{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T22:56:59Z","timestamp":1775257019255,"version":"3.50.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030030131","type":"print"},{"value":"9783030030148","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","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":[[2018]]},"DOI":"10.1007\/978-3-030-03014-8_16","type":"book-chapter","created":{"date-parts":[[2018,10,24]],"date-time":"2018-10-24T16:12:33Z","timestamp":1540397553000},"page":"187-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning Generalized Video Memory for Automatic Video Captioning"],"prefix":"10.1007","author":[{"given":"Poo-Hee","family":"Chang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ah-Hwee","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,25]]},"reference":[{"issue":"2","key":"16_CR1","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157\u2013166 (1994)","journal-title":"IEEE Trans. Neural Netw."},{"key":"16_CR2","first-page":"87","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"GA Carpenter","year":"2003","unstructured":"Carpenter, G.A., Grossberg, S.: Adaptive Resonance Theory. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks, pp. 87\u201390. MIT Press, Cambridge (2003)"},{"issue":"6","key":"16_CR3","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1016\/0893-6080(91)90056-B","volume":"4","author":"GA Carpenter","year":"1991","unstructured":"Carpenter, G.A., Grossberg, S., Rosen, D.B.: Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Netw. 4(6), 759\u2013771 (1991)","journal-title":"Neural Netw."},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Chang, P.-H., Tan, A.-H.: Encoding and recall of spatio-temporal episodic memory in real time. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 1490\u20131496 (2017)","DOI":"10.24963\/ijcai.2017\/206"},{"key":"16_CR5","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 190\u2013200 (2011)"},{"key":"16_CR6","unstructured":"Chen, X., et al.: Microsoft COCO captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Denkowski, M., Lavie, A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the ninth workshop on Statistical Machine Translation, pp. 376\u2013380 (2014)","DOI":"10.3115\/v1\/W14-3348"},{"key":"16_CR8","unstructured":"Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: International Conference on Machine Learning, pp. 647\u2013655 (2014)"},{"key":"16_CR9","unstructured":"Fakoor, R., Mohamed, A., Mitchell, M., Kang, S.B., Kohli, P.: Memory-augmented attention modelling for videos. arXiv preprint arXiv:1611.02261 (2016)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A., Hinton, G.: Speech recognition with deep recurrent neural networks. In: Proceedings of the IEEE international conference on Acoustics, Speech and Signal Processing, pp. 6645\u20136649 (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"10","key":"16_CR11","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2016.2582924","volume":"28","author":"K Greff","year":"2017","unstructured":"Greff, K., Srivastava, R.K., Koutn\u00edk, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. IEEE Trans. Neural Netw. Learn. Syst. 28(10), 2222\u20132232 (2017)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Guadarrama, S., et al.: YouTube2Text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2712\u20132719 (2013)","DOI":"10.1109\/ICCV.2013.337"},{"key":"16_CR13","unstructured":"Hermans, M., Schrauwen, B.: Training and analysing deep recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 190\u2013198 (2013)"},{"issue":"8","key":"16_CR14","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":"16_CR15","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, N., Malkarnenkar, G., Mooney, R.J., Saenko, K., Guadarrama, S.: Generating natural-language video descriptions using text-mined knowledge. In: Association for the Advancement of Artificial Intelligence, vol. 1, p. 2 (2013)","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"16_CR17","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Pan, P., Xu, Z., Yang, Y., Wu, F., Zhuang, Y.: Hierarchical recurrent neural encoder for video representation with application to captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1029\u20131038 (2016)","DOI":"10.1109\/CVPR.2016.117"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4594\u20134602 (2016)","DOI":"10.1109\/CVPR.2016.497"},{"key":"16_CR20","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 on Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"3","key":"16_CR21","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"16_CR22","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"16_CR23","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.neucom.2015.02.038","volume":"161","author":"B Subagdja","year":"2015","unstructured":"Subagdja, B., Tan, A.