{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:40:48Z","timestamp":1755826848431,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China under Grants","award":["U1706218"],"award-info":[{"award-number":["U1706218"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658068","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"220-228","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Soft Labeling for Visual Semantic Embedding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2243-5933","authenticated-orcid":false,"given":"Jiaao","family":"Yu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7253-7614","authenticated-orcid":false,"given":"Yunlai","family":"Ding","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7012-2087","authenticated-orcid":false,"given":"Junyu","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China & Sanya Oceanographic Institution, Ocean University of China, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9299-1945","authenticated-orcid":false,"given":"Yuezun","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Ocean University of China, Qingdao, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_33"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"e_1_3_2_1_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_8_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)."},{"key":"e_1_3_2_1_9_1","volume-title":"Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097","author":"Fang Han","year":"2021","unstructured":"Han Fang, Pengfei Xiong, Luhui Xu, and Yu Chen. 2021. Clip2video: Mastering video-text retrieval via image clip. arXiv preprint arXiv:2106.11097 (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. 2013. Devise: A deep visual-semantic embedding model. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"e_1_3_2_1_12_1","volume-title":"Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_13_1","volume-title":"Learning Semantic Concepts and Order for Image and Sentence Matching. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Huang Yan","year":"2018","unstructured":"Yan Huang, Qi Wu, Chunfeng Song, and Liang Wang. 2018. Learning Semantic Concepts and Order for Image and Sentence Matching. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108354"},{"key":"e_1_3_2_1_15_1","unstructured":"Diederik P Kingma. 2014. A method for stochastic optimization. ArXiv Prepr(2014)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David A Shamma et al. 2017. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision 123 (2017) 32--73.","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"e_1_3_2_1_20_1","volume-title":"Image-Text Retrieval with Binary and Continuous Label Supervision. arXiv preprint arXiv:2210.11319","author":"Li Zheng","year":"2022","unstructured":"Zheng Li, Caili Guo, Zerun Feng, Jenq-Neng Hwang, Ying Jin, and Yufeng Zhang. 2022. Image-Text Retrieval with Binary and Continuous Label Supervision. arXiv preprint arXiv:2210.11319 (2022)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022","author":"Li Zheng","year":"2022","unstructured":"Zheng Li, Caili Guo, Zerun Feng, Jenq-Neng Hwang, and Xijun Xue. 2022. MultiView Visual Semantic Embedding. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23--29 July 2022. IJCAI."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"e_1_3_2_1_25_1","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781(2013)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"e_1_3_2_1_28_1","volume-title":"Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)."},{"key":"e_1_3_2_1_29_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_30_1","volume-title":"Decoupled Cross-modal Phrase-Attention Network for Image-Sentence Matching","author":"Shi Zhangxiang","year":"2022","unstructured":"Zhangxiang Shi, Tianzhu Zhang, Xi Wei, Feng Wu, and Yongdong Zhang. 2022. Decoupled Cross-modal Phrase-Attention Network for Image-Sentence Matching. IEEE Transactions on Image Processing (2022)."},{"key":"e_1_3_2_1_31_1","volume-title":"Coder: Coupled diversitysensitive momentum contrastive learning for image-text retrieval. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27","author":"Wang Haoran","year":"2022","unstructured":"Haoran Wang, Dongliang He, Wenhao Wu, Boyang Xia, Min Yang, Fu Li, Yunlong Yu, Zhong Ji, Errui Ding, and Jingdong Wang. 2022. Coder: Coupled diversitysensitive momentum contrastive learning for image-text retrieval. In Computer Vision--ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXXVI. Springer, 700--716."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings, Part XXIV 16","author":"Wang Haoran","year":"2020","unstructured":"Haoran Wang, Ying Zhang, Zhong Ji, Yanwei Pang, and Lin Ma. 2020. Consensusaware visual-semantic embedding for image-text matching. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXIV 16. Springer, 18--34."},{"key":"e_1_3_2_1_33_1","volume-title":"Fvqa: Fact-based visual question answering","author":"Wang Peng","year":"2017","unstructured":"Peng Wang, Qi Wu, Chunhua Shen, Anthony Dick, and Anton Van Den Hengel. 2017. Fvqa: Fact-based visual question answering. IEEE transactions on pattern analysis and machine intelligence 40, 10 (2017), 2413--2427."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00590"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350940"},{"key":"e_1_3_2_1_37_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."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7006"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Phuket Thailand","acronym":"ICMR '24"},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658068","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:51:38Z","timestamp":1755766298000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":39,"alternative-id":["10.1145\/3652583.3658068","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658068","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}