{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:23Z","timestamp":1750309523165,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":42,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032015"],"award-info":[{"award-number":["62032015"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680866","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"5365-5373","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Effective Optimization of Root Selection Towards Improved Explanation of Deep Classifiers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8339-2457","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7524-5999","authenticated-orcid":false,"given":"Shenghua","family":"Zhong","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7576-3999","authenticated-orcid":false,"given":"Jianmin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, Guangdong, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Sanity checks for saliency maps. Advances in neural information processing systems","author":"Adebayo Julius","year":"2018","unstructured":"Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, and Been Kim. 2018. Sanity checks for saliency maps. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_2_1","volume-title":"Understanding Deep Neural Networks with Rectified Linear Units. In International Conference on Learning Representations.","author":"Arora Raman","year":"2018","unstructured":"Raman Arora, Amitabh Basu, Poorya Mianjy, and Anirbit Mukherjee. 2018. Understanding Deep Neural Networks with Rectified Linear Units. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/1756006.1859912"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44781-0_8"},{"key":"e_1_3_2_1_6_1","volume-title":"Optimising for Interpretability: Convolutional Dynamic Alignment Networks","author":"B\u00f6hle Moritz","year":"2022","unstructured":"Moritz B\u00f6hle, Mario Fritz, and Bernt Schiele. 2022. Optimising for Interpretability: Convolutional Dynamic Alignment Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548260"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547742"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TRPMS.2021.3066428"},{"key":"e_1_3_2_1_12_1","volume-title":"Large-scale unsupervised semantic segmentation","author":"Gao Shanghua","year":"2022","unstructured":"Shanghua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, and Philip Torr. 2022. Large-scale unsupervised semantic segmentation. IEEE transactions on pattern analysis and machine intelligence (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Computer Vision--ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2--6","author":"Gu Jindong","year":"2018","unstructured":"Jindong Gu, Yinchong Yang, and Volker Tresp. 2019. Understanding individual decisions of cnns via contrastive backpropagation. In Computer Vision--ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2--6, 2018, Revised Selected Papers, Part III 14. Springer, 119--134."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17374"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.10.067"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00513"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Learning Representations.","author":"Kindermans Pieter-Jan","year":"2018","unstructured":"Pieter-Jan Kindermans, Kristof T Sch\u00fctt, Maximilian Alber, Klaus-Robert M\u00fcller, Dumitru Erhan, Been Kim, and Sven D\u00e4hne. 2018. Learning how to explain neural networks: PatternNet and PatternAttribution. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548387"},{"key":"e_1_3_2_1_20_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_21_1","volume-title":"International Conference on Learning Representations.","author":"Madry Aleksander","year":"2018","unstructured":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. 2018. Towards Deep Learning Models Resistant to Adversarial Attacks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3546577"},{"key":"e_1_3_2_1_23_1","volume-title":"Layer-wise relevance propagation: an overview. Explainable AI: interpreting, explaining and visualizing deep learning","author":"Montavon Gr\u00e9goire","year":"2019","unstructured":"Gr\u00e9goire Montavon, Alexander Binder, Sebastian Lapuschkin, Wojciech Samek, and Klaus-Robert M\u00fcller. 2019. Layer-wise relevance propagation: an overview. Explainable AI: interpreting, explaining and visualizing deep learning (2019), 193--209."},{"key":"e_1_3_2_1_24_1","volume-title":"Explaining nonlinear classification decisions with deep taylor decomposition. Pattern recognition","author":"Montavon Gr\u00e9goire","year":"2017","unstructured":"Gr\u00e9goire Montavon, Sebastian Lapuschkin, Alexander Binder, Wojciech Samek, and Klaus-Robert M\u00fcller. 