{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T17:49:29Z","timestamp":1776707369203,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T00:00:00Z","timestamp":1686528000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2020AAA0107703"],"award-info":[{"award-number":["2020AAA0107703"]}]},{"name":"Research Initiation Project of Zhejiang Lab","award":["2022PD0AC02"],"award-info":[{"award-number":["2022PD0AC02"]}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["2022NSFSC0552"],"award-info":[{"award-number":["2022NSFSC0552"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006165"],"award-info":[{"award-number":["62006165"]}],"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":[[2023,6,12]]},"DOI":"10.1145\/3591106.3592257","type":"proceedings-article","created":{"date-parts":[[2023,6,8]],"date-time":"2023-06-08T22:33:38Z","timestamp":1686263618000},"page":"105-114","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Edge Enhanced Image Style Transfer via Transformers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5934-5837","authenticated-orcid":false,"given":"Chiyu","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science, Sichuan Normal University, China and Visual Computing and Virtual Reality Key Laboratory of Sichuan Provience, Sichuan Normal University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0838-6318","authenticated-orcid":false,"given":"Zaiyan","family":"Dai","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan Normal University, China and Zhejiang Lab, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6946-9181","authenticated-orcid":false,"given":"Peng","family":"Cao","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan Normal University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0971-6593","authenticated-orcid":false,"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan Normal University, China and Visual Computing and Virtual Reality Key Laboratory of Sichuan Provience, Sichuan Normal University, China"}]}],"member":"320","published-online":{"date-parts":[[2023,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00092"},{"key":"e_1_3_2_1_2_1","volume-title":"Real-time universal style transfer on high-resolution images via zero-channel pruning. arXiv preprint arXiv:2006.09029","author":"An Jie","year":"2020","unstructured":"Jie An, Tao Li, Haozhi Huang, Li Shen, Xuan Wang, Yongyi Tang, Jinwen Ma, Wei Liu, and Jiebo Luo. 2020. Real-time universal style transfer on high-resolution images via zero-channel pruning. arXiv preprint arXiv:2006.09029 (2020)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6614"},{"key":"e_1_3_2_1_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)."},{"key":"e_1_3_2_1_5_1","volume-title":"Toward transformer-based object detection. arXiv preprint arXiv:2012.09958","author":"Beal Josh","year":"2020","unstructured":"Josh Beal, Eric Kim, Eric Tzeng, Dong\u00a0Huk Park, Andrew Zhai, and Dmitry Kislyuk. 2020. Toward transformer-based object detection. arXiv preprint arXiv:2012.09958 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Style transfer functions for illustrative","author":"Bruckner Stefan","unstructured":"Stefan Bruckner and M\u00a0Eduard Gr\u00f6ller. 2007. Style transfer functions for illustrative volume rendering. In Computer Graphics Forum, Vol.\u00a026. Wiley Online Library, 715\u2013724."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.296"},{"key":"e_1_3_2_1_10_1","first-page":"26561","article-title":"Artistic style transfer with internal-external learning and contrastive learning","volume":"34","author":"Chen Haibo","year":"2021","unstructured":"Haibo Chen, Zhizhong Wang, Huiming Zhang, Zhiwen Zuo, Ailin Li, Wei Xing, Dongming Lu, 2021. Artistic style transfer with internal-external learning and contrastive learning. Advances in Neural Information Processing Systems 34 (2021), 26561\u201326573.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","volume-title":"Fast patch-based style transfer of arbitrary style. arXiv preprint arXiv:1612.04337","author":"Chen Tian\u00a0Qi","year":"2016","unstructured":"Tian\u00a0Qi Chen and Mark Schmidt. 2016. Fast patch-based style transfer of arbitrary style. arXiv preprint arXiv:1612.04337 (2016)."},{"key":"e_1_3_2_1_12_1","volume-title":"Do we really need explicit position encodings for vision transformers. arXiv preprint arXiv:2102.10882 3, 8","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu, Bo Zhang, Zhi Tian, Xiaolin Wei, and Huaxia Xia. 2021. Do we really need explicit position encodings for vision transformers. arXiv preprint arXiv:2102.10882 3, 8 (2021)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16208"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01104"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414015"},{"key":"e_1_3_2_1_17_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_18_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_19_1","volume-title":"A learned representation for artistic style. arXiv preprint arXiv:1610.07629","author":"Dumoulin Vincent","year":"2016","unstructured":"Vincent Dumoulin, Jonathon Shlens, and Manjunath Kudlur. 