{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:44:08Z","timestamp":1782967448410,"version":"3.54.5"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172122"],"award-info":[{"award-number":["62172122"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["93K172021K04"],"award-info":[{"award-number":["93K172021K04"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["2021ZD0200406"],"award-info":[{"award-number":["2021ZD0200406"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s12652-022-04354-2","type":"journal-article","created":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T05:04:39Z","timestamp":1661749479000},"page":"163-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Attribution rollout: a new way to interpret visual transformer"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4950-0789","authenticated-orcid":false,"given":"Li","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyue","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zechao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,29]]},"reference":[{"key":"4354_CR1","doi-asserted-by":"crossref","unstructured":"Abnar S, Zuidema W (2020) Quantifying attention flow in transformers. arXiv:2005.00928","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"4354_CR2","unstructured":"Adebayo J, Gilmer J, Muelly M et al (2018) Sanity checks for saliency maps. arXiv:1810.03292"},{"key":"4354_CR3","doi-asserted-by":"crossref","unstructured":"Binder A, Montavon G, Lapuschkin S et\u00a0al (2016) Layer-wise relevance propagation for neural networks with local renormalization layers. In: International conference on artificial neural networks. Springer, pp 63\u201371","DOI":"10.1007\/978-3-319-44781-0_8"},{"key":"4354_CR4","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G et\u00a0al (2020) End-to-end object detection with transformers. In: European conference on computer vision. Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"4354_CR5","doi-asserted-by":"crossref","unstructured":"Chefer H, Gur S, Wolf L (2021) Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 782\u2013791","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"4354_CR6","unstructured":"Chen J, Song L, Wainwright MJ et\u00a0al (2018) L-shapley and c-shapley: Efficient model interpretation for structured data. arXiv:1808.02610"},{"key":"4354_CR7","unstructured":"Chen M, Radford A, Child R et\u00a0al (2020) Generative pretraining from pixels. In: International conference on machine learning, PMLR, pp 1691\u20131703"},{"key":"4354_CR8","doi-asserted-by":"crossref","unstructured":"Cheng J, Dong L, Lapata M (2016) Long short-term memory-networks for machine reading. arXiv:1601.06733","DOI":"10.18653\/v1\/D16-1053"},{"key":"4354_CR9","unstructured":"Devlin J, Chang MW, Lee K et\u00a0al (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"key":"4354_CR10","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A et\u00a0al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv:2010.11929"},{"issue":"3","key":"4354_CR11","first-page":"1","volume":"1341","author":"D Erhan","year":"2009","unstructured":"Erhan D, Bengio Y, Courville A et al (2009) Visualizing higher-layer features of a deep network. Univ Montreal 1341(3):1","journal-title":"Univ Montreal"},{"key":"4354_CR12","doi-asserted-by":"crossref","unstructured":"Fong RC, Vedaldi A (2017) Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE international conference on computer vision, pp 3429\u20133437","DOI":"10.1109\/ICCV.2017.371"},{"key":"4354_CR13","doi-asserted-by":"crossref","unstructured":"Fong R, Patrick M, Vedaldi A (2019) Understanding deep networks via extremal perturbations and smooth masks. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 2950\u20132958","DOI":"10.1109\/ICCV.2019.00304"},{"key":"4354_CR14","doi-asserted-by":"crossref","unstructured":"Gu J, Yang Y, Tresp V (2018) Understanding individual decisions of cnns via contrastive backpropagation. In: Asian conference on computer vision. Springer, pp 119\u2013134","DOI":"10.1007\/978-3-030-20893-6_8"},{"issue":"3","key":"4354_CR15","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/s11263-014-0713-9","volume":"110","author":"M Guillaumin","year":"2014","unstructured":"Guillaumin M, K\u00fcttel D, Ferrari V (2014) Imagenet auto-annotation with segmentation propagation. Int J Comput Vis 110(3):328\u2013348","journal-title":"Int J Comput Vis"},{"key":"4354_CR16","doi-asserted-by":"crossref","unstructured":"Gur S, Ali A, Wolf L (2021) Visualization of supervised and self-supervised neural networks via attribution guided factorization. In: Proceedings of the AAAI conference on artificial intelligence, pp 11545\u201311554","DOI":"10.1609\/aaai.v35i13.17374"},{"key":"4354_CR17","doi-asserted-by":"crossref","unstructured":"Hao Y, Dong L, Wei F et\u00a0al (2020) Self-attention attribution: interpreting information interactions inside transformer. arXiv:2004.11207","DOI":"10.1609\/aaai.v35i14.17533"},{"key":"4354_CR18","doi-asserted-by":"crossref","unstructured":"Iwana BK, Kuroki R, Uchida S (2019) Explaining