{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T16:33:34Z","timestamp":1785256414845,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T00:00:00Z","timestamp":1650844800000},"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":[[2022,4,25]]},"DOI":"10.1145\/3485447.3512260","type":"proceedings-article","created":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T05:13:07Z","timestamp":1650863587000},"page":"3651-3655","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["On Explaining Multimodal Hateful Meme Detection Models"],"prefix":"10.1145","author":[{"given":"Ming Shan","family":"Hee","sequence":"first","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roy Ka-Wei","family":"Lee","sequence":"additional","affiliation":[{"name":"Singapore University of Technology and Design, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen-Haw","family":"Chong","sequence":"additional","affiliation":[{"name":"Singapore Management University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,4,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30-May 3, 2018, Conference Track Proceedings. OpenReview. net.","author":"Ancona Marco","year":"2018","unstructured":"Marco Ancona, Enea Ceolini, Cengiz \u00d6ztireli, and Markus Gross. 2018. Towards better understanding of gradient-based attribution methods for Deep Neural Networks. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30-May 3, 2018, Conference Track Proceedings. OpenReview. net."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313504"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_34"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3504"},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).","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_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.775"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093414"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_10_1","unstructured":"Yash Goyal Akrit Mohapatra Devi Parikh and Dhruv Batra. 2016. Towards transparent ai systems: Interpreting visual question answering models. arXiv preprint arXiv:1608.08974(2016)."},{"key":"e_1_3_2_1_11_1","volume-title":"A survey of methods for explaining black box models. ACM computing surveys (CSUR) 51, 5","author":"Guidotti Riccardo","year":"2018","unstructured":"Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, and Dino Pedreschi. 2018. A survey of methods for explaining black box models. ACM computing surveys (CSUR) 51, 5 (2018), 1\u201342."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.483"},{"key":"e_1_3_2_1_13_1","volume-title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. Advances in Neural Information Processing Systems 33","author":"Kiela Douwe","year":"2020","unstructured":"Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes. Advances in Neural Information Processing Systems 33 (2020)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Goro Kobayashi Tatsuki Kuribayashi Sho Yokoi and Kentaro Inui. 2020. Attention is not only a weight: Analyzing transformers with vector norms. arXiv preprint arXiv:2004.10102(2020).","DOI":"10.18653\/v1\/2020.emnlp-main.574"},{"key":"e_1_3_2_1_15_1","volume-title":"Captum: A unified and generic model interpretability library for pytorch. arXiv preprint arXiv:2009.07896(2020).","author":"Kokhlikyan Narine","year":"2020","unstructured":"Narine Kokhlikyan, Vivek Miglani, Miguel Martin, Edward Wang, Bilal Alsallakh, Jonathan Reynolds, Alexander Melnikov, Natalia Kliushkina, Carlos Araya, Siqi Yan, 2020. Captum: A unified and generic model interpretability library for pytorch. arXiv preprint arXiv:2009.07896(2020)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475625"},{"key":"e_1_3_2_1_17_1","volume-title":"Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557(2019).","author":"Li Liunian\u00a0Harold","year":"2019","unstructured":"Liunian\u00a0Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang. 2019. Visualbert: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557(2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_20_1","unstructured":"Phillip Lippe Nithin Holla Shantanu Chandra Santhosh Rajamanickam Georgios Antoniou Ekaterina Shutova and Helen Yannakoudakis. 2020. A multimodal framework for the detection of hateful memes. arXiv preprint arXiv:2012.12871(2020)."},{"key":"e_1_3_2_1_21_1","unstructured":"Jiasen Lu Dhruv Batra Devi Parikh and Stefan Lee. 2019. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. In NeurIPS."},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR). 32\u201344","author":"Parcalabescu Letitia","year":"2021","unstructured":"Letitia Parcalabescu, Albert Gatt, Anette Frank, and Iacer Calixto. 2021. Seeing past words: Testing the cross-modal capabilities of pretrained v&l models on counting tasks. In Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR). 32\u201344."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093295"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"e_1_3_2_1_25_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015), 91\u201399."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_28_1","unstructured":"Karen Simonyan Andrea Vedaldi and Andrew Zisserman. 2013. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034(2013)."},{"key":"e_1_3_2_1_29_1","volume-title":"Meet Shah, Marcus Rohrbach, Dhruv Batra, and Devi Parikh.","author":"Singh Amanpreet","year":"2020","unstructured":"Amanpreet Singh, Vedanuj Goswami, Vivek Natarajan, Yu Jiang, Xinlei Chen, Meet Shah, Marcus Rohrbach, Dhruv Batra, and Devi Parikh. 2020. MMF: A multimodal framework for vision and language research. https:\/\/github.com\/facebookresearch\/mmf."},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 3319\u20133328","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\u20133328."},{"key":"e_1_3_2_1_31_1","unstructured":"Riza Velioglu and Jewgeni Rose. 2020. Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge. arXiv preprint arXiv:2012.12975(2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.socialnlp-1.2"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.274"},{"key":"e_1_3_2_1_35_1","volume-title":"Multimodal Learning For Hateful Memes Detection. In 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 1\u20136.","author":"Zhou Yi","year":"2021","unstructured":"Yi Zhou, Zhenhao Chen, and Huiyuan Yang. 2021. Multimodal Learning For Hateful Memes Detection. In 2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). IEEE, 1\u20136."},{"key":"e_1_3_2_1_36_1","unstructured":"Ron Zhu. 2020. Enhance multimodal transformer with external label and in-domain pretrain: Hateful meme challenge winning solution. arXiv preprint arXiv:2012.08290(2020)."}],"event":{"name":"WWW '22: The ACM Web Conference 2022","location":"Virtual Event, Lyon France","acronym":"WWW '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2022"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512260","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485447.3512260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:14Z","timestamp":1750188614000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485447.3512260"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,25]]},"references-count":36,"alternative-id":["10.1145\/3485447.3512260","10.1145\/3485447"],"URL":"https:\/\/doi.org\/10.1145\/3485447.3512260","relation":{},"subject":[],"published":{"date-parts":[[2022,4,25]]},"assertion":[{"value":"2022-04-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}