{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T23:20:02Z","timestamp":1768778402586,"version":"3.49.0"},"reference-count":25,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,8,1]]},"DOI":"10.1587\/transinf.2021edp7205","type":"journal-article","created":{"date-parts":[[2022,7,31]],"date-time":"2022-07-31T22:19:38Z","timestamp":1659305978000},"page":"1401-1417","source":"Crossref","is-referenced-by-count":3,"title":["SeCAM: Tightly Accelerate the Image Explanation via Region-Based Segmentation"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Phong X.","family":"NGUYEN","sequence":"first","affiliation":[{"name":"Graduate School of Engineering Advanced Interdisciplinary Studies, The University of Tokyo"}]},{"given":"Hung","family":"Q. CAO","sequence":"additional","affiliation":[{"name":"Quy Nhon AI, FPT Software"}]},{"given":"Khang","family":"V. T. NGUYEN","sequence":"additional","affiliation":[{"name":"Quy Nhon AI, FPT Software"}]},{"given":"Hung","family":"NGUYEN","sequence":"additional","affiliation":[{"name":"Quy Nhon AI, FPT Software"}]},{"given":"Takehisa","family":"YAIRI","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Advanced Interdisciplinary Studies, The University of Tokyo"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] S. Mohseni, N. Zarei, and E.D. Ragan, \u201cA multidisciplinary survey and framework for design and evaluation of explainable ai systems,\u201d vol.11, no.3-4, Article No.24, pp.1-45Dec. 2020. 10.1145\/3387166","DOI":"10.1145\/3387166"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] A. Adadi and M. Berrada, \u201cPeeking inside the black-box: A survey on explainable artificial intelligence (xai),\u201d IEEE Access, vol.6, pp.52138-52160, 2018. 10.1109\/ACCESS.2018.2870052","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"3","unstructured":"[3] M. Du, N. Liu, and X. Hu, \u201cTechniques for interpretable machine learning,\u201d CoRR, vol.abs\/1808.00033, 2018. 10.48550\/arXiv.1808.00033"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] M.T. Ribeiro, S. Singh, and C. Guestrin, \u201c\u201cWhy should I trust you?\u201d: Explaining the predictions of any classifier,\u201d CoRR, vol.abs\/1602.04938, 2016. 10.48550\/arXiv.1602.04938","DOI":"10.1145\/2939672.2939778"},{"key":"5","unstructured":"[5] S. Lundberg and S. Lee, \u201cA unified approach to interpreting model predictions,\u201d CoRR, vol.abs\/1705.07874, 2017. 10.48550\/arXiv.1705.07874"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] B. Zhou, A. Khosla, \u00c0. Lapedriza, A. Oliva, and A. Torralba, \u201cLearning deep features for discriminative localization,\u201d CoRR, vol.abs\/1512.04150, 2015. 10.48550\/arXiv.1512.04150","DOI":"10.1109\/CVPR.2016.319"},{"key":"7","unstructured":"[7] S. Sattarzadeh, M. Sudhakar, A. Lem, S. Mehryar, K.N. Plataniotis, J. Jang, H. Kim, Y. Jeong, S. Lee, and K. Bae, \u201cExplaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation,\u201d CoRR, vol.abs\/2010.00672, 2020. 10.48550\/arXiv.2010.00672"},{"key":"8","unstructured":"[8] T.N. Mundhenk, B.Y. Chen, and G. Friedland, \u201cEfficient saliency maps for explainable AI,\u201d CoRR, vol.abs\/1911.11293, 2019. 10.48550\/arXiv.1911.11293"},{"key":"9","unstructured":"[9] S. Shi, X. Zhang, and W. Fan, \u201cA modified perturbed sampling method for local interpretable model-agnostic explanation,\u201d 2020. 10.48550\/arXiv.2002.07434"},{"key":"10","unstructured":"[10] R. Achanta, A. Shaji, K. Smith, A. Lucchi, P. Fua, and S. Susstrunk, \u201cSlic superpixels,\u201d Technical report, EPFL, June 2010."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] M.T. Ribeiro, S. Singh, and C. Guestrin, \u201cAnchors: High-precision model-agnostic explanations,\u201d AAAI Conf. Artifi. Intelli., (AAAI), Feb. 2018.","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"12","unstructured":"[12] D. Stutz, A. Hermans, and B. Leibe, \u201cSuperpixels: An evaluation of the state-of-the-art,\u201d CoRR, vol.abs\/1612.01601, 2016. 