{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:22Z","timestamp":1750309522380,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":61,"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"}],"funder":[{"name":"National Key Research and Development Program of China under Grant","award":["2022YFA1004100"],"award-info":[{"award-number":["2022YFA1004100"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276052"],"award-info":[{"award-number":["62276052"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/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":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680809","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"7123-7132","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5860-059X","authenticated-orcid":false,"given":"Jin","family":"Sun","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4934-0850","authenticated-orcid":false,"given":"Xiaoshuang","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Tsinghua University, Chengdu, SiChuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3835-4596","authenticated-orcid":false,"given":"Zhiyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4437-0671","authenticated-orcid":false,"given":"Kaidi","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Drexel University, Philadelphia, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China & Tongji University, Chengdu, SiChuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6840-0578","authenticated-orcid":false,"given":"Xiaofeng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, SiChuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Guiping Cao Shengda Luo Wenjian Huang Xiangyuan Lan Dongmei Jiang Yaowei Wang and Jianguo Zhang. 2023. Strip-MLP: Efficient Token Interaction for Vision MLP. In ICCV. 1494--1504.","DOI":"10.1109\/ICCV51070.2023.00144"},{"key":"e_1_3_2_2_2_1","volume-title":"CycleMLP: A MLP-like Architecture for Dense Visual Predictions","author":"Chen Shoufa","year":"2023","unstructured":"Shoufa Chen, Enze Xie, Chongjian Ge, Runjian Chen, Ding Liang, and Ping Luo. 2023. CycleMLP: A MLP-like Architecture for Dense Visual Predictions. IEEE TPAMI (2023)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Weijie Chen Di Xie Yuan Zhang and Shiliang Pu. 2019. All you need is a few shifts: Designing efficient convolutional neural networks for image classification. In CVPR. 7241--7250.","DOI":"10.1109\/CVPR.2019.00741"},{"key":"e_1_3_2_2_4_1","volume-title":"X-volution: On the unification of convolution and self-attention. arXiv preprint arXiv:2106.02253","author":"Chen Xuanhong","year":"2021","unstructured":"Xuanhong Chen, Hang Wang, and Bingbing Ni. 2021. X-volution: On the unification of convolution and self-attention. arXiv preprint arXiv:2106.02253 (2021)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"e_1_3_2_2_6_1","volume-title":"Randaugment: Practical automated data augmentation with a reduced search space. In CVPR. 702--703.","author":"Cubuk Ekin D","year":"2020","unstructured":"Ekin D Cubuk, Barret Zoph, Jonathon Shlens, and Quoc V Le. 2020. Randaugment: Practical automated data augmentation with a reduced search space. In CVPR. 702--703."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Jifeng Dai Haozhi Qi Yuwen Xiong Yi Li Guodong Zhang Han Hu and Yichen Wei. 2017. Deformable convolutional networks. In ICCV. 764--773.","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_3_2_2_8_1","volume-title":"Imagenet: A large-scale hierarchical image database. In CVPR. 248--255.","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In CVPR. 248--255."},{"key":"e_1_3_2_2_9_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. ICLR (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"Cognitron: A self-organizing multilayered neural network. Biological cybernetics","author":"Fukushima Kunihiko","year":"1975","unstructured":"Kunihiko Fukushima. 1975. Cognitron: A self-organizing multilayered neural network. Biological cybernetics, Vol. 20, 3--4 (1975), 121--136."},{"key":"e_1_3_2_2_11_1","volume-title":"Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics","author":"Fukushima Kunihiko","year":"1980","unstructured":"Kunihiko Fukushima. 