{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T19:58:17Z","timestamp":1778097497805,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":57,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"The National Key Research and Development Program of China","award":["020YFB1406703"],"award-info":[{"award-number":["020YFB1406703"]}]},{"name":"The National Natural Science Foundation of China","award":["U21B2026"],"award-info":[{"award-number":["U21B2026"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547953","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:46Z","timestamp":1665416566000},"page":"6288-6299","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Parameterization of Cross-token Relations with Relative Positional Encoding for Vision MLP"],"prefix":"10.1145","author":[{"given":"Zhicai","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbin","family":"Hao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingting","family":"Mu","sequence":"additional","affiliation":[{"name":"University of Manchester, Manchester, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba , Jamie Ryan Kiros, and Geoffrey E Hinton . 2016 . Layer normalization. arXiv preprint arXiv:1607.06450 (2016). Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_2_4_1","unstructured":"Kai Chen Jiaqi Wang Jiangmiao Pang Yuhang Cao Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jiarui Xu etal 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019).  Kai Chen Jiaqi Wang Jiangmiao Pang Yuhang Cao Yu Xiong Xiaoxiao Li Shuyang Sun Wansen Feng Ziwei Liu Jiarui Xu et al. 2019. MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)."},{"key":"e_1_3_2_2_5_1","volume-title":"CycleMLP: A MLP-like Architecture for Dense Prediction. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NMEceG4v69Y","author":"Chen Shoufa","year":"2022","unstructured":"Shoufa Chen , Enze Xie , Chongjian GE , Runjian Chen , Ding Liang , and Ping Luo . 2022 . CycleMLP: A MLP-like Architecture for Dense Prediction. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NMEceG4v69Y Shoufa Chen, Enze Xie, Chongjian GE, Runjian Chen, Ding Liang, and Ping Luo. 2022. CycleMLP: A MLP-like Architecture for Dense Prediction. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NMEceG4v69Y"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00075"},{"key":"e_1_3_2_2_7_1","volume-title":"Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882","author":"Chu Xiangxiang","year":"2021","unstructured":"Xiangxiang Chu , Zhi Tian , Bo Zhang , Xinlong Wang , Xiaolin Wei , Huaxia Xia , and Chunhua Shen . 2021. Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 ( 2021 ). Xiangxiang Chu, Zhi Tian, Bo Zhang, Xinlong Wang, Xiaolin Wei, Huaxia Xia, and Chunhua Shen. 2021. Conditional positional encodings for vision transformers. arXiv preprint arXiv:2102.10882 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"On the relationship between self-attention and convolutional layers. arXiv preprint arXiv:1911.03584","author":"Cordonnier Jean-Baptiste","year":"2019","unstructured":"Jean-Baptiste Cordonnier , Andreas Loukas , and Martin Jaggi . 2019. On the relationship between self-attention and convolutional layers. arXiv preprint arXiv:1911.03584 ( 2019 ). Jean-Baptiste Cordonnier, Andreas Loukas, and Martin Jaggi. 2019. On the relationship between self-attention and convolutional layers. arXiv preprint arXiv:1911.03584 (2019)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_2_2_10_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dai Zihang","year":"2021","unstructured":"Zihang Dai , Hanxiao Liu , Quoc Le , and Mingxing Tan . 2021 . Coatnet: Marrying convolution and attention for all data sizes . Advances in Neural Information Processing Systems , Vol. 34 (2021). Zihang Dai, Hanxiao Liu, Quoc Le, and Mingxing Tan. 2021. Coatnet: Marrying convolution and attention for all data sizes. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_12_1","volume-title":"RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition. arXiv preprint arXiv:2105.01883","author":"Ding Xiaohan","year":"2021","unstructured":"Xiaohan Ding , Xiangyu Zhang , Jungong Han , and Guiguang Ding . 