Computer Vision (ICCV), pp. 4894\u20134902 (201)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: European Conference on Computer Vision (ECCV), pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"issue":"8","key":"31_CR7","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":"31_CR8","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"31_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-030-01216-8_31","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W Jiang","year":"2018","unstructured":"Jiang, W., Ma, L., Jiang, Y.-G., Liu, W., Zhang, T.: Recurrent fusion network for image captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 510\u2013526. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_31"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"31_CR12","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, vol. 3, pp. 2048\u20132057 (2015)"},{"key":"31_CR13","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of ICLR (2017)"},{"key":"31_CR14","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":"31_CR15","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization (2015)"},{"key":"31_CR16","unstructured":"Yu, J., Li, J., Yu, Z., Huang, Q.: Multimodal transformer with multi-view visual representation for image captioning. arXiv:1905.07841v1 (2019)"},{"key":"31_CR17","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 3104\u20133112 (2014)"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Lin, Z.\u00b8 Zhao, S., Han, J.: Show, observe and tell: attribute-driven attention model for image captioning. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 606\u2013612 (2018)","DOI":"10.24963\/ijcai.2018\/84"},{"key":"31_CR19","unstructured":"Wu, Q., Shen, C., Wang, P., Dick, A., van den Hengel, A.: Image captioning and visual question answering based on attributes and external knowledge. IEEE Trans. Pattern Anal. Mach. Intell. 40, 1367\u20131381 (2018)"},{"key":"31_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-030-01252-6_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Chen","year":"2018","unstructured":"Chen, S., Zhao, Q.: Boosted Attention: Leveraging Human Attention for Image Captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 72\u201388. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_5"},{"key":"31_CR21","doi-asserted-by":"publisher","first-page":"739","DOI":"10.3390\/app8050739","volume":"8","author":"X Zhu","year":"2018","unstructured":"Zhu, X., Liu, J., Peng, H., Niu, X.: Captioning transformer with stacked attention modules. Appl. Sci. 8, 739 (2018)","journal-title":"Appl. Sci."},{"key":"31_CR22","unstructured":"Pu, Y., et al.: Variational autoencoder for deep learning of images, labels and captions. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, pp. 2352\u20132360 (2016)"},{"key":"31_CR23","unstructured":"Yang, Z., Yuan, Y., Wu, Y., Salakhutdinov, R., Cohen, W.W.: Encode, review, and decode: reviewer module for caption generation. In: NIPS (2016)"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.345"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. In: CVPR (2015)","DOI":"10.21236\/ADA623249"},{"key":"31_CR26","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: Paying more attention to saliency: image captioning with saliency and context attention. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 14, 1\u201321 (2018)"},{"key":"31_CR27","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.neucom.2018.12.026","volume":"333","author":"YH Tan","year":"2019","unstructured":"Tan, Y.H., Chan, C.S.: Phrase-based image caption generator with hierarchical LSTM network. Neurocomputing 333, 86\u2013100 (2019)","journal-title":"Neurocomputing"},{"key":"31_CR28","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.neucom.2018.10.059","volume":"330","author":"A Yuan","year":"2019","unstructured":"Yuan, A., Li, X., Lu, X.: 3G structure for image caption generation. Neurocomputing 330, 17\u201328 (2019)","journal-title":"Neurocomputing"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Aneja, J., Deshpande, A., Schwing, A.: Convolutional image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp. 5561\u20135570 (2018)","DOI":"10.1109\/CVPR.2018.00583"}],"container-title":["Lecture Notes in Computer Science","Mining Intelligence and Knowledge Exploration"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66187-8_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,19]],"date-time":"2020-12-19T06:15:59Z","timestamp":1608358559000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-66187-8_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030661861","9783030661878"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66187-8_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"20 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIKE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Mining Intelligence and Knowledge Exploration","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Goa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 December 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 December 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mike2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mike.org.in\/2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}