2017. Explaining nonlinear classification decisions with deep taylor decomposition. Pattern recognition, Vol. 65 (2017), 211--222."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5632"},{"key":"e_1_3_2_1_26_1","volume-title":"Model agnostic multilevel explanations. Advances in neural information processing systems","author":"Ramamurthy Karthikeyan Natesan","year":"2020","unstructured":"Karthikeyan Natesan Ramamurthy, Bhanukiran Vinzamuri, Yunfeng Zhang, and Amit Dhurandhar. 2020. Model agnostic multilevel explanations. Advances in neural information processing systems, Vol. 33 (2020), 5968--5979."},{"key":"e_1_3_2_1_27_1","volume-title":"Smooth grad-cam: An enhanced inference level visualization technique for deep convolutional neural network models. arXiv preprint arXiv:1908.01224","author":"Omeiza Daniel","year":"2019","unstructured":"Daniel Omeiza, Skyler Speakman, Celia Cintas, and Komminist Weldermariam. 2019. Smooth grad-cam: An enhanced inference level visualization technique for deep convolutional neural network models. arXiv preprint arXiv:1908.01224 (2019)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"e_1_3_2_1_29_1","volume-title":"Model agnostic supervised local explanations. Advances in neural information processing systems","author":"Plumb Gregory","year":"2018","unstructured":"Gregory Plumb, Denali Molitor, and Ameet S Talwalkar. 2018. Model agnostic supervised local explanations. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_30_1","volume-title":"Rainbows revisited: Modeling effective colormap design for graphical inference","author":"Reda Khairi","year":"2020","unstructured":"Khairi Reda and Danielle Albers Szafir. 2020. Rainbows revisited: Modeling effective colormap design for graphical inference. IEEE transactions on visualization and computer graphics, Vol. 27, 2 (2020), 1032--1042."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 3145--3153","author":"Shrikumar Avanti","year":"2017","unstructured":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. 2017. Learning important features through propagating activation differences. In International conference on machine learning. PMLR, 3145--3153."},{"key":"e_1_3_2_1_34_1","volume-title":"Not just a black box: Learning important features through propagating activation differences. arXiv preprint arXiv:1605.01713","author":"Shrikumar Avanti","year":"2016","unstructured":"Avanti Shrikumar, Peyton Greenside, Anna Shcherbina, and Anshul Kundaje. 2016. Not just a black box: Learning important features through propagating activation differences. arXiv preprint arXiv:1605.01713 (2016)."},{"key":"e_1_3_2_1_35_1","volume-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034","author":"Simonyan Karen","year":"2013","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_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00438"},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Machine Learning. PMLR, 9046--9057","author":"Sixt Leon","year":"2020","unstructured":"Leon Sixt, Maximilian Granz, and Tim Landgraf. 2020. When explanations lie: Why many modified bp attributions fail. In International Conference on Machine Learning. PMLR, 9046--9057."},{"key":"e_1_3_2_1_38_1","volume-title":"A Rigorous Study Of The Deep Taylor Decomposition. Transactions on Machine Learning Research","author":"Sixt Leon","year":"2022","unstructured":"Leon Sixt and Tim Landgraf. 2022. A Rigorous Study Of The Deep Taylor Decomposition. Transactions on Machine Learning Research (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Full-gradient representation for neural network visualization. Advances in neural information processing systems","author":"Srinivas Suraj","year":"2019","unstructured":"Suraj Srinivas and Franccois Fleuret. 2019. Full-gradient representation for neural network visualization. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524273.3533925"},{"key":"e_1_3_2_1_41_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_42_1","volume-title":"International Conference on Machine Learning. PMLR, 10514--10523","author":"Xiong Huan","year":"2020","unstructured":"Huan Xiong, Lei Huang, Mengyang Yu, Li Liu, Fan Zhu, and Ling Shao. 2020. On the number of linear regions of convolutional neural networks. In International Conference on Machine Learning. PMLR, 10514--10523."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3100641"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680866","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680866"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":42,"alternative-id":["10.1145\/3664647.3680866","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680866","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"}}]}}