1980. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological cybernetics, Vol. 36, 4 (1980), 193--202."},{"key":"e_1_3_2_2_12_1","volume-title":"Hire-mlp: Vision mlp via hierarchical rearrangement. In CVPR. 826--836.","author":"Guo Jianyuan","year":"2022","unstructured":"Jianyuan Guo, Yehui Tang, Kai Han, Xinghao Chen, Han Wu, Chao Xu, Chang Xu, and Yunhe Wang. 2022. Hire-mlp: Vision mlp via hierarchical rearrangement. In CVPR. 826--836."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"e_1_3_2_2_14_1","volume-title":"Escaping the big data paradigm with compact transformers. arXiv preprint arXiv:2104.05704","author":"Hassani Ali","year":"2021","unstructured":"Ali Hassani, Steven Walton, Nikhil Shah, Abulikemu Abuduweili, Jiachen Li, and Humphrey Shi. 2021. Escaping the big data paradigm with compact transformers. arXiv preprint arXiv:2104.05704 (2021)."},{"key":"e_1_3_2_2_15_1","unstructured":"Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Doll\u00e1r and Ross Girshick. 2022. Masked autoencoders are scalable vision learners. In CVPR. 16000--16009."},{"key":"e_1_3_2_2_16_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145427"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1965.28.2.229"},{"key":"e_1_3_2_2_20_1","volume-title":"Huiying Liang, Sally L Baxter, Alex McKeown, Ge Yang, Xiaokang Wu, Fangbing Yan, et al.","author":"Kermany Daniel S","year":"2018","unstructured":"Daniel S Kermany, Michael Goldbaum, Wenjia Cai, Carolina CS Valentim, Huiying Liang, Sally L Baxter, Alex McKeown, Ge Yang, Xiaokang Wu, Fangbing Yan, et al. 2018. Identifying medical diagnoses and treatable diseases by image-based deep learning. cell, Vol. 172, 5 (2018), 1122--1131."},{"key":"e_1_3_2_2_21_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. Citeseer Tech. Rep. (2009)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_2_2_23_1","volume-title":"1989 b. Generalization and network design strategies. Connectionism in perspective","author":"LeCun Yann","year":"1989","unstructured":"Yann LeCun et al. 1989 b. Generalization and network design strategies. Connectionism in perspective, Vol. 19, 143--155 (1989), 18."},{"key":"e_1_3_2_2_24_1","volume-title":"1989 a. Backpropagation applied to handwritten zip code recognition. Neural computation","author":"LeCun Yann","year":"1989","unstructured":"Yann LeCun, Bernhard Boser, John S Denker, Donnie Henderson, Richard E Howard, Wayne Hubbard, and Lawrence D Jackel. 1989 a. Backpropagation applied to handwritten zip code recognition. Neural computation, Vol. 1, 4 (1989), 541--551."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_2_26_1","volume-title":"Simon See, Xiaogang Wang, Hongwei Qin, and Hongsheng Li.","author":"Li Dasong","year":"2023","unstructured":"Dasong Li, Xiaoyu Shi, Yi Zhang, Ka Chun Cheung, Simon See, Xiaogang Wang, Hongwei Qin, and Hongsheng Li. 2023. A simple baseline for video restoration with grouped spatial-temporal shift. In CVPR. 9822--9832."},{"key":"e_1_3_2_2_27_1","volume-title":"Convmlp: Hierarchical convolutional mlps for vision. In CVPR. 6306--6315.","author":"Li Jiachen","year":"2023","unstructured":"Jiachen Li, Ali Hassani, Steven Walton, and Humphrey Shi. 2023. Convmlp: Hierarchical convolutional mlps for vision. In CVPR. 6306--6315."},{"key":"e_1_3_2_2_28_1","volume-title":"Moganet: Multi-order gated aggregation network. In ICLR.","author":"Li Siyuan","year":"2023","unstructured":"Siyuan Li, Zedong Wang, Zicheng Liu, Cheng Tan, Haitao Lin, Di Wu, Zhiyuan Chen, Jiangbin Zheng, and Stan Z Li. 2023. Moganet: Multi-order gated aggregation network. In ICLR."},{"key":"e_1_3_2_2_29_1","volume-title":"As-mlp: An axial shifted mlp architecture for vision. arXiv preprint arXiv:2107.08391","author":"Lian Dongze","year":"2021","unstructured":"Dongze Lian, Zehao Yu, Xing Sun, and Shenghua Gao. 2021. As-mlp: An axial shifted mlp architecture for vision. arXiv preprint arXiv:2107.08391 (2021)."