{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T06:59:56Z","timestamp":1782802796219,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":77,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00345398"],"award-info":[{"award-number":["RS-2024-00345398"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information & communications Technology Planning & Evaluation","award":["RS-2020-II201373"],"award-info":[{"award-number":["RS-2020-II201373"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,21]]},"DOI":"10.1145\/3627673.3679538","type":"proceedings-article","created":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T19:34:21Z","timestamp":1729452861000},"page":"983-993","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["HiLite: Hierarchical Level-implemented Architecture Attaining Part-Whole Interpretability"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5420-3574","authenticated-orcid":false,"given":"Yoo Hyun","family":"Jeong","sequence":"first","affiliation":[{"name":"Hanyang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4019-4134","authenticated-orcid":false,"given":"Sunghyun","family":"Hwang","sequence":"additional","affiliation":[{"name":"Hanyang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5410-6391","authenticated-orcid":false,"given":"Dong-Kyu","family":"Chae","sequence":"additional","affiliation":[{"name":"Hanyang University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Luca Bertinetto et al. 2020. Making better mistakes: Leveraging class hierarchies with deep networks. In CVPR. 12506--12515.","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"e_1_3_2_1_5_1","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."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR, 1691--1703","author":"Chen Mark","year":"2020","unstructured":"Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative pretraining from pixels. In International conference on machine learning. PMLR, 1691--1703."},{"key":"e_1_3_2_1_9_1","volume-title":"Cyclemlp: A mlp-like architecture for dense prediction. arXiv preprint arXiv:2107.10224","author":"Chen Shoufa","year":"2021","unstructured":"Shoufa Chen, Enze Xie, Chongjian Ge, Runjian Chen, Ding Liang, and Ping Luo. 2021. Cyclemlp: A mlp-like architecture for dense prediction. arXiv preprint arXiv:2107.10224 (2021)."},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_3_2_1_12_1","volume-title":"Charles Sutton, Sebastian Gehrmann, et al.","author":"Chowdhery Aakanksha","year":"2022","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2022. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Debiased contrastive learning. Advances in neural information processing systems","author":"Chuang Ching-Yao","year":"2020","unstructured":"Ching-Yao Chuang, Joshua Robinson, Yen-Chen Lin, Antonio Torralba, and Stefanie Jegelka. 2020. Debiased contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 8765--8775."},{"key":"e_1_3_2_1_14_1","volume-title":"Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. 2020. Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555 (2020)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93736-2_50"},{"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","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_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01332"},{"key":"e_1_3_2_1_20_1","volume-title":"European Union regulations on algorithmic decision-making and a 'right to explanation'. AI magazine","author":"Goodman Bryce","year":"2017","unstructured":"Bryce Goodman and Seth Flaxman. 2017. European Union regulations on algorithmic decision-making and a 'right to explanation'. AI magazine, Vol. 38, 3 (2017), 50--57."},{"key":"e_1_3_2_1_21_1","volume-title":"Neural module networks for reasoning over text. arXiv preprint arXiv:1912.04971","author":"Gupta Nitish","year":"2019","unstructured":"Nitish Gupta, Kevin Lin, Dan Roth, Sameer Singh, and Matt Gardner. 2019. Neural module networks for reasoning over text. arXiv preprint arXiv:1912.04971 (2019)."},{"key":"e_1_3_2_1_22_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, Vol. 34 (2021), 15908--15919.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"e_1_3_2_1_24_1","volume-title":"A thousand brains: A new theory of intelligence","author":"Hawkins Jeff","unstructured":"Jeff Hawkins. 2021. A thousand brains: A new theory of intelligence. Basic Books."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_27_1","volume-title":"How to represent part-whole hierarchies in a neural network. Neural Computation","author":"Hinton Geoffrey","year":"2022","unstructured":"Geoffrey Hinton. 2022. How to represent part-whole hierarchies in a neural network. Neural Computation (2022), 1--40."},{"key":"e_1_3_2_1_28_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)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-021-04715-0"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_31_1","volume-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360","author":"Iandola Forrest N","year":"2016","unstructured":"Forrest N Iandola, Song Han, Matthew W Moskewicz, Khalid Ashraf, William J Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv preprint arXiv:1602.07360 (2016)."},{"key":"e_1_3_2_1_32_1","volume-title":"Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144","author":"Jang Eric","year":"2016","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)."},{"key":"e_1_3_2_1_33_1","first-page":"14745","article-title":"Transgan: Two pure transformers can make one strong gan, and that can scale up","volume":"34","author":"Jiang Yifan","year":"2021","unstructured":"Yifan Jiang, Shiyu Chang, and Zhangyang Wang. 2021. Transgan: Two pure transformers can make one strong gan, and that can scale up. Advances in Neural Information Processing Systems, Vol. 34 (2021), 14745--14758.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","volume-title":"Supervised contrastive learning. Advances in neural information processing systems","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 18661--18673."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539463"},{"key":"e_1_3_2_1_36_1","volume-title":"What Does a Model Really Look at?: Extracting Model-Oriented Concepts for Explaining Deep Neural Networks","author":"Kim Seonggyeom","year":"2024","unstructured":"Seonggyeom Kim and Dong-Kyu Chae. 2024. What Does a Model Really Look at?: Extracting Model-Oriented Concepts for Explaining Deep Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_38_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_39_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)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_7"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00086"},{"key":"e_1_3_2_1_43_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_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"e_1_3_2_1_45_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_46_1","volume-title":"Liu","author":"Yahui","year":"2021","unstructured":"Yahui et al. Liu. 2021. Efficient training of visual transformers with small datasets. NeurIPS (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_48_1","volume-title":"Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets. arXiv preprint arXiv:2210.05958","author":"Lu Zhiying","year":"2022","unstructured":"Zhiying Lu, Hongtao Xie, Chuanbin Liu, and Yongdong Zhang. 