{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T23:55:35Z","timestamp":1784246135260,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108004"],"award-info":[{"award-number":["2020AAA0108004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2020J06001, 2021J01003"],"award-info":[{"award-number":["2020J06001, 2021J01003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276219"],"award-info":[{"award-number":["62276219"]}],"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":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612413","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"3897-3907","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9654-6792","authenticated-orcid":false,"given":"Yifan","family":"Dong","sequence":"first","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1010-1890","authenticated-orcid":false,"given":"Suhang","family":"Wu","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8158-2377","authenticated-orcid":false,"given":"Fandong","family":"Meng","sequence":"additional","affiliation":[{"name":"Tencent WeChat AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5899-5165","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Tencent WeChat AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8677-9080","authenticated-orcid":false,"given":"Xiaoli","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0359-8821","authenticated-orcid":false,"given":"Jianxin","family":"Lin","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5606-7122","authenticated-orcid":false,"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Neural Language Modeling with Visual Features. CoRR","author":"Anastasopoulos Antonios","year":"2019","unstructured":"Antonios Anastasopoulos, Shankar Kumar, and Hank Liao. 2019. Neural Language Modeling with Visual Features. CoRR, Vol. abs\/1903.02930 (2019). showeprint[arXiv]1903.02930 http:\/\/arxiv.org\/abs\/1903.02930"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_3_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_80"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1439"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1292"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.103"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016268"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.121"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.02098"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2008.05.002"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI 2016","author":"Gong Yuyun","year":"2016","unstructured":"Yuyun Gong and Qi Zhang. 2016. Hashtag Recommendation Using Attention-Based Convolutional Neural Network. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI 2016, New York, NY, USA, 9-15 July 2016, Subbarao Kambhampati (Ed.). IJCAI\/AAAI Press, 2782--2788. http:\/\/www.ijcai.org\/Abstract\/16\/395"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1154"},{"key":"e_1_3_2_1_16_1","volume-title":"Exploiting Pseudo Image Captions for Multimodal Summarization. In Findings of the Association for Computational Linguistics: ACL 2023","author":"Jiang Chaoya","year":"2023","unstructured":"Chaoya Jiang, Rui Xie, Wei Ye, Jinan Sun, and Shikun Zhang. 2023. Exploiting Pseudo Image Captions for Multimodal Summarization. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Computational Linguistics, 161--175. https:\/\/aclanthology.org\/2023.findings-acl.12"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"e_1_3_2_1_18_1","volume-title":"BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2023","author":"Kang Liyan","year":"2023","unstructured":"Liyan Kang, Luyang Huang, Ningxin Peng, Peihao Zhu, Zewei Sun, Shanbo Cheng, Mingxuan Wang, Degen Huang, and Jinsong Su. 2023. BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki (Eds.). Association for Computational Linguistics, 8456--8473. https:\/\/aclanthology.org\/2023.findings-acl.535"},{"key":"e_1_3_2_1_19_1","volume-title":"Bilinear Attention Networks. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018","author":"Kim Jin-Hwa","year":"2018","unstructured":"Jin-Hwa Kim, Jaehyun Jun, and Byoung-Tak Zhang. 2018. Bilinear Attention Networks. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montr\u00e9al, Canada. 1571--1581. https:\/\/proceedings.neurips.cc\/paper\/2018\/hash\/96ea64f3a1aa2fd00c72faacf0cb8ac9-Abstract.html"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"5594","author":"Kim Wonjae","year":"2021","unstructured":"Wonjae Kim, Bokyung Son, and Ildoo Kim. 2021. ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 5583--5594. http:\/\/proceedings.mlr.press\/v139\/kim21k.html"},{"key":"e_1_3_2_1_21_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.192"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.165"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413715"},{"key":"e_1_3_2_1_25_1","volume-title":"Progressive Neural Architecture Search. CoRR","author":"Liu Chenxi","year":"2017","unstructured":"Chenxi Liu, Barret Zoph, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan L. Yuille, Jonathan Huang, and Kevin Murphy. 2017. Progressive Neural Architecture Search. CoRR, Vol. abs\/1712.00559 (2017). showeprint[arXiv]1712.00559 http:\/\/arxiv.org\/abs\/1712.00559"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17--1054"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.232"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14--1162"},{"key":"e_1_3_2_1_30_1","volume-title":"Efficient Progressive Neural Architecture Search. In British Machine Vision Conference 2018, BMVC 2018","author":"Juan-Manuel P\u00e9","year":"2018","unstructured":"Juan-Manuel P\u00e9 rez-R\u00fa a, Moez Baccouche, and St\u00e9 phane Pateux. 2018. Efficient Progressive Neural Architecture Search. In British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, September 3-6, 2018. BMVA Press, 150. http:\/\/bmvc2018.org\/contents\/papers\/0291.pdf"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00713"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/0306--4573(88)90021-0"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609452"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17--1099"},{"key":"e_1_3_2_1_35_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.024"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.168"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17633"},{"key":"e_1_3_2_1_41_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA. 5998--6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19--1240"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.268"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103382"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.491"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.354"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea","author":"Ye Junjie","year":"2022","unstructured":"Junjie Ye, Junjun Guo, Yan Xiang, Kaiwen Tan, and Zhengtao Yu. 2022. Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation. In Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, Gyeongju, Republic of Korea, October 12-17, 2022. International Committee on Computational Linguistics, 5098--5108. https:\/\/aclanthology.org\/2022.coling-1.452"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/622"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.710"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1351"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/478"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015805"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/NER49283.2021.9441352"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612413","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:02:36Z","timestamp":1755820956000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":55,"alternative-id":["10.1145\/3581783.3612413","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612413","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}