{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:41:21Z","timestamp":1755823281100,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"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\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515011197, 2022A1515011245, 2021A1515010533"],"award-info":[{"award-number":["2023A1515011197, 2022A1515011245, 2021A1515010533"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016804","name":"Natural Science Foundation of Shenzhen City","doi-asserted-by":"publisher","award":["JCYJ20220809160139001"],"award-info":[{"award-number":["JCYJ20220809160139001"]}],"id":[{"id":"10.13039\/100016804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701310, 61902251"],"award-info":[{"award-number":["61701310, 61902251"]}],"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\/3581783.3612118","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"6765-6773","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual Redundancy Removal of Composite Images via Multimodal Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5791-8267","authenticated-orcid":false,"given":"Wuyuan","family":"Xie","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1705-8562","authenticated-orcid":false,"given":"Shukang","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1180-4783","authenticated-orcid":false,"given":"Rong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1125-9299","authenticated-orcid":false,"given":"Miaohui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2568459"},{"key":"e_1_3_2_2_2_1","volume-title":"BEiT: BERT Pre-Training of Image Transformers. In International Conference on Learning Representations (ICLR). 1469--1479","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. BEiT: BERT Pre-Training of Image Transformers. In International Conference on Learning Representations (ICLR). 1469--1479."},{"key":"e_1_3_2_2_3_1","volume-title":"Understanding News Text and Images Connection with Context-enriched Multimodal Transformers. In ACM International Conference on Multimedia (MM). 5821--5832","author":"Bartolomeu Cl\u00e1udio","year":"2022","unstructured":"Cl\u00e1udio Bartolomeu, Rui N\u00f3brega, and David Semedo. 2022. Understanding News Text and Images Connection with Context-enriched Multimodal Transformers. In ACM International Conference on Multimedia (MM). 5821--5832."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2952675"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/76.475889"},{"key":"e_1_3_2_2_6_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_2_7_1","volume-title":"AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification. In AAAI Conference on Artificial Intelligence. 4477--4485","author":"Farooq Ammarah","year":"2022","unstructured":"Ammarah Farooq, Muhammad Awais, Josef Kittler, and Syed Safwan Khalid. 2022. AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification. In AAAI Conference on Artificial Intelligence. 4477--4485."},{"key":"e_1_3_2_2_8_1","volume-title":"Multimodal Entity Linking: A New Dataset and A Baseline. In ACM International Conference on Multimedia (MM). 993--1001","author":"Gan Jingru","year":"2021","unstructured":"Jingru Gan, Jinchang Luo, Haiwei Wang, Shuhui Wang, Wei He, and Qingming Huang. 2021. Multimodal Entity Linking: A New Dataset and A Baseline. In ACM International Conference on Multimedia (MM). 993--1001."},{"key":"e_1_3_2_2_9_1","volume-title":"Momentum Contrast for Unsupervised Visual Representation Learning. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 9729--9738","author":"He Kaiming","year":"2020","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2020. Momentum Contrast for Unsupervised Visual Representation Learning. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 9729--9738."},{"key":"e_1_3_2_2_10_1","volume-title":"Hui Yong Kim, Se Yoon Jeong, and C-C Jay Kuo.","author":"Huang Qin","year":"2017","unstructured":"Qin Huang, Haiqiang Wang, Sung Chang Lim, Hui Yong Kim, Se Yoon Jeong, and C-C Jay Kuo. 2017. Measure and Prediction of HEVC Perceptually Lossy\/Lossless Boundary QP Values. In data compression conference (DCC). 42--51."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3174398"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2016.13.IQSP-222"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818439"},{"key":"e_1_3_2_2_14_1","volume-title":"Most Apparent Distortion: Full-Reference Image Quality Assessment and the Role of Strategy. SPIE Journal of electronic imaging","author":"Larson Eric Cooper","year":"2010","unstructured":"Eric Cooper Larson and Damon Michael Chandler. 2010. Most Apparent Distortion: Full-Reference Image Quality Assessment and the Role of Strategy. SPIE Journal of electronic imaging, Vol. 19, 1 (2010), 1116--1137."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2019.8743252"},{"key":"e_1_3_2_2_16_1","volume-title":"MMFL: Multimodal Fusion Learning For Text-Guided Image Inpainting. In ACM International Conference on Multimedia (MM). 1094--1102","author":"Lin Qing","year":"2020","unstructured":"Qing Lin, Bo Yan, Jichun Li, and Weimin Tan. 2020. MMFL: Multimodal Fusion Learning For Text-Guided Image Inpainting. In ACM International Conference on Multimedia (MM). 1094--1102."},{"key":"e_1_3_2_2_17_1","volume-title":"Multimodal Asymmetric Dual Learning for Unsupervised Eyeglasses Removal. In ACM International Conference on Multimedia (MM). 