{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:20:13Z","timestamp":1765308013964,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-21-CE38-0012"],"award-info":[{"award-number":["ANR-21-CE38-0012"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["AI4Media, 951911"],"award-info":[{"award-number":["AI4Media, 951911"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758170","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:44:48Z","timestamp":1761371088000},"page":"12437-12445","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Re-examining Concept-based Explainable Models for Multimodal Interpretative Tasks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1979-1818","authenticated-orcid":false,"given":"Julie","family":"Tores","sequence":"first","affiliation":[{"name":"Universit\u00e9 C\u00f4te d'Azur, CNRS, Inria, I3S, Sophia Antipolis, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2457-4461","authenticated-orcid":false,"given":"Elisa","family":"Ancarani","sequence":"additional","affiliation":[{"name":"Universit\u00e9 C\u00f4te d'Azur, CNRS, I3S, Sophia Antipolis, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5644-7985","authenticated-orcid":false,"given":"R\u00e9my","family":"Sun","sequence":"additional","affiliation":[{"name":"Universit\u00e9 C\u00f4te d'Azur, Inria, CNRS, I3S, Sophia Antipolis, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1232-1787","authenticated-orcid":false,"given":"Lucile","family":"Sassatelli","sequence":"additional","affiliation":[{"name":"Universit\u00e9 C\u00f4te d'Azur, CNRS, I3S, Sophia Antipolis, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7315-210X","authenticated-orcid":false,"given":"Hui-Yin","family":"Wu","sequence":"additional","affiliation":[{"name":"Universit\u00e9 C\u00f4te d'Azur, Inria, Sophia Antipolis, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8712-1443","authenticated-orcid":false,"given":"Frederic","family":"Precioso","sequence":"additional","affiliation":[{"name":"Universit\u00e9 C\u00f4te d'Azur, CNRS, Inria, I3S, Sophia Antipolis, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00265-z"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00146-021-01162-8"},{"key":"e_1_3_2_1_4_1","volume-title":"Roberto Novoa, and James Zou.","author":"Daneshjou Roxana","year":"2022","unstructured":"Roxana Daneshjou, Mert Yuksekgonul, Zhuo Ran Cai, Roberto Novoa, and James Zou. 2022. SkinCon: a skin disease dataset densely annotated by domain experts for fine-grained model debugging and analysis (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 1320, 11 pages."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/20539517211035955"},{"key":"e_1_3_2_1_7_1","volume-title":"AST: Audio Spectrogram Transformer. arXiv:2104.01778 [cs.SD] https:\/\/arxiv.org\/abs\/2104.01778","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James Glass. 2021. AST: Audio Spectrogram Transformer. arXiv:2104.01778 [cs.SD] https:\/\/arxiv.org\/abs\/2104.01778"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. Minneapolis, Minnesota."},{"key":"e_1_3_2_1_9_1","volume-title":"International conference on machine learning. PMLR, 2668-2677","author":"Kim Been","year":"2018","unstructured":"Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, et al., 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In International conference on machine learning. PMLR, 2668-2677."},{"key":"e_1_3_2_1_10_1","volume-title":"Learning how to explain neural networks: Patternnet and patternattribution. arXiv preprint arXiv:1705.05598","author":"Kindermans Pieter-Jan","year":"2017","unstructured":"Pieter-Jan Kindermans, Kristof T Sch\u00fctt, Maximilian Alber, Klaus-Robert M\u00fcller, Dumitru Erhan, Been Kim, and Sven D\u00e4hne. 2017. Learning how to explain neural networks: Patternnet and patternattribution. arXiv preprint arXiv:1705.05598 (2017)."},{"key":"e_1_3_2_1_11_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_12_1","first-page":"5338","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","author":"Koh Pang Wei","year":"2020","unstructured":"Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, and Percy Liang. 2020a. Concept Bottleneck Models. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 5338-5348. https:\/\/proceedings.mlr.press\/v119\/koh20a.html"},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR, 5338-5348","author":"Koh Pang Wei","year":"2020","unstructured":"Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, and Percy Liang. 2020b. Concept bottleneck models. In International conference on machine learning. PMLR, 5338-5348."},{"key":"e_1_3_2_1_14_1","first-page":"740","volume-title":"Switzerland","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer vision-ECCV 2014: 13th European conference, zurich, Switzerland, September 6-12, 2014, proceedings, part v 13. Springer, 740-755."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_1_16_1","volume-title":"Interpretability beyond classification output: Semantic bottleneck networks''. arXiv preprint arXiv:1907.10882","author":"Losch Max","year":"2019","unstructured":"Max Losch, Mario Fritz, and Bernt Schiele. 2019. ''Interpretability beyond classification output: Semantic bottleneck networks''. arXiv preprint arXiv:1907.10882 (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"Promises and pitfalls of black-box concept learning models. arXiv preprint arXiv:2106.13314","author":"Mahinpei Anita","year":"2021","unstructured":"Anita Mahinpei, Justin Clark, Isaac Lage, Finale Doshi-Velez, and Weiwei Pan. 2021. Promises and pitfalls of black-box concept learning models. arXiv preprint arXiv:2106.13314 (2021)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_20_1","volume-title":"About Face: A Survey of Facial Recognition Evaluation. arXiv:2102.00813 [cs.CV] https:\/\/arxiv.org\/abs\/2102.00813","author":"Raji Inioluwa Deborah","year":"2021","unstructured":"Inioluwa Deborah Raji and Genevieve Fried. 2021. About Face: A Survey of Facial Recognition Evaluation. arXiv:2102.00813 [cs.CV] https:\/\/arxiv.org\/abs\/2102.00813"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_3_2_1_22_1","unstructured":"Julie Tores Elisa Ancarani Lucile Sassatelli Hui-Yin Wu Clement Bergman Lea Andolfi Victor Ecrement Remy Sun Frederic Precioso Thierry Devars Magali Guaresi Virginie Julliard and Sarah Lecossais. 2025. MObyGaze: a film dataset of multimodal objectification densely annotated by experts. arXiv:2505.22084 [cs.CV] https:\/\/arxiv.org\/abs\/2505.22084"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01033"},{"key":"e_1_3_2_1_24_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_25_1","unstructured":"Catherine Wah Steve Branson Peter Welinder Pietro Perona and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset."},{"key":"e_1_3_2_1_26_1","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Xie Yunfei","year":"2025","unstructured":"Yunfei Xie, Ce Zhou, Lang Gao, Juncheng Wu, Xianhang Li, Hong-Yu Zhou, Sheng Liu, Lei Xing, James Zou, Cihang Xie, and Yuyin Zhou. 2025. MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=IwgmgidYPS"},{"key":"e_1_3_2_1_27_1","unstructured":"Mert Yuksekgonul Maggie Wang and James Zou. 2022. Post-hoc Concept Bottleneck Models. In ICLR 2022 Workshop on PAIR\u22272Struct: Privacy Accountability Interpretability Robustness Reasoning on Structured Data. https:\/\/openreview.net\/forum?id=HAMeOIRD_g9"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Zarlenga Mateo Espinosa","year":"2022","unstructured":"Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna, Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Zohreh Shams, Frederic Precioso, Stefano Melacci, Adrian Weller, Pietro Lio, and Mateja Jamnik. 2022. Concept embedding models: beyond the accuracy-explainability trade-off. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '22). Curran Associates Inc., Red Hook, NY, USA, Article 1555, 14 pages."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758170","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:15:27Z","timestamp":1765307727000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758170"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":29,"alternative-id":["10.1145\/3746027.3758170","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758170","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}