2022. Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small Datasets. arXiv preprint arXiv:2210.05958 (2022)."},{"key":"e_1_3_2_1_49_1","volume-title":"Interpretability Needs a New Paradigm. arXiv preprint arXiv:2405.05386","author":"Madsen Andreas","year":"2024","unstructured":"Andreas Madsen, Himabindu Lakkaraju, Siva Reddy, and Sarath Chandar. 2024. Interpretability Needs a New Paradigm. arXiv preprint arXiv:2405.05386 (2024)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"crossref","unstructured":"Nithesh Naik BM Hameed Dasharathraj K Shetty Dishant Swain Milap Shah Rahul Paul Kaivalya Aggarwal Sufyan Ibrahim Vathsala Patil Komal Smriti et al. 2022. Legal and ethical consideration in artificial intelligence in healthcare: who takes responsibility? Frontiers in surgery Vol. 9 (2022) 266.","DOI":"10.3389\/fsurg.2022.862322"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML54575.2023.00039"},{"key":"e_1_3_2_1_54_1","volume-title":"Detecting novel associations in large data sets. science","author":"Reshef David N","year":"2011","unstructured":"David N Reshef, Yakir A Reshef, Hilary K Finucane, Sharon R Grossman, Gilean McVean, Peter J Turnbaugh, Eric S Lander, Michael Mitzenmacher, and Pardis C Sabeti. 2011. Detecting novel associations in large data sets. science, Vol. 334, 6062 (2011), 1518--1524."},{"key":"e_1_3_2_1_55_1","volume-title":"Detecting novel associations in large data sets. science","author":"Reshef David N","year":"2011","unstructured":"David N Reshef, Yakir A Reshef, Hilary K Finucane, Sharon R Grossman, Gilean McVean, Peter J Turnbaugh, Eric S Lander, Michael Mitzenmacher, and Pardis C Sabeti. 2011. Detecting novel associations in large data sets. science, Vol. 334, 6062 (2011), 1518--1524."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_1_57_1","volume-title":"Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature machine intelligence","author":"Rudin Cynthia","year":"2019","unstructured":"Cynthia Rudin. 2019. Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature machine intelligence, Vol. 1, 5 (2019), 206--215."},{"key":"e_1_3_2_1_58_1","volume-title":"Dynamic routing between capsules. Advances in neural information processing systems","author":"Sabour Sara","year":"2017","unstructured":"Sara Sabour, Nicholas Frosst, and Geoffrey E Hinton. 2017. Dynamic routing between capsules. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_59_1","volume-title":"The Kolmogorov--Arnold representation theorem revisited. Neural networks","author":"Schmidt-Hieber Johannes","year":"2021","unstructured":"Johannes Schmidt-Hieber. 2021. The Kolmogorov--Arnold representation theorem revisited. Neural networks, Vol. 137 (2021), 119--126."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_61_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_62_1","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume":"33","author":"Sitzmann Vincent","year":"2020","unstructured":"Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. 2020. Implicit neural representations with periodic activation functions. Advances in Neural Information Processing Systems, Vol. 33 (2020), 7462--7473.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_63_1","volume-title":"Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications","author":"Smith Leslie N","year":"2019","unstructured":"Leslie N Smith and Nicholay Topin. 2019. Super-convergence: Very fast training of neural networks using large learning rates. In Artificial intelligence and machine learning for multi-domain operations applications, Vol. 11006. SPIE, 369--386."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13347-020-00414-7"},{"key":"e_1_3_2_1_66_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 34 (2021), 24261--24272."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-022-00142-y"},{"key":"e_1_3_2_1_68_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0028343"},{"key":"e_1_3_2_1_70_1","volume-title":"Order of processing in visual perception. Canadian Journal of Psychology\/Revue canadienne de psychologie","author":"White Murray J","year":"1976","unstructured":"Murray J White. 1976. Order of processing in visual perception. Canadian Journal of Psychology\/Revue canadienne de psychologie, Vol. 30, 3 (1976), 140--156."},{"key":"e_1_3_2_1_71_1","volume-title":"Principal component analysis. Chemometrics and intelligent laboratory systems","author":"Wold Svante","year":"1987","unstructured":"Svante Wold, Kim Esbensen, and Paul Geladi. 1987. Principal component analysis. Chemometrics and intelligent laboratory systems, Vol. 2, 1--3 (1987), 37--52."},{"key":"e_1_3_2_1_72_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_1_73_1","volume-title":"Recommender Transformers with Behavior Pathways. arXiv preprint arXiv:2206.06804","author":"Yao Zhiyu","year":"2022","unstructured":"Zhiyu Yao, Xinyang Chen, Sinan Wang, Qinyan Dai, Yumeng Li, Tanchao Zhu, and Mingsheng Long. 2022. Recommender Transformers with Behavior Pathways. arXiv preprint arXiv:2206.06804 (2022)."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01657-x"},{"key":"e_1_3_2_1_76_1","volume-title":"Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective. arXiv preprint arXiv:2302.03751","author":"Zhu Haoran","year":"2023","unstructured":"Haoran Zhu, Boyuan Chen, and Carter Yang. 2023. Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective. arXiv preprint arXiv:2302.03751 (2023)."},{"key":"e_1_3_2_1_77_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":"CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management","location":"Boise ID USA","acronym":"CIKM '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679538","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627673.3679538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:22Z","timestamp":1750294702000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627673.3679538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":77,"alternative-id":["10.1145\/3627673.3679538","10.1145\/3627673"],"URL":"https:\/\/doi.org\/10.1145\/3627673.3679538","relation":{},"subject":[],"published":{"date-parts":[[2024,10,21]]},"assertion":[{"value":"2024-10-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}