2016. A learned representation for artistic style. arXiv preprint arXiv:1610.07629 (2016)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383296"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"e_1_3_2_1_22_1","volume-title":"Texture synthesis using convolutional neural networks. Advances in neural information processing systems 28","author":"Gatys Leon","year":"2015","unstructured":"Leon Gatys, Alexander\u00a0S Ecker, and Matthias Bethge. 2015. Texture synthesis using convolutional neural networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_23_1","volume-title":"Preserving color in neural artistic style transfer. arXiv preprint arXiv:1606.05897","author":"Gatys A","year":"2016","unstructured":"Leon\u00a0A Gatys, Matthias Bethge, Aaron Hertzmann, and Eli Shechtman. 2016. Preserving color in neural artistic style transfer. arXiv preprint arXiv:1606.05897 (2016)."},{"key":"e_1_3_2_1_24_1","volume-title":"A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576","author":"Gatys A","year":"2015","unstructured":"Leon\u00a0A Gatys, Alexander\u00a0S Ecker, and Matthias Bethge. 2015. A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00858"},{"key":"e_1_3_2_1_28_1","first-page":"15908","article-title":"Transformer in transformer","volume":"34","author":"Han Kai","year":"2021","unstructured":"Kai Han, An Xiao, Enhua Wu, Jianyuan Guo, Chunjing Xu, and Yunhe Wang. 2021. Transformer in transformer. Advances in Neural Information Processing Systems 34 (2021), 15908\u201315919.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"e_1_3_2_1_30_1","volume-title":"Transgan: Two transformers can make one strong gan. arXiv preprint arXiv:2102.07074 1, 3","author":"Jiang Yifan","year":"2021","unstructured":"Yifan Jiang, Shiyu Chang, and Zhangyang Wang. 2021. Transgan: Two transformers can make one strong gan. arXiv preprint arXiv:2102.07074 1, 3 (2021)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5862"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"e_1_3_2_1_33_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_34_1","volume-title":"Vitgan: Training gans with vision transformers. arXiv preprint arXiv:2107.04589","author":"Lee Kwonjoon","year":"2021","unstructured":"Kwonjoon Lee, Huiwen Chang, Lu Jiang, Han Zhang, Zhuowen Tu, and Ce Liu. 2021. Vitgan: Training gans with vision transformers. arXiv preprint arXiv:2107.04589 (2021)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_43"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123425"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00393"},{"key":"e_1_3_2_1_38_1","volume-title":"Universal style transfer via feature transforms. Advances in neural information processing systems 30","author":"Li Yijun","year":"2017","unstructured":"Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, and Ming-Hsuan Yang. 2017. Universal style transfer via feature transforms. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_28"},{"key":"e_1_3_2_1_40_1","volume-title":"Demystifying neural style transfer. arXiv preprint arXiv:1701.01036","author":"Li Yanghao","year":"2017","unstructured":"Yanghao Li, Naiyan Wang, Jiaying Liu, and Xiaodi Hou. 2017. Demystifying neural style transfer. arXiv preprint arXiv:1701.01036 (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"Improved multiscale vision transformers for classification and detection. arXiv preprint arXiv:2112.01526","author":"Li Yanghao","year":"2021","unstructured":"Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, and Christoph Feichtenhofer. 2021. Improved multiscale vision transformers for classification and detection. arXiv preprint arXiv:2112.01526 (2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Kaiming He, and Ross Girshick.","author":"Li Yanghao","year":"2021","unstructured":"Yanghao Li, Saining Xie, Xinlei Chen, Piotr Dollar, Kaiming He, and Ross Girshick. 2021. Benchmarking detection transfer learning with vision transformers. arXiv preprint arXiv:2111.11429 (2021)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450525"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00510"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00658"},{"key":"e_1_3_2_1_47_1","volume-title":"Geometric style transfer. arXiv preprint arXiv:2007.05471","author":"Liu Xiao-Chang","year":"2020","unstructured":"Xiao-Chang Liu, Xuan-Yi Li, Ming-Ming Cheng, and Peter Hall. 2020. Geometric style transfer. arXiv preprint arXiv:2007.05471 (2020)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_50_1","volume-title":"Transformer-Based Neural Texture Synthesis and Style Transfer. In 2022 4th Asia Pacific Information Technology Conference. 