{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:57:49Z","timestamp":1777568269039,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":37,"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":"the Key R&D Projects in Liaoning Province","award":["2023JH26\/10200015"],"award-info":[{"award-number":["2023JH26\/10200015"]}]},{"name":"the Natural Science Foundation of China","award":["62376051,62366040,62076046,62066044"],"award-info":[{"award-number":["62376051,62366040,62076046,62066044"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["DUT24LAB123"],"award-info":[{"award-number":["DUT24LAB123"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681712","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"7298-7306","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Peeling Back the Layers: Interpreting the Storytelling of ViT"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5412-2348","authenticated-orcid":false,"given":"Jingjie","family":"Zeng","sequence":"first","affiliation":[{"name":"Dalian University of Technology, Dalian, LiaoNing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6186-2024","authenticated-orcid":false,"given":"Zhihao","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, LiaoNing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8597-122X","authenticated-orcid":false,"given":"Qi","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, LiaoNing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5557-7515","authenticated-orcid":false,"given":"Liang","family":"Yang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology & Ministry of Education, Key Laboratory of Social Computing and Cognitive Intelligence, Dalian, LiaoNing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0872-7688","authenticated-orcid":false,"given":"Hongfei","family":"Lin","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian, LiaoNing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907375117"},{"key":"e_1_3_2_1_2_1","volume-title":"Visualizing and Understanding Generative Adversarial Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Hyg_X2C5FX","author":"Bau David","year":"2019","unstructured":"David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou, Joshua B. Tenenbaum, William T. Freeman, and Antonio Torralba. 2019. Visualizing and Understanding Generative Adversarial Networks. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Hyg_X2C5FX"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44781-0_8"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00247"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"e_1_3_2_1_6_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_7_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arxiv: 2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_8_1","volume-title":"Vision Transformers Need Registers. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2dnO3LLiJ1","author":"Darcet Timoth\u00e9e","year":"2024","unstructured":"Timoth\u00e9e Darcet, Maxime Oquab, Julien Mairal, and Piotr Bojanowski. 2024. Vision Transformers Need Registers. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2dnO3LLiJ1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_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"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.522"},{"key":"e_1_3_2_1_12_1","first-page":"1","article-title":"A mathematical framework for transformer circuits","volume":"1","author":"Elhage Nelson","year":"2021","unstructured":"Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Nicholas Joseph, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, et al. 2021. A mathematical framework for transformer circuits. Transformer Circuits Thread, Vol. 1 (2021), 1.","journal-title":"Transformer Circuits Thread"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"e_1_3_2_1_14_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=5Ca9sSzuDp","author":"Gandelsman Yossi","year":"2024","unstructured":"Yossi Gandelsman, Alexei A. Efros, and Jacob Steinhardt. 2024. Interpreting CLIP's Image Representation via Text-Based Decomposition. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=5Ca9sSzuDp"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00030"},{"key":"e_1_3_2_1_16_1","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In ICML."},{"key":"e_1_3_2_1_17_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML.","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In ICML."},{"key":"e_1_3_2_1_18_1","volume-title":"Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81.","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74--81."},{"key":"e_1_3_2_1_19_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"e_1_3_2_1_21_1","volume-title":"Are sixteen heads really better than one? Advances in neural information processing systems","author":"Michel Paul","year":"2019","unstructured":"Paul Michel, Omer Levy, and Graham Neubig. 2019. Are sixteen heads really better than one? Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_22_1","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume":"34","author":"Naseer Muhammad Muzammal","year":"2021","unstructured":"Muhammad Muzammal Naseer, Kanchana Ranasinghe, Salman H Khan, Munawar Hayat, Fahad Shahbaz Khan, and Ming-Hsuan Yang. 2021. Intriguing properties of vision transformers. Advances in Neural Information Processing Systems, Vol. 34 (2021), 23296--23308.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00024.001"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"8763","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_27_1","volume-title":"Wortman Vaughan (Eds.)","volume":"34","author":"Raghu Maithra","year":"2021","unstructured":"Maithra Raghu, Thomas Unterthiner, Simon Kornblith, Chiyuan Zhang, and Alexey Dosovitskiy. 2021. Do Vision Transformers See Like Convolutional Neural Networks?. In Advances in Neural Information Processing Systems, M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan (Eds.), Vol. 34. Curran Associates, Inc., 12116--12128. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/652cf38361a209088302ba2b8b7f51e0-Paper.pdf"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zf_Ll3HZWgy","author":"Shen Sheng","year":"2022","unstructured":"Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, and Kurt Keutzer. 2022. How Much Can CLIP Benefit Vision-and-Language Tasks?. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=zf_Ll3HZWgy"},{"key":"e_1_3_2_1_30_1","volume-title":"Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389","author":"Sun Quan","year":"2023","unstructured":"Quan Sun, Yuxin Fang, Ledell Wu, Xinlong Wang, and Yue Cao. 2023. Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Zeyi Sun Ye Fang Tong Wu Pan Zhang Yuhang Zang Shu Kong Yuanjun Xiong Dahua Lin and Jiaqi Wang. 2023. Alpha-CLIP: A CLIP Model Focusing on Wherever You Want. arxiv: 2312.03818 [cs.CV]","DOI":"10.1109\/CVPR52733.2024.01237"},{"key":"e_1_3_2_1_32_1","volume-title":"International conference on machine learning. PMLR, 3319--3328","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International conference on machine learning. PMLR, 3319--3328."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00501"},{"key":"e_1_3_2_1_36_1","volume-title":"International conference on machine learning. PMLR","author":"Xu Kelvin","year":"2015","unstructured":"Kelvin Xu, Jimmy Ba, Ryan Kiros, Kyunghyun Cho, Aaron Courville, Ruslan Salakhudinov, Rich Zemel, and Yoshua Bengio. 2015. Show, attend and tell: Neural image caption generation with visual attention. In International conference on machine learning. PMLR, 2048--2057."},{"key":"e_1_3_2_1_37_1","volume-title":"Post-hoc Concept Bottleneck Models. In The Eleventh International Conference on Learning Representations.","author":"Yuksekgonul Mert","year":"2022","unstructured":"Mert Yuksekgonul, Maggie Wang, and James Zou. 2022. Post-hoc Concept Bottleneck Models. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_38_1","volume-title":"BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations.","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations."}],"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\/3664647.3681712","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:28Z","timestamp":1750295848000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681712"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":37,"alternative-id":["10.1145\/3664647.3681712","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681712","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"}}]}}