2021. RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition. arXiv preprint arXiv:2105.01883 ( 2021 ). Xiaohan Ding, Xiangyu Zhang, Jungong Han, and Guiguang Ding. 2021. RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition. arXiv preprint arXiv:2105.01883 (2021)."},{"key":"e_1_3_2_2_13_1","volume-title":"Cswin transformer: A general vision transformer backbone with cross-shaped windows. arXiv preprint arXiv:2107.00652","author":"Dong Xiaoyi","year":"2021","unstructured":"Xiaoyi Dong , Jianmin Bao , Dongdong Chen , Weiming Zhang , Nenghai Yu , Lu Yuan , Dong Chen , and Baining Guo . 2021. Cswin transformer: A general vision transformer backbone with cross-shaped windows. arXiv preprint arXiv:2107.00652 ( 2021 ). Xiaoyi Dong, Jianmin Bao, Dongdong Chen, Weiming Zhang, Nenghai Yu, Lu Yuan, Dong Chen, and Baining Guo. 2021. Cswin transformer: A general vision transformer backbone with cross-shaped windows. arXiv preprint arXiv:2107.00652 (2021)."},{"key":"e_1_3_2_2_14_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy","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. https:\/\/openreview.net\/forum?id=YicbFdNTTy 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. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_2_15_1","volume-title":"International Conference on Machine Learning. PMLR, 2286--2296","author":"Ascoli St\u00e9phane","year":"2021","unstructured":"St\u00e9phane d' Ascoli , Hugo Touvron , Matthew L Leavitt , Ari S Morcos , Giulio Biroli , and Levent Sagun . 2021 . Convit: Improving vision transformers with soft convolutional inductive biases . In International Conference on Machine Learning. PMLR, 2286--2296 . St\u00e9phane d'Ascoli, Hugo Touvron, Matthew L Leavitt, Ari S Morcos, Giulio Biroli, and Levent Sagun. 2021. Convit: Improving vision transformers with soft convolutional inductive biases. In International Conference on Machine Learning. PMLR, 2286--2296."},{"key":"e_1_3_2_2_16_1","volume-title":"Cross-Modality High-Frequency Transformer for MR Image Super-Resolution. arXiv preprint arXiv:2203.15314","author":"Fang Chaowei","year":"2022","unstructured":"Chaowei Fang , Dingwen Zhang , Liang Wang , Yulun Zhang , Lechao Cheng , and Junwei Han . 2022. Cross-Modality High-Frequency Transformer for MR Image Super-Resolution. arXiv preprint arXiv:2203.15314 ( 2022 ). Chaowei Fang, Dingwen Zhang, Liang Wang, Yulun Zhang, Lechao Cheng, and Junwei Han. 2022. Cross-Modality High-Frequency Transformer for MR Image Super-Resolution. arXiv preprint arXiv:2203.15314 (2022)."},{"key":"e_1_3_2_2_17_1","volume-title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement. arXiv preprint arXiv:2108.13341","author":"Guo Jianyuan","year":"2021","unstructured":"Jianyuan Guo , Yehui Tang , Kai Han , Xinghao Chen , Han Wu , Chao Xu , Chang Xu , and Yunhe Wang . 2021. Hire-MLP: Vision MLP via Hierarchical Rearrangement. arXiv preprint arXiv:2108.13341 ( 2021 ). Jianyuan Guo, Yehui Tang, Kai Han, Xinghao Chen, Han Wu, Chao Xu, Chang Xu, and Yunhe Wang. 2021. Hire-MLP: Vision MLP via Hierarchical Rearrangement. arXiv preprint arXiv:2108.13341 (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00100"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_21_1","volume-title":"Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654","author":"He Pengcheng","year":"2020","unstructured":"Pengcheng He , Xiaodong Liu , Jianfeng Gao , and Weizhu Chen . 2020 . Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020). Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2020. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 (2020)."},{"key":"e_1_3_2_2_22_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton , Oriol Vinyals , and Jeff Dean . 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 ( 2015 ). Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_23_1","volume-title":"Vision permutator: A permutable mlp-like architecture for visual recognition","author":"Hou Qibin","year":"2022","unstructured":"Qibin Hou , Zihang Jiang , Li Yuan , Ming-Ming Cheng , Shuicheng Yan , and Jiashi Feng . 2022. Vision permutator: A permutable mlp-like architecture for visual recognition . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2022 ). Qibin Hou, Zihang Jiang, Li Yuan, Ming-Ming Cheng, Shuicheng Yan, and Jiashi Feng. 2022. Vision permutator: A permutable mlp-like architecture for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"e_1_3_2_2_27_1","volume-title":"Improve transformer models with better relative position embeddings. arXiv preprint arXiv:2009.13658","author":"Huang Zhiheng","year":"2020","unstructured":"Zhiheng Huang , Davis Liang , Peng Xu , and Bing Xiang . 2020. Improve transformer models with better relative position embeddings. arXiv preprint arXiv:2009.13658 ( 2020 ). Zhiheng Huang, Davis Liang, Peng Xu, and Bing Xiang. 2020. Improve transformer models with better relative position embeddings. arXiv preprint arXiv:2009.13658 (2020)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413577"},{"key":"e_1_3_2_2_29_1","volume-title":"Rethinking positional encoding in language pre-training. arXiv preprint arXiv:2006.15595","author":"Ke Guolin","year":"2020","unstructured":"Guolin Ke , Di He , and Tie-Yan Liu . 2020. Rethinking positional encoding in language pre-training. arXiv preprint arXiv:2006.15595 ( 2020 ). Guolin Ke, Di He, and Tie-Yan Liu. 2020. Rethinking positional encoding in language pre-training. arXiv preprint arXiv:2006.15595 (2020)."},{"key":"e_1_3_2_2_30_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems , Vol. 25 ( 2012 ), 1097--1105. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, Vol. 25 (2012), 1097--1105."},{"key":"e_1_3_2_2_31_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). 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_32_1","first-page":"16079","article-title":"CAPE: Encoding relative positions with continuous augmented positional embeddings","volume":"34","author":"Likhomanenko Tatiana","year":"2021","unstructured":"Tatiana Likhomanenko , Qiantong Xu , Gabriel Synnaeve , Ronan Collobert , and Alex Rogozhnikov . 2021 . CAPE: Encoding relative positions with continuous augmented positional embeddings . Advances in Neural Information Processing Systems , Vol. 34 (2021), 16079 -- 16092 . Tatiana Likhomanenko, Qiantong Xu, Gabriel Synnaeve, Ronan Collobert, and Alex Rogozhnikov. 2021. CAPE: Encoding relative positions with continuous augmented positional embeddings. Advances in Neural Information Processing Systems, Vol. 34 (2021), 16079--16092.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_35_1","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Liu Hanxiao","year":"2021","unstructured":"Hanxiao Liu , Zihang Dai , David So , and Quoc Le . 2021 a. Pay attention to MLPs . Advances in Neural Information Processing Systems , Vol. 34 (2021). Hanxiao Liu, Zihang Dai, David So, and Quoc Le. 2021a. Pay attention to MLPs. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_37_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter . 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 ( 2017 ). Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_2_38_1","series-title":"SIAM journal on control and optimization","volume-title":"Acceleration of stochastic approximation by averaging","author":"Polyak Boris T","year":"1992","unstructured":"Boris T Polyak and Anatoli B Juditsky . 1992. Acceleration of stochastic approximation by averaging . SIAM journal on control and optimization , Vol. 30 , 4 ( 1992 ), 838--855. Boris T Polyak and Anatoli B Juditsky. 1992. Acceleration of stochastic approximation by averaging. SIAM journal on control and optimization, Vol. 30, 4 (1992), 838--855."},{"key":"e_1_3_2_2_39_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018).  Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_2_40_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever etal 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9.  Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_2_2_42_1","volume-title":"Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683","author":"Raffel Colin","year":"2019","unstructured":"Colin Raffel , Noam Shazeer , Adam Roberts , Katherine Lee , Sharan Narang , Michael Matena , Yanqi Zhou , Wei Li , and Peter J Liu . 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 ( 2019 ). Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2019)."},{"key":"e_1_3_2_2_43_1","volume-title":"Self-attention with relative position representations. arXiv preprint arXiv:1803.02155","author":"Shaw Peter","year":"2018","unstructured":"Peter Shaw , Jakob Uszkoreit , and Ashish Vaswani . 