},{"key":"e_1_3_2_2_30_1","volume-title":"Tsm: Temporal shift module for efficient video understanding. In CVPR. 7083--7093.","author":"Lin Ji","year":"2019","unstructured":"Ji Lin, Chuang Gan, and Song Han. 2019. Tsm: Temporal shift module for efficient video understanding. In CVPR. 7083--7093."},{"key":"e_1_3_2_2_31_1","first-page":"9204","article-title":"Pay attention to mlps","volume":"34","author":"Liu Hanxiao","year":"2021","unstructured":"Hanxiao Liu, Zihang Dai, David So, and Quoc V Le. 2021. Pay attention to mlps. NeurIPS, Vol. 34 (2021), 9204--9215.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_32_1","volume-title":"Decebal Constantin Mocanu, and Zhangyang Wang","author":"Liu Shiwei","year":"2022","unstructured":"Shiwei Liu, Tianlong Chen, Xiaohan Chen, Xuxi Chen, Qiao Xiao, Boqian Wu, Tommi K\u00e4rkk\u00e4inen, Mykola Pechenizkiy, Decebal Constantin Mocanu, and Zhangyang Wang. 2022. More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity. In ICLR."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Ze Liu Yutong Lin Yue Cao Han Hu Yixuan Wei Zheng Zhang Stephen Lin and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In ICCV. 10012--10022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_34_1","volume-title":"A convnet for the","author":"Liu Zhuang","year":"2020","unstructured":"Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, and Saining Xie. 2022. A convnet for the 2020s. In CVPR. 11976--11986."},{"key":"e_1_3_2_2_35_1","volume-title":"Decoupled weight decay regularization. ICLR","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. ICLR (2019)."},{"volume-title":"Diagonalwise refactorization: An efficient training method for depthwise convolutions","author":"Qin Zheng","key":"e_1_3_2_2_36_1","unstructured":"Zheng Qin, Zhaoning Zhang, Dongsheng Li, Yiming Zhang, and Yuxing Peng. 2018. Diagonalwise refactorization: An efficient training method for depthwise convolutions. In IJCNN. IEEE, 1--8."},{"key":"e_1_3_2_2_37_1","volume-title":"Ross Girshick, Kaiming He, and Piotr Doll\u00e1r.","author":"Radosavovic Ilija","year":"2020","unstructured":"Ilija Radosavovic, Raj Prateek Kosaraju, Ross Girshick, Kaiming He, and Piotr Doll\u00e1r. 2020. Designing network design spaces. In CVPR. 10428--10436."},{"key":"e_1_3_2_2_38_1","first-page":"10353","article-title":"Hornet: Efficient high-order spatial interactions with recursive gated convolutions","volume":"35","author":"Rao Yongming","year":"2022","unstructured":"Yongming Rao, Wenliang Zhao, Yansong Tang, Jie Zhou, Ser Nam Lim, and Jiwen Lu. 2022. Hornet: Efficient high-order spatial interactions with recursive gated convolutions. NeurIPS, Vol. 35 (2022), 10353--10366.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_39_1","volume-title":"Very deep convolutional networks for large-scale image recognition. ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. ICLR (2015)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20133"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Yehui Tang Kai Han Jianyuan Guo Chang Xu Yanxi Li Chao Xu and Yunhe Wang. 2022. An image patch is a wave: Phase-aware vision mlp. In CVPR. 10935--10944.","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"e_1_3_2_2_42_1","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al. 2021. Mlp-mixer: An all-mlp architecture for vision. NeurIPS, Vol. 34 (2021), 24261--24272.","journal-title":"NeurIPS"},{"key":"e_1_3_2_2_43_1","volume-title":"Resmlp: Feedforward networks for image classification with data-efficient training","author":"Touvron Hugo","year":"2022","unstructured":"Hugo Touvron, Piotr Bojanowski, Mathilde Caron, Matthieu Cord, Alaaeldin El-Nouby, Edouard Grave, Gautier Izacard, Armand Joulin, Gabriel Synnaeve, Jakob Verbeek, et al. 2022. Resmlp: Feedforward networks for image classification with data-efficient training. IEEE TPAMI (2022)."},{"key":"e_1_3_2_2_44_1","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 ICML. 10347--10357."},{"key":"e_1_3_2_2_45_1","volume-title":"Patches are all you need? arXiv preprint arXiv:2201.09792","author":"Trockman Asher","year":"2022","unstructured":"Asher Trockman and J Zico Kolter. 2022. Patches are all you need? arXiv preprint arXiv:2201.09792 (2022)."