{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:42:33Z","timestamp":1774021353602,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":63,"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":[{"name":"the National Key R&D Program of China","award":["2022ZD0161501"],"award-info":[{"award-number":["2022ZD0161501"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611918","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T19:52:54Z","timestamp":1698436374000},"page":"2427-2436","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Neural Image Popularity Assessment with Retrieval-augmented Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1587-7772","authenticated-orcid":false,"given":"Liya","family":"Ji","sequence":"first","affiliation":[{"name":"HKUST, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6679-4961","authenticated-orcid":false,"given":"Chan Ho","family":"Park","sequence":"additional","affiliation":[{"name":"HKUST, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9579-8665","authenticated-orcid":false,"given":"Zhefan","family":"Rao","sequence":"additional","affiliation":[{"name":"HKUST, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2199-3948","authenticated-orcid":false,"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST, Hong Kong, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3036690"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018","author":"Bhat Shariq Farooq","year":"2021","unstructured":"Shariq Farooq Bhat, Ibraheem Alhashim, and PeterWonka. 2021. Adabins: Depth estimation using adaptive bins. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018."},{"key":"e_1_3_2_1_3_1","unstructured":"Andreas Blattmann Robin Rombach Kaan Oktay Jonas M\u00fcller and Bj\u00f6rn Ommer. 2022. Semi-Parametric Neural Image Synthesis. In Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2507824"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371834"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551568"},{"key":"e_1_3_2_1_7_1","volume-title":"Block Popularity Prediction for Multimedia Storage Systems Using Spatial-Temporal-Sequential Neural Networks. In MM '21: ACM Multimedia Conference","author":"Cheng Yingying","year":"2021","unstructured":"Yingying Cheng, Fan Zhang, Gang Hu, Yiwen Wang, Hanhui Yang, Gong Zhang, and Zhuo Cheng. 2021. Block Popularity Prediction for Multimedia Storage Systems Using Spatial-Temporal-Sequential Neural Networks. In MM '21: ACM Multimedia Conference, Virtual Event, China, October 20 - 24, 2021, Heng Tao Shen, Yueting Zhuang, John R. Smith, Yang Yang, Pablo C\u00e9sar, Florian Metze, and Balakrishnan Prabhakaran (Eds.). ACM, 3390--3398. https:\/\/doi.org\/10.1145\/ 3474085.3475495"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475605"},{"key":"e_1_3_2_1_10_1","volume-title":"Locally Adaptive Structure and Texture Similarity for Image Quality Assessment. CoRR abs\/2110.08521","author":"Ding Keyan","year":"2021","unstructured":"Keyan Ding, Yi Liu, Xueyi Zou, Shiqi Wang, and Kede Ma. 2021. Locally Adaptive Structure and Texture Similarity for Image Quality Assessment. CoRR abs\/2110.08521 (2021). arXiv:2110.08521 https:\/\/arxiv.org\/abs\/2110.08521"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351007"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356062"},{"key":"e_1_3_2_1_13_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 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_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547872"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806361"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351081"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356054"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356064"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551593"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356064"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2910017.2910620"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356060"},{"key":"e_1_3_2_1_27_1","volume-title":"MUSIQ: Multi-scale Image Quality Transformer. In ICCV.","author":"Ke Junjie","year":"2021","unstructured":"Junjie Ke, QifeiWang, YilinWang, Peyman Milanfar, and Feng Yang. 2021. MUSIQ: Multi-scale Image Quality Transformer. In ICCV."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.213"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380052"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416273"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548244"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475695"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548147"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3478557"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2018.00042"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"e_1_3_2_1_38_1","volume-title":"Damian Konrad Kowalczyk, and Lars Kai Hansen","author":"Riis Christoffer","year":"2020","unstructured":"Christoffer Riis, Damian Konrad Kowalczyk, and Lars Kai Hansen. 2020. On the limits to multi-modal popularity prediction on instagram-a new robust, efficient and explainable baseline. arXiv preprint arXiv:2004.12482 (2020)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2021. High-Resolution Image Synthesis with Latent Diffusion Models. arXiv:2112.10752 [cs.CV]","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_40_1","volume-title":"NIMA: Neural image assessment","author":"Talebi Hossein","year":"2018","unstructured":"Hossein Talebi and Peyman Milanfar. 2018. NIMA: Neural image assessment. IEEE transactions on image processing 27, 8 (2018), 3998--4011."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551607"},{"key":"e_1_3_2_1_42_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 N 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_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416294"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3356084"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9970"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551576"},{"key":"e_1_3_2_1_48_1","volume-title":"Memorizing transformers. arXiv preprint arXiv:2203.08913","author":"Wu Yuhuai","year":"2022","unstructured":"Yuhuai Wu, Markus N Rabe, DeLesley Hutchins, and Christian Szegedy. 2022. Memorizing transformers. arXiv preprint arXiv:2203.08913 (2022)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548032"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475705"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416272"},{"key":"e_1_3_2_1_53_1","volume-title":"Cross-modal Joint Prediction and Alignment for Composed Query Image Retrieval. In MM '21: ACM Multimedia Conference","author":"Yang Yuchen","year":"2021","unstructured":"Yuchen Yang, Min Wang, Wengang Zhou, and Houqiang Li. 2021. Cross-modal Joint Prediction and Alignment for Composed Query Image Retrieval. In MM '21: ACM Multimedia Conference, Virtual Event, China, October 20 - 24, 2021, Heng Tao Shen, Yueting Zhuang, John R. Smith, Yang Yang, Pablo C\u00e9sar, Florian Metze, and Balakrishnan Prabhakaran (Eds.). ACM, 3303--3311. https:\/\/doi.org\/10.1145\/ 3474085.3475483"},{"key":"e_1_3_2_1_54_1","volume-title":"Personalized Image Aesthetics Assessment with Rich Attributes. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022","author":"Yang Yuzhe","year":"2022","unstructured":"Yuzhe Yang, Liwu Xu, Leida Li, Nan Qie, Yaqian Li, Peng Zhang, and Yandong Guo. 2022. Personalized Image Aesthetics Assessment with Rich Attributes. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. IEEE, 19829--19837. https:\/\/doi.org\/10.1109\/ CVPR52688.2022.01924"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.15166"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17281"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416289"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548126"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186026"},{"key":"e_1_3_2_1_61_1","unstructured":"Hengshuang Zhao Jianping Shi Xiaojuan Qi XiaogangWang and Jiaya Jia. 2017. Pyramid Scene Parsing Network. In CVPR."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547982"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479234"}],"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\/3581783.3611918","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611918","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:12:29Z","timestamp":1755821549000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611918"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":63,"alternative-id":["10.1145\/3581783.3611918","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611918","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"}}]}}