{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T12:48:33Z","timestamp":1777639713575,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413877","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T13:10:44Z","timestamp":1602508244000},"page":"4190-4198","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Improving Intra- and Inter-Modality Visual Relation for Image Captioning"],"prefix":"10.1145","author":[{"given":"Yong","family":"Wang","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"WenKai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Liu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences & University of Chinese Academy of Sciences, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences & Institute of Electronics, Chinese Academy of Science, beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_2_3_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_4_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 ( 2014 ). Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie . 2005 . METEOR: An automatic metric for MT evaluation with improved correlation with human judgments . In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72 . Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018142"},{"key":"e_1_3_2_2_7_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen , Hao Fang , Tsung-Yi Lin , Ramakrishna Vedantam , Saurabh Gupta , Piotr Doll\u00e1r , and C Lawrence Zitnick . 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 ( 2015 ). Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2015. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_2_8_1","unstructured":"Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in neural information processing systems. 3844--3852.  Micha\u00ebl Defferrard Xavier Bresson and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in neural information processing systems. 3844--3852."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.412"},{"key":"e_1_3_2_2_11_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri , David J Fleet , Jamie Ryan Kiros, and Sanja Fidler . 2017 . Vse+: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017). Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. Vse+: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_13_1","volume-title":"Image Captioning: Transforming Objects into Words. In Advances in Neural Information Processing Systems. 11135--11145.","author":"Herdade Simao","year":"2019","unstructured":"Simao Herdade , Armin Kappeler , Kofi Boakye , and Joao Soares . 2019 . Image Captioning: Transforming Objects into Words. In Advances in Neural Information Processing Systems. 11135--11145. Simao Herdade, Armin Kappeler, Kofi Boakye, and Joao Soares. 2019. Image Captioning: Transforming Objects into Words. In Advances in Neural Information Processing Systems. 11135--11145."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Lun Huang Wenmin Wang Jie Chen and Xiaoyong Wei. 2019. Attention on Attention for Image Captioning. (2019) 4634--4643.  Lun Huang Wenmin Wang Jie Chen and Xiaoyong Wei. 2019. Attention on Attention for Image Captioning. (2019) 4634--4643.","DOI":"10.1109\/ICCV.2019.00473"},{"key":"e_1_3_2_2_15_1","volume-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy . 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 ( 2015 ). Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_31"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Lei Ke Wenjie Pei Ruiyu Li Xiaoyong Shen and Yuwing Tai. 2019. Reflective Decoding Network for Image Captioning. (2019) 8888--8897.  Lei Ke Wenjie Pei Ruiyu Li Xiaoyong Shen and Yuwing Tai. 2019. Reflective Decoding Network for Image Captioning. (2019) 8888--8897.","DOI":"10.1109\/ICCV.2019.00898"},{"key":"e_1_3_2_2_18_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_19_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin . 2004 . Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00754"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni , Salim Roukos , Todd Ward , and Wei-Jing Zhu . 2002 . BLEU: a method for automatic evaluation of machine translation . In Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318 . Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting on association for computational linguistics. Association for Computational Linguistics, 311--318."},{"key":"e_1_3_2_2_25_1","volume-title":"Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732","author":"Ranzato Marc'Aurelio","year":"2015","unstructured":"Marc'Aurelio Ranzato , Sumit Chopra , Michael Auli , and Wojciech Zaremba . 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 ( 2015 ). Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli, and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Amanpreet Singh Vivek Natarajan Meet Shah Yu Jiang Xinlei Chen Dhruv Batra Devi Parikh and Marcus Rohrbach. 2019. Towards vqa models that can read. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8317--8326.  Amanpreet Singh Vivek Natarajan Meet Shah Yu Jiang Xinlei Chen Dhruv Batra Devi Parikh and Marcus Rohrbach. 2019. Towards vqa models that can read. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8317--8326.","DOI":"10.1109\/CVPR.2019.00851"},{"key":"e_1_3_2_2_30_1","volume-title":"Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022","author":"Ulyanov Dmitry","year":"2016","unstructured":"Dmitry Ulyanov , Andrea Vedaldi , and Victor Lempitsky . 2016. Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 ( 2016 ). Dmitry Ulyanov, Andrea Vedaldi, and Victor Lempitsky. 2016. Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022 (2016)."},{"key":"e_1_3_2_2_31_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"e_1_3_2_2_35_1","volume-title":"International conference on machine learning. 2048--2057","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu , Jimmy Ba , Ryan Kiros , Kyunghyun Cho , Aaron Courville , Ruslan Salakhudinov , Rich Zemel , and Yoshua Bengio . 2015 . Show, attend and tell: Neural image caption generation with visual attention . In International conference on machine learning. 2048--2057 . Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. 2048--2057."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01094"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2019. Hierarchy Parsing for Image Captioning. (2019) 2621--2629.  Ting Yao Yingwei Pan Yehao Li and Tao Mei. 2019. Hierarchy Parsing for Image Captioning. (2019) 2621--2629.","DOI":"10.1109\/ICCV.2019.00271"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413877","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:18Z","timestamp":1750197678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":40,"alternative-id":["10.1145\/3394171.3413877","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413877","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}