{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T21:18:15Z","timestamp":1785273495272,"version":"3.55.0"},"reference-count":33,"publisher":"Tsinghua University Press","issue":"4","content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1007\/s41095-016-0059-z","type":"journal-article","created":{"date-parts":[[2016,8,30]],"date-time":"2016-08-30T10:24:04Z","timestamp":1472552644000},"page":"379-388","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["LSTM-in-LSTM for generating long descriptions of images"],"prefix":"10.26599","volume":"2","author":[{"given":"Jun","family":"Song","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongfei","family":"Mark Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Watson School of Engineering and Applied Sciences, Binghamton University, Binghamton, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"59_CR1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision\u2014ECCV 2010","author":"A. Farhadi","year":"2010","unstructured":"Farhadi, A.; Hejrati, M.; Sadeghi, M. A.; Young, P.; Rashtchian, C.; Hockenmaier, J.; Forsyth, D. Every picture tells a story: Generating sentences from images. In: Computer Vision\u2014ECCV 2010. Daniilidis, K.; Maragos, P.; Paragios, N. Eds. Springer Berlin Heidelberg, 15\u201329, 2010."},{"issue":"12","key":"59_CR2","doi-asserted-by":"crossref","first-page":"2891","DOI":"10.1109\/TPAMI.2012.162","volume":"35","author":"G. Kulkarni","year":"2013","unstructured":"Kulkarni, G.; Premraj, V.; Ordonez, V.; Dhar, S.; Li, S.; Choi, Y.; Berg, A. C.; Berg, T. L. BabyTalk: Understanding and generating simple image descriptions. IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 35, No. 12, 2891\u20132903, 2013.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"59_CR3","first-page":"220","volume-title":"Proceedings of the 15th Conference on Computational Natural Language Learning","author":"S. Li","year":"2011","unstructured":"Li, S.; Kulkarni, G.; Berg, T. L.; Berg, A. C.; Choi, Y. Composing simple image descriptions using web-scale n-grams. In: Proceedings of the 15th Conference on Computational Natural Language Learning, 220\u2013228, 2011."},{"key":"59_CR4","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1007\/978-3-319-10593-2_35","volume-title":"Computer Vision\u2014ECCV 2014","author":"Y. Gong","year":"2014","unstructured":"Gong, Y.; Wang, L.; Hodosh, M.; Hockenmaier, J.; Lazebnik, S. Improving image-sentence embeddings using large weakly annotated photo collections. In: Computer Vision\u2014ECCV 2014. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer International Publishing, 529\u2013545, 2014."},{"key":"59_CR5","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M. Hodosh","year":"2013","unstructured":"Hodosh, M.; Young, P.; Hockenmaier, J. Framing image description as a ranking task: Data, models and evaluation metrics. Journal of Artificial Intelligence Research Vol. 47, 853\u2013899, 2013.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"59_CR6","first-page":"1143","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"V. Ordonez","year":"2011","unstructured":"Ordonez, V.; Kulkarni, G.; Berg, T. L. Im2text: Describing images using 1 million captioned photographs. In: Proceedings of Advances in Neural Information Processing Systems, 1143\u20131151, 2011."},{"key":"59_CR7","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1162\/tacl_a_00177","volume":"2","author":"R. Socher","year":"2014","unstructured":"Socher, R.; Karpathy, A.; Le, Q. V.; Manning, C. D.; Ng, A. Y. Grounded compositional semantics for finding and describing images with sentences. Transactions of the Association for Computational Linguistics Vol. 2, 207\u2013218, 2014.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"59_CR8","first-page":"3128","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"A. Karpathy","year":"2015","unstructured":"Karpathy, A.; Fei-Fei, L. Deep visual-semantic alignments for generating image descriptions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 3128\u20133137, 2015."},{"key":"59_CR9","volume-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"J. Mao","year":"2014","unstructured":"Mao, J.; Xu, W.; Yang, Y.; Wang, J.; Huang, Z.; Yuille, A. Deep captioning with multimodal recurrent neural networks (m-RNN). arXiv preprint arXiv:1412.6632, 2014."},{"key":"59_CR10","first-page":"3156","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"O. Vinyals","year":"2015","unstructured":"Vinyals, O.; Toshev, A.; Bengio, S.; Erhan, D. Show and tell: A neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3156\u20133164, 2015."},{"key":"59_CR11","volume-title":"Aligning where to see and what to tell: Image caption with region-based attention and scene factorization","author":"J. Jin","year":"2015","unstructured":"Jin, J.; Fu, K.; Cui, R.; Sha, F.; Zhang, C. Aligning where to see and what to tell: Image caption with region-based attention and scene factorization. arXiv preprint arXiv:1506.06272, 2015."},{"key":"59_CR12","first-page":"2048","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"K. Xu","year":"2015","unstructured":"Xu, K.; Ba, J.; Kiros, R.; Cho, K.; Courville, A.; Salakhutdinov, R.; Zemel, R. S.; Bengio, Y. Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of the 32nd International Conference on Machine Learning, 2048\u20132057, 2015."},{"key":"59_CR13","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/3-540-33486-6_6","volume-title":"Innovations in Machine Learning","author":"Y. Bengio","year":"2006","unstructured":"Bengio, Y.; Schwenk, H.; Senecal, J.-S.; Morin, F.; Gauvain, J.-L. Neural probabilistic language models. In: Innovations in Machine Learning. Holmes, D. E.; Jain, L. C. Eds. Springer Berlin Heidelberg, 137\u2013186, 2006."},{"issue":"4","key":"59_CR14","doi-asserted-by":"crossref","first-page":"694","DOI":"10.1109\/TASLP.2016.2520371","volume":"24","author":"H. Palangi","year":"2016","unstructured":"Palangi, H.; Deng, L.; Shen, Y.; Gao, J.; He, X.; Chen, J.; Song, X.; Ward, R. Deep sentence embedding using the long short term memory network: Analysis and application to information retrieval. IEEE\/ACM Transactions on Audio, Speech, and Language Processing Vol. 24, No. 4, 694\u2013707, 2016.