},{"key":"e_1_3_2_2_46_1","volume-title":"NeurIPS","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. NeurIPS, Vol. 30 (2017)."},{"key":"e_1_3_2_2_47_1","volume-title":"NeurIPS","volume":"29","author":"Vinyals Oriol","year":"2016","unstructured":"Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Daan Wierstra, et al. 2016. Matching networks for one shot learning. NeurIPS, Vol. 29 (2016)."},{"key":"e_1_3_2_2_48_1","volume-title":"Internimage: Exploring large-scale vision foundation models with deformable convolutions. In CVPR. 14408--14419.","author":"Wang Wenhai","year":"2023","unstructured":"Wenhai Wang, Jifeng Dai, Zhe Chen, Zhenhang Huang, Zhiqi Li, Xizhou Zhu, Xiaowei Hu, Tong Lu, Lewei Lu, Hongsheng Li, et al. 2023. Internimage: Exploring large-scale vision foundation models with deformable convolutions. In CVPR. 14408--14419."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Wenhai Wang Enze Xie Xiang Li Deng-Ping Fan Kaitao Song Ding Liang Tong Lu Ping Luo and Ling Shao. 2021. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In ICCV. 568--578.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_2_50_1","unstructured":"Ziyu Wang Wenhao Jiang Yiming M Zhu Li Yuan Yibing Song and Wei Liu. 2022. Dynamixer: a vision MLP architecture with dynamic mixing. In ICML. 22691--22701."},{"key":"e_1_3_2_2_51_1","volume-title":"Resnet strikes back: An improved training procedure in timm. arXiv preprint arXiv:2110.00476","author":"Wightman Ross","year":"2021","unstructured":"Ross Wightman, Hugo Touvron, and Herv\u00e9 J\u00e9gou. 2021. Resnet strikes back: An improved training procedure in timm. arXiv preprint arXiv:2110.00476 (2021)."},{"key":"e_1_3_2_2_52_1","volume-title":"Cvt: Introducing convolutions to vision transformers. In ICCV. 22--31.","author":"Wu Haiping","year":"2021","unstructured":"Haiping Wu, Bin Xiao, Noel Codella, Mengchen Liu, Xiyang Dai, Lu Yuan, and Lei Zhang. 2021. Cvt: Introducing convolutions to vision transformers. In ICCV. 22--31."},{"key":"e_1_3_2_2_53_1","volume-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747","author":"Xiao Han","year":"2017","unstructured":"Han Xiao, Kashif Rasul, and Roland Vollgraf. 2017. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)."},{"key":"e_1_3_2_2_54_1","unstructured":"Saining Xie Ross Girshick Piotr Doll\u00e1r Zhuowen Tu and Kaiming He. 2017. Aggregated residual transformations for deep neural networks. In CVPR. 1492--1500."},{"key":"e_1_3_2_2_55_1","volume-title":"S2-MLPv2: Improved Spatial-Shift MLP Architecture for Vision. arXiv preprint arXiv:2108.01072","author":"Yu Tan","year":"2021","unstructured":"Tan Yu, Xu Li, Yunfeng Cai, Mingming Sun, and Ping Li. 2021. S2-MLPv2: Improved Spatial-Shift MLP Architecture for Vision. arXiv preprint arXiv:2108.01072 (2021)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"e_1_3_2_2_57_1","volume-title":"Sanghyuk Chun, Junsuk Choe, and Youngjoon Yoo.","author":"Yun Sangdoo","year":"2019","unstructured":"Sangdoo Yun, Dongyoon Han, Seong Joon Oh, Sanghyuk Chun, Junsuk Choe, and Youngjoon Yoo. 2019. Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV. 6023--6032."},{"key":"e_1_3_2_2_58_1","volume-title":"mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412","author":"Zhang Hongyi","year":"2017","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. 2017. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)."},{"key":"e_1_3_2_2_59_1","volume-title":"Shufflenet: An extremely efficient convolutional neural network for mobile devices. In CVPR. 6848--6856.","author":"Zhang Xiangyu","year":"2018","unstructured":"Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, and Jian Sun. 2018. Shufflenet: An extremely efficient convolutional neural network for mobile devices. In CVPR. 6848--6856."},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20252"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680809","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":61,"alternative-id":["10.1145\/3664647.3680809","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680809","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"}}]}}