{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T23:02:13Z","timestamp":1793314933279,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":95,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681011","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T02:59:33Z","timestamp":1729911573000},"page":"7444-7453","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["AesMamba: Universal Image Aesthetic Assessment with State Space Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-0975","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"first","affiliation":[{"name":"Xidian University, Xian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0328-9626","authenticated-orcid":false,"given":"Yuhao","family":"Lin","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1915-6229","authenticated-orcid":false,"given":"Jiaqi","family":"Shi","sequence":"additional","affiliation":[{"name":"Xidian University, Xian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0990-5506","authenticated-orcid":false,"given":"Maoying","family":"Qiao","sequence":"additional","affiliation":[{"name":"The University of Technology, Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1435-489X","authenticated-orcid":false,"given":"Nannan","family":"Wang","sequence":"additional","affiliation":[{"name":"Xidian University, Xian, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-16178-5_1"},{"key":"e_1_3_2_1_2_1","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao Hangbo","year":"2022","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, Songhao Piao, and Furu Wei. 2022. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. NeurIPS, Vol. 35 (2022), 32897--32912.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_3_1","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. Advances in Neural Information Processing Systems, Vol. 33 (2020), 1877--1901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3191853"},{"key":"e_1_3_2_1_5_1","volume-title":"Image Aesthetics Assessment with Emotion-Aware Multi-Branch Network","author":"Chen Hangwei","year":"2024","unstructured":"Hangwei Chen, Feng Shao, Baoyang Mu, and Qiuping Jiang. 2024. Image Aesthetics Assessment with Emotion-Aware Multi-Branch Network. IEEE Transactions on Instrumentation and Measurement (2024)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01412"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.10.011"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_23"},{"key":"e_1_3_2_1_9_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995467"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Learning Representations. 1--9.","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, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. 1--9."},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Learning Representations. 1--22","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. 1--22."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00556"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956162"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26395"},{"key":"e_1_3_2_1_17_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. 2023. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023), 1--37."},{"key":"e_1_3_2_1_18_1","first-page":"35971","article-title":"On the parameterization and initialization of diagonal state space models","volume":"35","author":"Gu Albert","year":"2022","unstructured":"Albert Gu, Karan Goel, Ankit Gupta, and Christopher R\u00e9. 2022. On the parameterization and initialization of diagonal state space models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 35971--35983.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_19_1","volume-title":"Efficiently Modeling Long Sequences with Structured State Spaces. In International Conference on Learning Representations.","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Karan Goel, and Christopher Re. 2021. Efficiently Modeling Long Sequences with Structured State Spaces. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_20_1","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state space layers","volume":"34","author":"Gu Albert","year":"2021","unstructured":"Albert Gu, Isys Johnson, Karan Goel, Khaled Saab, Tri Dao, Atri Rudra, and Christopher R\u00e9. 2021. Combining recurrent, convolutional, and continuous-time models with linear state space layers. Advances in Neural Information Processing Systems, Vol. 34 (2021), 572--585.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","first-page":"22982","article-title":"Diagonal state spaces are as effective as structured state spaces","volume":"35","author":"Gupta Ankit","year":"2022","unstructured":"Ankit Gupta, Albert Gu, and Jonathan Berant. 2022. Diagonal state spaces are as effective as structured state spaces. Advances in Neural Information Processing Systems, Vol. 35 (2022), 22982--22994.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01996"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/132"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00960"},{"key":"e_1_3_2_1_26_1","volume-title":"Towards transparent deep image aesthetics assessment with tag-based content descriptors","author":"Hou Jingwen","year":"2023","unstructured":"Jingwen Hou, Weisi Lin, Yuming Fang, Haoning Wu, Chaofeng Chen, Liang Liao, and Weide Liu. 2023. Towards transparent deep image aesthetics assessment with tag-based content descriptors. IEEE Transactions on Image Processing (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3189276"},{"key":"e_1_3_2_1_28_1","volume-title":"Localmamba: Visual state space model with windowed selective scan. arXiv preprint arXiv:2403.09338","author":"Huang Tao","year":"2024","unstructured":"Tao Huang, Xiaohuan Pei, Shan You, Fei Wang, Chen Qian, and Chang Xu. 2024. Localmamba: Visual state space model with windowed selective scan. arXiv preprint arXiv:2403.09338 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225728"},{"key":"e_1_3_2_1_30_1","volume-title":"AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception. arXiv preprint arXiv:2401.08276","author":"Huang Yipo","year":"2024","unstructured":"Yipo Huang, Quan Yuan, Xiangfei Sheng, Zhichao Yang, Haoning Wu, Pengfei Chen, Yuzhe Yang, Leida Li, and Weisi Lin. 2024. AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception. arXiv preprint arXiv:2401.08276 (2024), 1--9."