10.48550\/arXiv.1612.01601"},{"key":"13","unstructured":"[13] M. Sundararajan, J. Xu, A. Taly, R. Sayres, and A. Najmi, \u201cExploring principled visualizations for deep network attributions,\u201d IUI Workshops, 2019."},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] S. Zhang, C. Li, S. Qiu, C. Gao, F. Zhang, Z. Du, and R. Liu, \u201cEMMCNN: An ETPS-based multi-scale and multi-feature method using CNN for high spatial resolution image land-cover classification,\u201d Remote Sensing, vol.12, no.1, 2020. 10.3390\/rs12010066","DOI":"10.3390\/rs12010066"},{"key":"15","unstructured":"[15] M.V. den Bergh, X. Boix, G. Roig, and L.V. Gool, \u201cSEEDS: superpixels extracted via energy-driven sampling,\u201d CoRR, vol.abs\/1309. 3848, 2013. 10.48550\/arXiv.1309.3848"},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] A. Vedaldi and S. Soatto, \u201cQuick shift and kernel methods for mode seeking,\u201d Comput. Vis.-ECCV 2008, ed. D. Forsyth, P. Torr, and A. Zisserman, Berlin, Heidelberg, pp.705-718, Springer Berlin Heidelberg, 2008. 10.1007\/978-3-540-88693-8_52","DOI":"10.1007\/978-3-540-88693-8_52"},{"key":"17","doi-asserted-by":"publisher","unstructured":"[17] R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, \u201cGrad-cam: Visual explanations from deep networks via gradient-based localization,\u201d Int. J. Comput. Vis., vol.128, no.2, p.336-359, Oct. 2019. 10.1007\/s11263-019-01228-7","DOI":"10.1007\/s11263-019-01228-7"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] A. Kapishnikov, T. Bolukbasi, F.B. Vi\u00e9gas, and M. Terry, \u201cSegment integrated gradients: Better attributions through regions,\u201d CoRR, vol.abs\/1906.02825, 2019. 10.48550\/arXiv.1906.02825","DOI":"10.1109\/ICCV.2019.00505"},{"key":"19","unstructured":"[19] H. Wang, M. Du, F. Yang, and Z. Zhang, \u201cScore-cam: Improved visual explanations via score-weighted class activation mapping,\u201d CoRR, vol.abs\/1910.01279, 2019."},{"key":"20","unstructured":"[20] T. Rojat, R. Puget, D. Filliat, J.D. Ser, R. Gelin, and N.D. Rodr\u00edguez, \u201cExplainable artificial intelligence (XAI) on timeseries data: A survey,\u201d CoRR, vol.abs\/2104.00950, 2021. 10.48550\/arXiv.2104.00950"},{"key":"21","unstructured":"[21] V. Petsiuk, A. Das, and K. Saenko, \u201cRISE: randomized input sampling for explanation of black-box models,\u201d CoRR, vol.abs\/1806.07421, 2018. 10.48550\/arXiv.1806.07421"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] M.A.A.K. Jalwana, N. Akhtar, M. Bennamoun, and A. Mian, \u201cCAMERAS: enhanced resolution and sanity preserving class activation mapping for image saliency,\u201d CoRR, vol.abs\/2106.10649, 2021. 10.48550\/arXiv.2106.10649","DOI":"10.1109\/CVPR46437.2021.01606"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] I. Palatnik de Sousa, M. Maria Bernardes Rebuzzi Vellasco, and E. Costa da Silva, \u201cLocal interpretable model-agnostic explanations for classification of lymph node metastases,\u201d Sensors, vol.19, no.13, 2019. 10.3390\/s19132969","DOI":"10.3390\/s19132969"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] W.b. Chen and X. Zhang, \u201cA new watershed algorithm for cellular image segmentation based on mathematical morphology,\u201d 2010 Int. Conf. Machine Vision and Human-machine Interface, pp.653-656, 2010. 10.1109\/MVHI.2010.55","DOI":"10.1109\/MVHI.2010.55"},{"key":"25","unstructured":"[25] S. Nanjundan, S. Sankaran, C.R. Arjun, and G.P. Anand, \u201cIdentifying the number of clusters for k-means: A hypersphere density based approach,\u201d CoRR, vol.abs\/1912.00643, 2019. 10.48550\/arXiv.1912.00643"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/8\/E105.D_2021EDP7205\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,6]],"date-time":"2022-08-06T03:35:47Z","timestamp":1659756947000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/8\/E105.D_2021EDP7205\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,1]]},"references-count":25,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021edp7205","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,1]]},"article-number":"2021EDP7205"}}