{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:09:52Z","timestamp":1781107792693,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T00:00:00Z","timestamp":1508716800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672523"],"award-info":[{"award-number":["61672523"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,23]]},"DOI":"10.1145\/3123266.3123366","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"1549-1557","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":66,"title":["Fluency-Guided Cross-Lingual Image Captioning"],"prefix":"10.1145","author":[{"given":"Weiyu","family":"Lan","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xirong","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,10,23]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"D. Bahdanau K. Cho and Y. Bengio. 2015. Neural machine translation by jointly learning to align and translate ICLR.  D. Bahdanau K. Cho and Y. Bengio. 2015. Neural machine translation by jointly learning to align and translate ICLR."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3013558.3013571"},{"key":"e_1_3_2_1_3_1","unstructured":"C. Callison-Burch M. Osborne and P. Koehn. 2006. Re-evaluation the Role of Bleu in Machine Translation Research EACL.  C. Callison-Burch M. Osborne and P. Koehn. 2006. Re-evaluation the Role of Bleu in Machine Translation Research EACL."},{"key":"e_1_3_2_1_4_1","unstructured":"J.-S. Chang and S.-S. Lin. 2009. Improving Translation Fluency with Search-Based Decoding and a Monolingual Statistical Machine Translation Model for Automatic Post-Editing ROCLING.  J.-S. Chang and S.-S. Lin. 2009. Improving Translation Fluency with Search-Based Decoding and a Monolingual Statistical Machine Translation Model for Automatic Post-Editing ROCLING."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"D. Chen and C. Manning. 2014. A Fast and Accurate Dependency Parser using Neural Networks EMNLP.  D. Chen and C. Manning. 2014. A Fast and Accurate Dependency Parser using Neural Networks EMNLP.","DOI":"10.3115\/v1\/D14-1082"},{"key":"e_1_3_2_1_6_1","volume-title":"Meteor Universal: Language Specific Translation Evaluation for Any Target Language EACL Workshop.","author":"Denkowski M."},{"key":"e_1_3_2_1_7_1","unstructured":"C. Elkan. 2001. The Foundations of Cost-Sensitive Learning. In IJCAI.   C. Elkan. 2001. The Foundations of Cost-Sensitive Learning. In IJCAI."},{"key":"e_1_3_2_1_8_1","unstructured":"D. Elliott S. Frank and E. Hasler. 2015. Multilingual Image Description with Neural Sequence Models. arXiv preprint arXiv:1510.04709 (2015).  D. Elliott S. Frank and E. Hasler. 2015. Multilingual Image Description with Neural Sequence Models. arXiv preprint arXiv:1510.04709 (2015)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"H. Fang S. Gupta F. Iandola R. Srivastava L. Deng P. Dollar J. Gao X. He M. Mitchell J. Platt L. Zitnick and G. Zweig. 2015. From Captions to Visual Concepts and Back. In CVPR.  H. Fang S. Gupta F. Iandola R. Srivastava L. Deng P. Dollar J. Gao X. He M. Mitchell J. Platt L. Zitnick and G. Zweig. 2015. From Captions to Visual Concepts and Back. In CVPR.","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"A. Farhadi M. Hejrati M. Sadeghi P. Young C. Rashtchian J. Hockenmaier and D. Forsyth. 2010. Every picture tells a story: Generating sentences from images ECCV.   A. Farhadi M. Hejrati M. Sadeghi P. Young C. Rashtchian J. Hockenmaier and D. Forsyth. 2010. Every picture tells a story: Generating sentences from images ECCV.","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"e_1_3_2_1_11_1","unstructured":"A. Frome G. Corrado J. Shlens S. Bengio J. Dean M. Ranzato and T. Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model NIPS.   A. Frome G. Corrado J. Shlens S. Bengio J. Dean M. Ranzato and T. Mikolov. 2013. DeViSE: A Deep Visual-Semantic Embedding Model NIPS."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"A. Fukui D. H. Park D. Yang A. Rohrbach T. Darrell and M. Rohrbach. 2016. Multimodal compact bilinear pooling for visual question answering and visual grounding EMNLP.  A. Fukui D. H. Park D. Yang A. Rohrbach T. Darrell and M. Rohrbach. 2016. Multimodal compact bilinear pooling for visual question answering and visual grounding EMNLP.","DOI":"10.18653\/v1\/D16-1044"},{"key":"e_1_3_2_1_13_1","unstructured":"H. Gao J. Mao J. Zhou Z. Huang L. Wang and W. Xu. 2015. Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering NIPS.   H. Gao J. Mao J. Zhou Z. Huang L. Wang and W. Xu. 2015. Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question Answering NIPS."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"K. He X. Zhang S. Ren and J. Sun. 2016. Deep residual learning for image recognition. In CVPR.  K. He X. Zhang S. Ren and J. Sun. 2016. Deep residual learning for image recognition. In CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566993"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1025510524115"},{"key":"e_1_3_2_1_18_1","unstructured":"Y. Jia M. Salzmann and T. Darrell. 2011. Learning cross-modality similarity for multinomial data ICCV.  Y. Jia M. Salzmann and T. Darrell. 2011. Learning cross-modality similarity for multinomial data ICCV."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984070"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"A. Karpathy and L. Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions CVPR.  A. Karpathy and L. Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions CVPR.","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_21_1","volume-title":"Adam: A method for stochastic optimization. In ICLR.","author":"Kingma D.","year":"2015"},{"key":"e_1_3_2_1_22_1","unstructured":"R. Kiros R. Salakhutdinov and R. S. Zemel. 2015. Unifying visual-semantic embeddings with multimodal neural language models. TACL (2015).  R. Kiros R. Salakhutdinov and R. S. Zemel. 2015. Unifying visual-semantic embeddings with multimodal neural language models. TACL (2015)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912049"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984069"},{"key":"e_1_3_2_1_25_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries ACL workshop.","author":"Lin C.","year":"2004"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"T. Lin M. Maire S. Belongie J. Hays P. Perona D. Ramanan P. Doll\u00e1r and C. L. Zitnick. 2014. Microsoft coco: Common objects in context. In ECCV.  T. Lin M. Maire S. Belongie J. Hays P. Perona D. Ramanan P. Doll\u00e1r and C. L. Zitnick. 2014. Microsoft coco: Common objects in context. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_27_1","unstructured":"J. Mao W. Xu Y. Yang J. Wang Z. Huang and A. Yuille. 2015. Deep captioning with multimodal recurrent neural networks (m-rnn) ICLR.  J. Mao W. Xu Y. Yang J. Wang Z. Huang and A. Yuille. 2015. Deep captioning with multimodal recurrent neural networks (m-rnn) ICLR."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25207-0_48"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"T. Miyazaki and N. Shimizu. 2016. Cross-lingual image caption generation. In ACL.  T. Miyazaki and N. Shimizu. 2016. Cross-lingual image caption generation. In ACL.","DOI":"10.18653\/v1\/P16-1168"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"S. J Rennie E. Marcheret Y. Mroueh J. Ross and V. Goel. 2016. Self-critical Sequence Training for Image Captioning. arXiv preprint arXiv:1612.00563 (2016).  S. J Rennie E. Marcheret Y. Mroueh J. Ross and V. Goel. 2016. Self-critical Sequence Training for Image Captioning. arXiv preprint arXiv:1612.00563 (2016).","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"e_1_3_2_1_33_1","unstructured":"S. Stymne J. Tiedemann C. Hardmeier and J. Nivre. 2013. Statistical machine translation with readability constraints Nodalida.  S. Stymne J. Tiedemann C. Hardmeier and J. Nivre. 2013. Statistical machine translation with readability constraints Nodalida."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"e_1_3_2_1_35_1","volume-title":"Cider: Consensus-based image description evaluation CVPR.","author":"Vedantam R.","year":"2015"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"O. Vinyals A. Toshev S. Bengio and D. Erhan. 2015. Show and Tell: A Neural Image Caption Generator. CVPR.  O. Vinyals A. Toshev S. Bengio and D. Erhan. 2015. Show and Tell: A Neural Image Caption Generator. CVPR.","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964299"},{"key":"e_1_3_2_1_38_1","first-page":"35","article-title":"Cost-sensitive learning vs. sampling: Which is best for handling unbalanced classes with unequal error costs","volume":"7","author":"Weiss G.","year":"2007","journal-title":"DMIN"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Q. Wu C. Shen L. Liu A. Dick and A. van den Hengel. 2016 b. What value do explicit high level concepts have in vision to language problems? CVPR.  Q. Wu C. Shen L. Liu A. Dick and A. van den Hengel. 2016 b. What value do explicit high level concepts have in vision to language problems? CVPR.","DOI":"10.1109\/CVPR.2016.29"},{"key":"e_1_3_2_1_40_1","volume-title":"2016 a. Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. arXiv preprint arXiv:1609.08144","author":"Wu Y.","year":"2016"},{"key":"e_1_3_2_1_41_1","unstructured":"K. Xu J. Ba R. Kiros K. Cho A. Courville R. Salakhutdinov R. Zemel and Y. Bengio. 2015. Show Attend and Tell: Neural Image Caption Generation with Visual Attention ICML.   K. Xu J. Ba R. Kiros K. Cho A. Courville R. Salakhutdinov R. Zemel and Y. Bengio. 2015. Show Attend and Tell: Neural Image Caption Generation with Visual Attention ICML."},{"key":"e_1_3_2_1_42_1","unstructured":"T. Yao Y. Pan Y. Li Z. Qiu and T. Mei. 2016. Boosting image captioning with attributes. arXiv preprint arXiv:1611.01646 (2016).  T. Yao Y. Pan Y. Li Z. Qiu and T. Mei. 2016. Boosting image captioning with attributes. arXiv preprint arXiv:1611.01646 (2016)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00105"}],"event":{"name":"MM '17: ACM Multimedia Conference","location":"Mountain View California USA","acronym":"MM '17","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123366","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:14:03Z","timestamp":1750212843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123366"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,23]]},"references-count":44,"alternative-id":["10.1145\/3123266.3123366","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3123366","relation":{},"subject":[],"published":{"date-parts":[[2017,10,23]]},"assertion":[{"value":"2017-10-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}