{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:13Z","timestamp":1750309453648,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2024,12,3]]},"DOI":"10.1145\/3696409.3700190","type":"proceedings-article","created":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T09:55:23Z","timestamp":1735379723000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Where You See Is What You Know: A Visual-Semantic Conceptual Explainer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4983-5423","authenticated-orcid":false,"given":"Luhao","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Management, Zhejiang University, Hangzhou, China and Ningbo Institute of Digital Twin, Eastern Instituteof Technology, Ningbo, China, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0851-6752","authenticated-orcid":false,"given":"Xiangwei","family":"Kong","sequence":"additional","affiliation":[{"name":"School of Management, Zhejiang Univercity, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3544-6956","authenticated-orcid":false,"given":"Runsen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Management, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9583-0055","authenticated-orcid":false,"given":"Guodong","family":"Guo","sequence":"additional","affiliation":[{"name":"Ningbo Institute of Digital Twin, Eastern Instituteof Technology, Ningbo, China, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Reduan Achtibat Maximilian Dreyer Ilona Eisenbraun Sebastian Bosse Thomas Wiegand Wojciech Samek and Sebastian Lapuschkin. 2023. From attribution maps to human-understandable explanations through Concept Relevance Propagation. Nature Machine Intelligence 5 9 (2023) 1006\u20131019.","DOI":"10.1038\/s42256-023-00711-8"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Gulsum Alicioglu and Bo Sun. 2022. A survey of visual analytics for Explainable Artificial Intelligence methods. Computers & Graphics 102 (2022) 502\u2013520.","DOI":"10.1016\/j.cag.2021.09.002"},{"key":"e_1_3_3_2_4_2","volume-title":"NeurIPS","author":"Brown Tom\u00a0B.","year":"2020","unstructured":"Tom\u00a0B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel\u00a0M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In NeurIPS, Hugo Larochelle, Marc\u2019Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Diogo\u00a0V Carvalho Eduardo\u00a0M Pereira and Jaime\u00a0S Cardoso. 2019. Machine learning interpretability: A survey on methods and metrics. Electronics 8 8 (2019) 832.","DOI":"10.3390\/electronics8080832"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"e_1_3_3_2_7_2","first-page":"8928","volume-title":"NeurIPS","author":"Chen Chaofan","year":"2019","unstructured":"Chaofan Chen, Oscar Li, Daniel Tao, Alina Barnett, Cynthia Rudin, and Jonathan Su. 2019. This Looks Like That: Deep Learning for Interpretable Image Recognition. In NeurIPS, Hanna\u00a0M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d\u2019Alch\u00e9-Buc, Emily\u00a0B. Fox, and Roman Garnett (Eds.). 8928\u20138939. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/adf7ee2dcf142b0e11888e72b43fcb75-Abstract.html"},{"key":"e_1_3_3_2_8_2","volume-title":"NeurIPS","author":"Colin Julien","year":"2022","unstructured":"Julien Colin, Thomas Fel, R\u00e9mi Cad\u00e8ne, and Thomas Serre. 2022. What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods. In NeurIPS. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/13113e938f2957891c0c5e8df811dd01-Abstract-Conference.html"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093360"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Sanjoy Dey Prithwish Chakraborty Bum\u00a0Chul Kwon Amit Dhurandhar Mohamed Ghalwash Fernando J\u00a0Suarez Saiz Kenney Ng Daby Sow Kush\u00a0R Varshney and Pablo Meyer. 2022. Human-centered explainability for life sciences healthcare and medical informatics. Patterns 3 5 (2022).","DOI":"10.1016\/j.patter.2022.100493"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00266"},{"key":"e_1_3_3_2_13_2","first-page":"9273","volume-title":"NeurIPS","author":"Ghorbani Amirata","year":"2019","unstructured":"Amirata Ghorbani, James Wexler, James\u00a0Y. Zou, and Been Kim. 2019. Towards Automatic Concept-based Explanations. In NeurIPS, Hanna\u00a0M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d\u2019Alch\u00e9-Buc, Emily\u00a0B. Fox, and Roman Garnett (Eds.). 