88\u201395","author":"Lu Jiahao","year":"2022","unstructured":"Jiahao Lu. 2022. Transformer-Based Neural Texture Synthesis and Style Transfer. In 2022 4th Asia Pacific Information Technology Conference. 88\u201395."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00605"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00603"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.2308\/iace-50038"},{"key":"e_1_3_2_1_54_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_55_1","volume-title":"Stable and controllable neural texture synthesis and style transfer using histogram losses. arXiv preprint arXiv:1701.08893","author":"Risser Eric","year":"2017","unstructured":"Eric Risser, Pierre Wilmot, and Connelly Barnes. 2017. Stable and controllable neural texture synthesis and style transfer using histogram losses. arXiv preprint arXiv:1701.08893 (2017)."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00860"},{"key":"e_1_3_2_1_57_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01383"},{"key":"e_1_3_2_1_59_1","volume-title":"International Conference on Machine Learning. PMLR, 10347\u201310357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning. PMLR, 10347\u201310357."},{"key":"e_1_3_2_1_60_1","volume-title":"Maxvit: Multi-axis vision transformer. arXiv preprint arXiv:2204.01697","author":"Tu Zhengzhong","year":"2022","unstructured":"Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, and Yinxiao Li. 2022. Maxvit: Multi-axis vision transformer. arXiv preprint arXiv:2204.01697 (2022)."},{"key":"e_1_3_2_1_61_1","volume-title":"Texture networks: Feed-forward synthesis of textures and stylized images. arXiv preprint arXiv:1603.03417","author":"Ulyanov Dmitry","year":"2016","unstructured":"Dmitry Ulyanov, Vadim Lebedev, Andrea Vedaldi, and Victor Lempitsky. 2016. Texture networks: Feed-forward synthesis of textures and stylized images. arXiv preprint arXiv:1603.03417 (2016)."},{"key":"e_1_3_2_1_62_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)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.437"},{"key":"e_1_3_2_1_64_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00193"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00781"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01435"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6914"},{"key":"e_1_3_2_1_71_1","volume-title":"International Conference on Machine Learning. PMLR, 10524\u201310533","author":"Xiong Ruibin","year":"2020","unstructured":"Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, and Tieyan Liu. 2020. On layer normalization in the transformer architecture. In International Conference on Machine Learning. PMLR, 10524\u201310533."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00156"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"e_1_3_2_1_75_1","volume-title":"S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention. arXiv preprint arXiv:2210.12381","author":"Zhang Chiyu","year":"2022","unstructured":"Chiyu Zhang, Jun Yang, Lei Wang, and Zaiyan Dai. 2022. S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention. arXiv preprint arXiv:2210.12381 (2022)."},{"key":"e_1_3_2_1_76_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0\u20130.","author":"Zhang Hang","year":"2018","unstructured":"Hang Zhang and Kristin Dana. 2018. Multi-style generative network for real-time transfer. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops. 0\u20130."},{"key":"e_1_3_2_1_77_1","volume-title":"Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning. arXiv preprint arXiv:2205.09542","author":"Zhang Yuxin","year":"2022","unstructured":"Yuxin Zhang, Fan Tang, Weiming Dong, Haibin Huang, Chongyang Ma, Tong-Yee Lee, and Changsheng Xu. 2022. Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning. arXiv preprint arXiv:2205.09542 (2022)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"e_1_3_2_1_79_1","volume-title":"Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159","author":"Zhu Xizhou","year":"2020","unstructured":"Xizhou Zhu, Weijie Su, Lewei Lu, Bin Li, Xiaogang Wang, and Jifeng Dai. 2020. Deformable detr: Deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)."}],"event":{"name":"ICMR '23: International Conference on Multimedia Retrieval","location":"Thessaloniki Greece","acronym":"ICMR '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2023 ACM International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592257","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3591106.3592257","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:30Z","timestamp":1750178250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3591106.3592257"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,12]]},"references-count":79,"alternative-id":["10.1145\/3591106.3592257","10.1145\/3591106"],"URL":"https:\/\/doi.org\/10.1145\/3591106.3592257","relation":{},"subject":[],"published":{"date-parts":[[2023,6,12]]},"assertion":[{"value":"2023-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}