2018. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 ( 2018 ). Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. 2018. Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)."},{"key":"e_1_3_2_2_44_1","volume-title":"Natural image statistics and neural representation. Annual review of neuroscience","author":"Simoncelli Eero P","year":"2001","unstructured":"Eero P Simoncelli and Bruno A Olshausen . 2001. Natural image statistics and neural representation. Annual review of neuroscience , Vol. 24 , 1 ( 2001 ), 1193--1216. Eero P Simoncelli and Bruno A Olshausen. 2001. Natural image statistics and neural representation. Annual review of neuroscience, Vol. 24, 1 (2001), 1193--1216."},{"key":"e_1_3_2_2_45_1","volume-title":"Advances in Neural Information Processing Systems","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 , 2021 . Mlp-mixer: An all-mlp architecture for vision . Advances in Neural Information Processing Systems , Vol. 34 (2021). 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. Advances in Neural Information Processing Systems, Vol. 34 (2021)."},{"key":"e_1_3_2_2_46_1","volume-title":"Resmlp: Feedforward networks for image classification with data-efficient training. arXiv preprint arXiv:2105.03404","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron , Piotr Bojanowski , Mathilde Caron , Matthieu Cord , Alaaeldin El-Nouby , Edouard Grave , Gautier Izacard , Armand Joulin , Gabriel Synnaeve , Jakob Verbeek , 2021 a. Resmlp: Feedforward networks for image classification with data-efficient training. arXiv preprint arXiv:2105.03404 (2021). Hugo Touvron, Piotr Bojanowski, Mathilde Caron, Matthieu Cord, Alaaeldin El-Nouby, Edouard Grave, Gautier Izacard, Armand Joulin, Gabriel Synnaeve, Jakob Verbeek, et al. 2021a. Resmlp: Feedforward networks for image classification with data-efficient training. arXiv preprint arXiv:2105.03404 (2021)."},{"key":"e_1_3_2_2_47_1","volume-title":"International Conference on Machine Learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron , Matthieu Cord , Matthijs Douze , Francisco Massa , Alexandre Sablayrolles , and Herv\u00e9 J\u00e9gou . 2021 b. Training data-efficient image transformers & distillation through attention . In International Conference on Machine Learning. PMLR, 10347--10357 . Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021b. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning. PMLR, 10347--10357."},{"key":"e_1_3_2_2_48_1","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. In Advances in neural information processing systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998--6008."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"e_1_3_2_2_51_1","volume-title":"Early convolutions help transformers see better. arXiv preprint arXiv:2106.14881","author":"Xiao Tete","year":"2021","unstructured":"Tete Xiao , Mannat Singh , Eric Mintun , Trevor Darrell , Piotr Doll\u00e1r , and Ross Girshick . 2021. Early convolutions help transformers see better. arXiv preprint arXiv:2106.14881 ( 2021 ). Tete Xiao, Mannat Singh, Eric Mintun, Trevor Darrell, Piotr Doll\u00e1r, and Ross Girshick. 2021. Early convolutions help transformers see better. arXiv preprint arXiv:2106.14881 (2021)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_2_54_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 ). 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_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"e_1_3_2_2_56_1","volume-title":"Aggregating nested transformers. arXiv preprint arXiv:2105.12723","author":"Zhang Zizhao","year":"2021","unstructured":"Zizhao Zhang , Han Zhang , Long Zhao , Ting Chen , and Tomas Pfister . 2021b. Aggregating nested transformers. arXiv preprint arXiv:2105.12723 ( 2021 ). Zizhao Zhang, Han Zhang, Long Zhao, Ting Chen, and Tomas Pfister. 2021b. Aggregating nested transformers. arXiv preprint arXiv:2105.12723 (2021)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547953","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:31Z","timestamp":1750186831000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":57,"alternative-id":["10.1145\/3503161.3547953","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547953","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}