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3547144"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00968"},{"key":"e_1_3_2_1_34_1","volume-title":"Adam: A method for stochastic optimization. arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_40"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3313507"},{"key":"e_1_3_2_1_37_1","first-page":"509","article-title":"Survey of Evolutionary Multitasking Optimization","volume":"34","author":"Li Hao","year":"2023","unstructured":"Hao Li, Lei Wang, Yuanqiao Zhang, Yue Wu, and Maoguo Gong. 2023. Survey of Evolutionary Multitasking Optimization. Journal of Software, Vol. 34, 2 (2023), 509--538.","journal-title":"Journal of Software"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744078_23"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859845"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3249185"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.058"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2968285"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272984"},{"key":"e_1_3_2_1_44_1","volume-title":"UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images. arXiv preprint arXiv:2311.11306","author":"Li Weijie","year":"2023","unstructured":"Weijie Li, Yitian Wan, Xingjiao Wu, Junjie Xu, and Liang He. 2023. UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images. arXiv preprint arXiv:2311.11306 (2023), 1--16."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548244"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3035065"},{"key":"e_1_3_2_1_47_1","volume-title":"Vmamba: Visual state space model. arXiv preprint arXiv:2401.10166","author":"Liu Yue","year":"2024","unstructured":"Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, Yaowei Wang, Qixiang Ye, and Yunfan Liu. 2024. Vmamba: Visual state space model. arXiv preprint arXiv:2401.10166 (2024), 1--14."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_29"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3130752"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240635"},{"key":"e_1_3_2_1_53_1","volume-title":"International Conference on Learning Representations.","author":"Mehta Harsh","year":"2023","unstructured":"Harsh Mehta, Ankit Gupta, Ashok Cutkosky, and Behnam Neyshabur. 2023. Long Range Language Modeling via Gated State Spaces. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354807"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611996"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201510"},{"key":"e_1_3_2_1_58_1","volume-title":"Efficientvmamba: Atrous selective scan for light weight visual mamba. arXiv preprint arXiv:2403.09977","author":"Pei Xiaohuan","year":"2024","unstructured":"Xiaohuan Pei, Tao Huang, and Chang Xu. 2024. Efficientvmamba: Atrous selective scan for light weight visual mamba. arXiv preprint arXiv:2403.09977 (2024)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00091"},{"key":"e_1_3_2_1_60_1","volume-title":"VL-Mamba: Exploring State Space Models for Multimodal Learning. arXiv preprint arXiv:2403.13600","author":"Qiao Yanyuan","year":"2024","unstructured":"Yanyuan Qiao, Zheng Yu, Longteng Guo, Sihan Chen, Zijia Zhao, Mingzhen Sun, Qi Wu, and Jing Liu. 2024. VL-Mamba: Exploring State Space Models for Multimodal Learning. arXiv preprint arXiv:2403.13600 (2024)."},{"key":"e_1_3_2_1_61_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al.","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In ICML. 8748--8763."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.76"},{"key":"e_1_3_2_1_63_1","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, et al. 2022. Laion-5b: An open large-scale dataset for training next generation image-text models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 25278--25294.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_1","volume-title":"Glu variants improve transformer. arXiv preprint arXiv:2002.05202","author":"Shazeer Noam","year":"2020","unstructured":"Noam Shazeer. 2020. Glu variants improve transformer. arXiv preprint arXiv:2002.05202 (2020), 1--5."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00837"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240554"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611969"},{"key":"e_1_3_2_1_68_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR). 1--14","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR). 1--14."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3349961"},{"key":"e_1_3_2_1_70_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, Vol. 27, 8 (2018), 3998--4011."},{"key":"e_1_3_2_1_71_1","first-page":"1","article-title":"Attention is all you need","volume":"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, Vol. 30 (2017), 1--11.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.5555\/3304415.3304551"},{"key":"e_1_3_2_1_73_1","unstructured":"Yonghui Wu Mike Schuster Zhifeng Chen Quoc V Le Mohammad Norouzi Wolfgang Macherey Maxim Krikun Yuan Cao Qin Gao Klaus Macherey et al. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144 (2016) 1--23."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00065"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01516"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.104044"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01924"},{"key":"e_1_3_2_1_79_1","volume-title":"Multi-level transitional contrast learning for personalized image aesthetics assessment","author":"Yang Zhichao","year":"2023","unstructured":"Zhichao Yang, Leida Li, Yuzhe Yang, Yaqian Li, and Weisi Lin. 2023. Multi-level transitional contrast learning for personalized image aesthetics assessment. IEEE Transactions on Multimedia (2023)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02144"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941778"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941778"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.046"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2911428"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985526"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12112526"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110227"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103024"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25485"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2984670"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611942"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3123468"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.11834\/jig.210211"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.3390\/math10224181"},{"key":"e_1_3_2_1_95_1","volume-title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. arXiv preprint arXiv:2401.09417","author":"Zhu Lianghui","year":"2024","unstructured":"Lianghui Zhu, Bencheng Liao, Qian Zhang, Xinlong Wang, Wenyu Liu, and Xinggang Wang. 2024. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model. arXiv preprint arXiv:2401.09417 (2024)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681011","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681011","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T21:17:36Z","timestamp":1750281456000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681011"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":95,"alternative-id":["10.1145\/3664647.3681011","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681011","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}