{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T18:10:07Z","timestamp":1744049407580,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819626434"},{"type":"electronic","value":"9789819626441"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-2644-1_3","type":"book-chapter","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T17:29:15Z","timestamp":1744046955000},"page":"31-46","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CROCODILE: Crop-Based Contrastive Discriminative Learning for\u00a0Enhancing Explainability of\u00a0End-to-End Driving Models"],"prefix":"10.1007","author":[{"given":"Chenkai","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daisuke","family":"Deguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenzhen","family":"Quan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hiroshi","family":"Murase","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,28]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108421","volume":"123","author":"H Ben-Younes","year":"2022","unstructured":"Ben-Younes, H., Zablocki, \u00c9., P\u00e9rez, P., Cord, M.: Driving behavior explanation with multi-level fusion. Pattern Recogn. 123, 108421 (2022)","journal-title":"Pattern Recogn."},{"key":"3_CR2","unstructured":"Bojarski, M., et al.: Visualbackprop: visualizing CNNs for autonomous driving 2, 1\u20132. arXiv preprint arXiv:1611.05418 (2016)"},{"key":"3_CR3","unstructured":"Bojarski, M., et\u00a0al.: End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316 (2016)"},{"key":"3_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"5","key":"3_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 1\u201342 (2018)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: CCNet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Jin, B., et al.: Adapt: action-aware driving caption transformer. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 7554\u20137561. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160326"},{"key":"3_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1007\/978-3-030-01216-8_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Kim","year":"2018","unstructured":"Kim, J., Rohrbach, A., Darrell, T., Canny, J., Akata, Z.: Textual explanations for self-driving vehicles. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 577\u2013593. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_35"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Mori, K., Fukui, H., Murase, T., Hirakawa, T., Yamashita, T., Fujiyoshi, H.: Visual explanation by attention branch network for end-to-end learning-based self-driving. In: 2019 IEEE Intelligent Vehicles Symposium (IV), pp. 1577\u20131582. IEEE (2019)","DOI":"10.1109\/IVS.2019.8813900"},{"key":"3_CR14","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"3_CR15","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1613\/jair.1.13200","volume":"73","author":"G Ras","year":"2022","unstructured":"Ras, G., Xie, N., Van Gerven, M., Doran, D.: Explainable deep learning: a field guide for the uninitiated. J. Artif. Intell. Res. 73, 329\u2013396 (2022)","journal-title":"J. Artif. Intell. Res."},{"issue":"4","key":"3_CR16","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1109\/TNNLS.2020.3043505","volume":"33","author":"A Tampuu","year":"2020","unstructured":"Tampuu, A., Matiisen, T., Semikin, M., Fishman, D., Muhammad, N.: A survey of end-to-end driving: architectures and training methods. IEEE Trans. Neural Netw. Learn. Syst. 33(4), 1364\u20131384 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Wang, D., Devin, C., Cai, Q.Z., Yu, F., Darrell, T.: Deep object-centric policies for autonomous driving. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 8853\u20138859. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794224"},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.X., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3733\u20133742 (2018)","DOI":"10.1109\/CVPR.2018.00393"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Xu, H., Gao, Y., Yu, F., Darrell, T.: End-to-end learning of driving models from large-scale video datasets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2174\u20132182 (2017)","DOI":"10.1109\/CVPR.2017.376"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Explainable object-induced action decision for autonomous vehicles. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9523\u20139532 (2020)","DOI":"10.1109\/CVPR42600.2020.00954"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Drivegpt4: Interpretable end-to-end autonomous driving via large language model. arXiv preprint arXiv:2310.01412 (2023)","DOI":"10.1109\/LRA.2024.3440097"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"3_CR24","doi-asserted-by":"publisher","first-page":"14521","DOI":"10.1109\/TITS.2024.3385754","volume":"25","author":"C Zhang","year":"2024","unstructured":"Zhang, C., Deguchi, D., Chen, J., Murase, H.: Toward explainable end-to-end driving models via simplified objectification constraints. IEEE Trans. Intell. Transp. Syst. 25, 14521\u201314534 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, C., Deguchi, D., Murase, H.: Refined objectification for improving end-to-end driving model explanation persuasibility. In: 2023 IEEE Intelligent Vehicles Symposium (IV), pp.\u00a01\u20136. IEEE (2023)","DOI":"10.1109\/IV55152.2023.10186742"},{"key":"3_CR26","doi-asserted-by":"publisher","first-page":"4270","DOI":"10.1109\/ACCESS.2023.3235739","volume":"11","author":"C Zhang","year":"2023","unstructured":"Zhang, C., Deguchi, D., Okafuji, Y., Murase, H.: More persuasive explanation method for end-to-end driving models. IEEE Access 11, 4270\u20134282 (2023)","journal-title":"IEEE Access"},{"key":"3_CR27","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"issue":"5","key":"3_CR28","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1109\/TETCI.2021.3100641","volume":"5","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Ti\u0148o, P., Leonardis, A., Tang, K.: A survey on neural network interpretability. IEEE Trans. Emerg. Topics Comput. Intell. 5(5), 726\u2013742 (2021)","journal-title":"IEEE Trans. Emerg. Topics Comput. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2644-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T17:29:23Z","timestamp":1744046963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2644-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819626434","9789819626441"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2644-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"28 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}