5092--5100","author":"Lin Qing","year":"2021","unstructured":"Qing Lin, Bo Yan, and Weimin Tan. 2021. Multimodal Asymmetric Dual Learning for Unsupervised Eyeglasses Removal. In ACM International Conference on Multimedia (MM). 5092--5100."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2010.2087432"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2933743"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIP49896.2020.9339415"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2718185"},{"key":"e_1_3_2_2_22_1","volume-title":"Ahumada Jr","author":"Peterson Heidi A.","year":"1992","unstructured":"Heidi A. Peterson and Albert J. Ahumada Jr. 1992. Luminance-Model-Based DCT Quantization for Color Image Compression. In Human Vision, Visual Processing, and Digital Display III. 365--374."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2014.10.009"},{"key":"e_1_3_2_2_24_1","volume-title":"Deepfuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs. In IEEE International Conference on Computer Vision (ICCV). 4714--4722","author":"Prabhakar K Ram","year":"2017","unstructured":"K Ram Prabhakar, V Sai Srikar, and R Venkatesh Babu. 2017. Deepfuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs. In IEEE International Conference on Computer Vision (ICCV). 4714--4722."},{"key":"e_1_3_2_2_25_1","volume-title":"LIVE Image Quality Assessment Database Release 2. URL http:\/\/live.ece.utexas.edu\/research\/quality","author":"Sheikh Hamid R","year":"2005","unstructured":"Hamid R Sheikh, Zhou Wang, Lawrence Cormack, and Alan C Bovik. 2005. LIVE Image Quality Assessment Database Release 2. URL http:\/\/live.ece.utexas.edu\/research\/quality (2005)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3029428"},{"key":"e_1_3_2_2_27_1","volume-title":"Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking. In ACM International Conference on Multimedia (MM). 2262--2270","author":"Sun Jingxian","year":"2021","unstructured":"Jingxian Sun, Lichao Zhang, Yufei Zha, Abel Gonzalez-Garcia, Peng Zhang, Wei Huang, and Yanning Zhang. 2021. Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking. In ACM International Conference on Multimedia (MM). 2262--2270."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3408320"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/WPMC.2014.7014800"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3092234"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3139895"},{"key":"e_1_3_2_2_33_1","first-page":"3838","article-title":"Just Noticeable Difference Estimation for Screen Content Images","volume":"25","author":"Wang Shiqi","year":"2016","unstructured":"Shiqi Wang, Lin Ma, Yuming Fang, Weisi Lin, Siwei Ma, and Wen Gao. 2016b. Just Noticeable Difference Estimation for Screen Content Images. IEEE Transactions on Image Processing, Vol. 25, 8 (2016), 3838--3851.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_2_2_34_1","volume-title":"Recovering Realistic Texture in Image Super-Resolution By Deep Spatial Feature Transform. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 606--615","author":"Wang Xintao","year":"2018","unstructured":"Xintao Wang, Ke Yu, Chao Dong, and Chen Change Loy. 2018. Recovering Realistic Texture in Image Super-Resolution By Deep Spatial Feature Transform. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 606--615."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2685682"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2279934"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548366"},{"key":"e_1_3_2_2_39_1","unstructured":"Wuyuan Xie Shukang Wang Sukun Tian Lirong Huang Ye Liu and Miaohui Wang. [n. d.]. Just Noticeable Visual Redundancy Forecasting: A Deep Multimodal-Driven Approach."},{"key":"e_1_3_2_2_40_1","volume-title":"Disentangled Representation Learning for Multimodal Emotion Recognition. In ACM International Conference on Multimedia (MM). 1642--1651","author":"Yang Dingkang","year":"2022","unstructured":"Dingkang Yang, Shuai Huang, Haopeng Kuang, Yangtao Du, and Lihua Zhang. 2022. Disentangled Representation Learning for Multimodal Emotion Recognition. In ACM International Conference on Multimedia (MM). 1642--1651."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2465145"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2005.04.001"},{"key":"e_1_3_2_2_43_1","first-page":"2635","article-title":"Feedforward and Feedback Modulations Based Foveated JND Estimation for Images","volume":"25","author":"Yin Haibing","year":"2023","unstructured":"Haibing Yin, Hongkui Wang, Li Yu, Junhui Liang, and Guangtao Zhai. 2023. Feedforward and Feedback Modulations Based Foveated JND Estimation for Images. ACM Transactions on Multimedia Computing, Communications, and Applications, Vol. 25, 1 (2023), 2635--2744.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_2_2_44_1","volume-title":"Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection. In International Conference on Learning Representations (ICLR). 1125--1134","author":"Zong Bo","year":"2018","unstructured":"Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, and Haifeng Chen. 2018. Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection. In International Conference on Learning Representations (ICLR). 1125--1134."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612118","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:59:18Z","timestamp":1755820758000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":44,"alternative-id":["10.1145\/3581783.3612118","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612118","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"}}]}}