-H.: Neural modeling of sequential inferences and learning over episodic memory. Neurocomputing 161, 229\u2013242 (2015)","journal-title":"Neurocomputing"},{"key":"16_CR24","unstructured":"Sukhbaatar, S., Weston, J., Fergus, R., et al.: End-to-end memory networks. In: Advances in Neural Information Processing Systems, pp. 2440\u20132448 (2015)"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Schl\u00fcter, R., Ney, H.: LSTM neural networks for language modeling. In: Conference of the International Speech Communication Association (2012)","DOI":"10.21437\/Interspeech.2012-65"},{"key":"16_CR26","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Advances in Neural Information Processing Systems, pp. 3104\u20133112 (2014)"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Tan, A.-H.: Falcon: a fusion architecture for learning, cognition, and navigation. In: Proceedings of the IEEE International Joint Conference on Neural Network, vol. 4, pp. 3297\u20133302. IEEE (2004)","DOI":"10.1109\/IJCNN.2004.1381208"},{"key":"16_CR29","unstructured":"Tan, A.-H.: Direct code access in self-organizing neural networks for reinforcement learning. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 1071\u20131076 (2007)"},{"key":"16_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1007\/978-3-540-72383-7_128","volume-title":"Advances in Neural Networks \u2013 ISNN 2007","author":"A-H Tan","year":"2007","unstructured":"Tan, A.-H., Carpenter, G.A., Grossberg, S.: Intelligence through interaction: towards a unified theory for learning. In: Liu, D., Fei, S., Hou, Z.-G., Zhang, H., Sun, C. (eds.) ISNN 2007. LNCS, vol. 4491, pp. 1094\u20131103. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-72383-7_128"},{"issue":"5","key":"16_CR31","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1109\/TNNLS.2014.2327636","volume":"26","author":"TH Teng","year":"2015","unstructured":"Teng, T.H., Tan, A.-H., Zurada, J.M.: Self-organizing neural networks integrating domain knowledge and reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. 26(5), 889\u2013902 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"16_CR32","unstructured":"Thomason, J., Venugopalan, S., Guadarrama, S., Saenko, K., Mooney, R.: Integrating language and vision to generate natural language descriptions of videos in the wild. In: Proceedings of the International Conference on Computational Linguistics, pp. 1218\u20131227 (2014)"},{"key":"16_CR33","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1494\u20131504 (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Wang, P., Zhou, W.J., Wang, D., Tan, A.-H.: Probabilistic guided exploration for reinforcement learning in self-organizing neural networks. In: Proceedings of International Conference on Agents, pp. 109\u2013112 (2018)","DOI":"10.1109\/AGENTS.2018.8460067"},{"key":"16_CR37","doi-asserted-by":"crossref","unstructured":"Wang, W., Subagdja, B., Tan, A.-H., Starzyk, J.A.: A self-organizing approach to episodic memory modeling. In: Proceedings of the IEEE International Joint Conference on Neural Networks, pp. 1\u20138. IEEE (2010)","DOI":"10.1109\/IJCNN.2010.5596734"},{"issue":"10","key":"16_CR38","doi-asserted-by":"publisher","first-page":"1574","DOI":"10.1109\/TNNLS.2012.2208477","volume":"23","author":"W Wang","year":"2012","unstructured":"Wang, W., Subagdja, B., Tan, A.-H., Starzyk, J.A.: Neural modeling of episodic memory: encoding, retrieval, and forgetting. IEEE Trans. Neural Netw. Learn. Syst. 23(10), 1574\u20131586 (2012)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"16_CR39","unstructured":"Weston, J., et al.: Towards ai-complete question answering: a set of prerequisite toy tasks. arXiv preprint arXiv:1502.05698 (2015)"},{"key":"16_CR40","unstructured":"Weston, J., Chopra, S., Bordes, A.: Memory networks. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4584\u20134593 (2016)","DOI":"10.1109\/CVPR.2016.496"}],"container-title":["Lecture Notes in Computer Science","Multi-disciplinary Trends in Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-03014-8_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T21:33:28Z","timestamp":1775252008000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-03014-8_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030030131","9783030030148"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-03014-8_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"MIWAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multi-disciplinary Trends in Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2018","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":"miwai2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/khamreang.msu.ac.th\/miwai18\/index.html","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"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"65","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"16","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"9","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"25% - 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"}},{"value":"3,09","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"2,45","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}