9273\u20139282. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/77d2afcb31f6493e350fca61764efb9a-Abstract.html"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_15_2","unstructured":"Amlan Jyoti Karthik\u00a0Balaji Ganesh Manoj Gayala Nandita\u00a0Lakshmi Tunuguntla Sandesh Kamath and Vineeth\u00a0N Balasubramanian. 2022. On the robustness of explanations of deep neural network models: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.04780 (2022)."},{"key":"e_1_3_3_2_16_2","unstructured":"Margot\u00a0E Kaminski and Jennifer\u00a0M Urban. 2021. The right to contest AI. Columbia Law Review 121 7 (2021) 1957\u20132048."},{"key":"e_1_3_3_2_17_2","first-page":"2673","volume-title":"ICML","author":"Kim Been","year":"2018","unstructured":"Been Kim, Martin Wattenberg, Justin Gilmer, Carrie\u00a0J. Cai, James Wexler, Fernanda\u00a0B. Vi\u00e9gas, and Rory Sayres. 2018. Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV). In ICML , Jennifer\u00a0G. Dy and Andreas Krause (Eds.), Vol.\u00a080. PMLR, 2673\u20132682. http:\/\/proceedings.mlr.press\/v80\/kim18d.html"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C Berg Wan-Yen Lo et\u00a0al. 2023. Segment anything. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_19_2","first-page":"5338","volume-title":"ICML","author":"Koh Pang\u00a0Wei","year":"2020","unstructured":"Pang\u00a0Wei Koh, Thao Nguyen, Yew\u00a0Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, and Percy Liang. 2020. Concept Bottleneck Models. In ICML , Vol.\u00a0119. PMLR, 5338\u20135348. http:\/\/proceedings.mlr.press\/v119\/koh20a.html"},{"key":"e_1_3_3_2_20_2","unstructured":"Mauritz Kop. 2021. Eu artificial intelligence act: The european approach to ai. Stanford-Vienna Transatlantic Technology Law Forum Transatlantic Antitrust\u00a0\u2026."},{"key":"e_1_3_3_2_21_2","volume-title":"ICLR","author":"Mikolov Tom\u00e1s","year":"2013","unstructured":"Tom\u00e1s Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. In ICLR, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_3_3_2_22_2","first-page":"3111","volume-title":"NeurIPS","author":"Mikolov Tom\u00e1s","year":"2013","unstructured":"Tom\u00e1s Mikolov, Ilya Sutskever, Kai Chen, Gregory\u00a0S. Corrado, and Jeffrey Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In NeurIPS, Christopher J.\u00a0C. Burges, L\u00e9on Bottou, Zoubin Ghahramani, and Kilian\u00a0Q. Weinberger (Eds.). 3111\u20133119. https:\/\/proceedings.neurips.cc\/paper\/2013\/hash\/9aa42b31882ec039965f3c4923ce901b-Abstract.html"},{"key":"e_1_3_3_2_23_2","first-page":"746","volume-title":"Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics","author":"Mikolov Tom\u00e1s","year":"2013","unstructured":"Tom\u00e1s Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013. Linguistic Regularities in Continuous Space Word Representations. In Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Lucy Vanderwende, Hal\u00a0Daum\u00e9 III, and Katrin Kirchhoff (Eds.). The Association for Computational Linguistics, 746\u2013751. https:\/\/aclanthology.org\/N13-1090\/"},{"key":"e_1_3_3_2_24_2","volume-title":"ICLR","author":"Oikarinen Tuomas\u00a0P.","year":"2023","unstructured":"Tuomas\u00a0P. Oikarinen, Subhro Das, Lam\u00a0M. Nguyen, and Tsui-Wei Weng. 2023. Label-free Concept Bottleneck Models. In ICLR. https:\/\/openreview.net\/pdf?id=FlCg47MNvBA"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Stefan Palan and Christian Schitter. 2018. Prolific. ac\u2014A subject pool for online experiments. Journal of Behavioral and Experimental Finance 17 (2018) 22\u201327.","DOI":"10.1016\/j.jbef.2017.12.004"},{"key":"e_1_3_3_2_26_2","first-page":"151","volume-title":"BMVC","author":"Petsiuk Vitali","year":"2018","unstructured":"Vitali Petsiuk, Abir Das, and Kate Saenko. 