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"59_CR15","volume-title":"Neural machine translation by jointly learning to align and translate","author":"D. Bahdanau","year":"2014","unstructured":"Bahdanau, D.; Cho, K.; Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014."},{"key":"59_CR16","first-page":"1097","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A. Krizhevsky","year":"2012","unstructured":"Krizhevsky, A.; Sutskever, I.; Hinton, G. E. Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems, 1097\u20131105, 2012."},{"key":"59_CR17","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"K. Simonyan","year":"2014","unstructured":"Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014."},{"key":"59_CR18","first-page":"580","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"R. Girshick","year":"2014","unstructured":"Girshick, R.; Donahue, J.; Darrell, T.; Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 580\u2013587, 2014."},{"key":"59_CR19","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1007\/978-3-319-10578-9_23","volume-title":"Computer Vision\u2014ECCV 2014","author":"K. He","year":"2014","unstructured":"He, K.; Zhang, X.; Ren, S.; Sun, J. Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Computer Vision\u2014ECCV 2014. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer International Publishing, 346\u2013361, 2014."},{"key":"59_CR20","first-page":"1440","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"R. Girshick","year":"2015","unstructured":"Girshick, R. Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, 1440\u20131448, 2015."},{"key":"59_CR21","first-page":"1889","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A. Karpathy","year":"2014","unstructured":"Karpathy, A.; Joulin, A.; Li, F. F. F. Deep fragment embeddings for bidirectional image sentence mapping. In: Proceedings of Advances in Neural Information Processing Systems, 1889\u20131897, 2014."},{"key":"59_CR22","first-page":"1292","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"D. Elliott","year":"2013","unstructured":"Elliott, D.; Keller, F. Image description using visual dependency representations. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, 1292\u20131302, 2013."},{"key":"59_CR23","volume-title":"Reinforcement Learning: An Introduction","author":"R. S. Sutton","year":"1998","unstructured":"Sutton, R. S.; Barto, A. G. Reinforcement Learning: An Introduction. The MIT Press, 1998."},{"key":"59_CR24","first-page":"3104","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"I. Sutskever","year":"2014","unstructured":"Sutskever, I.; Vinyals, O.; Le, Q. V. Sequence to sequence learning with neural networks. In: Proceedings of Advances in Neural Information Processing Systems, 3104\u20133112, 2014."},{"key":"59_CR25","volume-title":"Generating sequences with recurrent neural networks","author":"A. Graves","year":"2013","unstructured":"Graves, A. Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850, 2013."},{"key":"59_CR26","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P. Young","year":"2014","unstructured":"Young, P.; Lai, A.; Hodosh, M.; Hockenmaier, J. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics Vol. 2, 67\u201378, 2014.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"59_CR27","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision\u2014ECCV 2014","author":"T.-Y. Lin","year":"2014","unstructured":"Lin, T.-Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollar, P.; Zitnick, C. L. Microsoft COCO: Common objects in context. In: Computer Vision\u2014ECCV 2014. Fleet, D.; Pajdla, T.; Schiele, B.; Tuytelaars, T. Eds. Springer International Publishing, 740\u2013755, 2014."},{"key":"59_CR28","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting on Association for Computational Linguistics","author":"K. Papineni","year":"2002","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, 311\u2013318, 2002."},{"key":"59_CR29","unstructured":"Lin, C.-Y. ROUGE: A package for automatic evaluation of summaries. In: Text Summarization Branches Out: Proceedings of the ACL-04 Workshop, Vol. 8, 2004."},{"key":"59_CR30","first-page":"359","volume":"1","author":"P. Kuznetsova","year":"2012","unstructured":"Kuznetsova, P.; Ordonez, V.; Berg, A. C.; Berg, T. L.; Choi, Y. Collective generation of natural image descriptions. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, Vol. 1, 359\u2013368, 2012.","journal-title":"Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers"},{"key":"59_CR31","first-page":"4566","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"R. Vedantam","year":"2015","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, 4566\u20134575, 2015."},{"key":"59_CR32","volume-title":"Proceedings of the 9th Workshop on Statistical Machine Translation","author":"M. Denkowski","year":"2014","unstructured":"Denkowski, M.; Lavie, A. Meteor universal: Language specific translation evaluation for any target language. In: Proceedings of the 9th Workshop on Statistical Machine Translation, 2014."},{"key":"59_CR33","first-page":"1","volume-title":"Proceedings of the Workshop on Cross-Framework and Cross-Domain Parser Evaluation","author":"M.-C. Marneffe De","year":"2008","unstructured":"De Marneffe, M.-C.; Manning, C. D. The Stanford typed dependencies representation. In: Proceedings of the Workshop on Cross-Framework and Cross-Domain Parser Evaluation, 1\u20138, 2008."}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41095-016-0059-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/10897369\/10897377.pdf?arnumber=10897377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:38:17Z","timestamp":1762367897000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10897377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":33,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1007\/s41095-016-0059-z","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}