2018. RISE: Randomized Input Sampling for Explanation of Black-box Models. In BMVC. BMVA Press, 151. http:\/\/bmvc2018.org\/contents\/papers\/1064.pdf"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01052"},{"key":"e_1_3_3_2_28_2","unstructured":"Tianhe Ren Shilong Liu Ailing Zeng Jing Lin Kunchang Li He Cao Jiayu Chen Xinyu Huang Yukang Chen Feng Yan Zhaoyang Zeng Hao Zhang Feng Li Jie Yang Hongyang Li Qing Jiang and Lei Zhang. 2024. Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks. arxiv:https:\/\/arXiv.org\/abs\/2401.14159\u00a0[cs.CV]"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Cynthia Rudin. 2019. Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature machine intelligence 1 5 (2019) 206\u2013215.","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_3_2_31_2","volume-title":"ICLR","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2014. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. In ICLR, Yoshua Bengio and Yann LeCun (Eds.). http:\/\/arxiv.org\/abs\/1312.6034"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375830"},{"key":"e_1_3_3_2_33_2","unstructured":"Daniel Smilkov Nikhil Thorat Been Kim Fernanda Vi\u00e9gas and Martin Wattenberg. 2017. Smoothgrad: removing noise by adding noise. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.03825 (2017)."},{"key":"e_1_3_3_2_34_2","first-page":"4126","volume-title":"NeurIPS","author":"Srinivas Suraj","year":"2019","unstructured":"Suraj Srinivas and Fran\u00e7ois Fleuret. 2019. Full-Gradient Representation for Neural Network Visualization. In NeurIPS, Hanna\u00a0M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d\u2019Alch\u00e9-Buc, Emily\u00a0B. Fox, and Roman Garnett (Eds.). 4126\u20134135."},{"key":"e_1_3_3_2_35_2","unstructured":"Ao Sun Pingchuan Ma Yuanyuan Yuan and Shuai Wang. 2023. Explain Any Concept: Segment Anything Meets Concept-Based Explanation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.10289 (2023)."},{"key":"e_1_3_3_2_36_2","first-page":"3319","volume-title":"ICML","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic Attribution for Deep Networks. In ICML , Doina Precup and Yee\u00a0Whye Teh (Eds.), Vol.\u00a070. PMLR, 3319\u20133328. http:\/\/proceedings.mlr.press\/v70\/sundararajan17a.html"},{"key":"e_1_3_3_2_37_2","unstructured":"Johanna Vielhaben Stefan Bl\u00fccher and Nils Strodthoff. 2023. Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.11911 (2023)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Yongqin Xian Christoph\u00a0H Lampert Bernt Schiele and Zeynep Akata. 2018. Zero-shot learning\u2014a comprehensive evaluation of the good the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence 41 9 (2018) 2251\u20132265.","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V35I13.17389"},{"key":"e_1_3_3_2_42_2","unstructured":"Youcai Zhang Xinyu Huang Jinyu Ma Zhaoyang Li Zhaochuan Luo Yanchun Xie Yuzhuo Qin Tong Luo Yaqian Li Shilong Liu et\u00a0al. 2023. Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.03514 (2023)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Yu Zhang Peter Ti\u0148o Ale\u0161 Leonardis and Ke Tang. 2021. A survey on neural network interpretability. IEEE Transactions on Emerging Topics in Computational Intelligence 5 5 (2021) 726\u2013742.","DOI":"10.1109\/TETCI.2021.3100641"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_8"}],"event":{"name":"MMAsia '24: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Auckland New Zealand","acronym":"MMAsia '24"},"container-title":["Proceedings of the 6th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700190","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696409.3700190","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:11Z","timestamp":1750295411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696409.3700190"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":44,"alternative-id":["10.1145\/3696409.3700190","10.1145\/3696409"],"URL":"https:\/\/doi.org\/10.1145\/3696409.3700190","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"2024-12-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}