convolutional neural networks using softmax gradient layer-wise relevance propagation. In: 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW), pp 4176\u20134185","DOI":"10.1109\/ICCVW.2019.00513"},{"key":"4354_CR19","doi-asserted-by":"crossref","unstructured":"Li K, Wu Z, Peng KC et\u00a0al (2018) Tell me where to look: guided attention inference network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9215\u20139223","DOI":"10.1109\/CVPR.2018.00960"},{"key":"4354_CR20","unstructured":"Lu J, Batra D, Parikh D et\u00a0al (2019) Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. arXiv:1908.02265"},{"key":"4354_CR21","unstructured":"Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems, pp 4768\u20134777"},{"issue":"3","key":"4354_CR22","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s11263-016-0911-8","volume":"120","author":"A Mahendran","year":"2016","unstructured":"Mahendran A, Vedaldi A (2016) Visualizing deep convolutional neural networks using natural pre-images. Int J Comput Vis 120(3):233\u2013255","journal-title":"Int J Comput Vis"},{"key":"4354_CR23","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.patcog.2016.11.008","volume":"65","author":"G Montavon","year":"2017","unstructured":"Montavon G, Lapuschkin S, Binder A et al (2017) Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn 65:211\u2013222","journal-title":"Pattern Recogn"},{"key":"4354_CR24","unstructured":"Murdoch WJ, Liu PJ, Yu B (2018) Beyond word importance: Contextual decomposition to extract interactions from lstms. arXiv:1801.05453"},{"key":"4354_CR25","doi-asserted-by":"crossref","unstructured":"Nam WJ, Gur S, Choi J et\u00a0al (2020) Relative attributing propagation: interpreting the comparative contributions of individual units in deep neural networks. In: Proceedings of the AAAI conference on artificial intelligence, pp 2501\u20132508","DOI":"10.1609\/aaai.v34i03.5632"},{"issue":"1","key":"4354_CR26","doi-asserted-by":"publisher","first-page":"207","DOI":"10.3390\/s20010207","volume":"20","author":"Y Ren","year":"2020","unstructured":"Ren Y, Zhu F, Sharma PK et al (2020) Data query mechanism based on hash computing power of blockchain in internet of things. Sensors 20(1):207","journal-title":"Sensors"},{"key":"4354_CR27","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1016\/j.future.2020.09.019","volume":"115","author":"Y Ren","year":"2021","unstructured":"Ren Y, Leng Y, Qi J et al (2021) Multiple cloud storage mechanism based on blockchain in smart homes. Future Gener Comput Syst 115:304\u2013313","journal-title":"Future Gener Comput Syst"},{"issue":"3","key":"4354_CR28","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"4354_CR29","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A et al (2017) Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"4354_CR30","unstructured":"Shrikumar A, Greenside P, Shcherbina A et\u00a0al (2016) Not just a black box: learning important features through propagating activation differences. arXiv:1605.01713"},{"key":"4354_CR31","unstructured":"Shrikumar A, Greenside P, Kundaje A (2017) Learning important features through propagating activation differences. In: International conference on machine learning, PMLR, pp 3145\u20133153"},{"key":"4354_CR32","unstructured":"Simonyan K, Vedaldi A, Zisserman A (2013) Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv:1312.6034"},{"key":"4354_CR33","unstructured":"Singh C, Murdoch WJ, Yu B (2018) Hierarchical interpretations for neural network predictions. arXiv:1806.05337"},{"key":"4354_CR34","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: International conference on machine learning, PMLR, pp 3319\u20133328"},{"key":"4354_CR35","doi-asserted-by":"crossref","unstructured":"Tan H, Bansal M (2019) Lxmert: learning cross-modality encoder representations from transformers. arXiv:1908.07490","DOI":"10.18653\/v1\/D19-1514"},{"key":"4354_CR36","unstructured":"Vaswani A, Shazeer N, Parmar N et\u00a0al (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"4354_CR37","doi-asserted-by":"crossref","unstructured":"Voita E, Talbot D, Moiseev F et\u00a0al (2019) Analyzing multi-head self-attention: Specialized heads do the heavy lifting, the rest can be pruned. arXiv:1905.09418","DOI":"10.18653\/v1\/P19-1580"},{"key":"4354_CR38","doi-asserted-by":"crossref","unstructured":"Wang H, Wang Z, Du M et\u00a0al (2020) Score-cam: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 24\u201325","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"4354_CR39","unstructured":"Xu K, Ba J, Kiros R et\u00a0al (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning, PMLR, pp 2048\u20132057"},{"key":"4354_CR40","unstructured":"Yuan T, Li X, Xiong H et\u00a0al (2021) Explaining information flow inside vision transformers using Markov chain. In: eXplainable AI approaches for debugging and diagnosis"},{"key":"4354_CR41","doi-asserted-by":"crossref","unstructured":"Yun J, Basak M, Han MM (2021) Bayesian rule modeling for interpretable mortality classification of Covid-19 patients. In: Cmc-Computers Materials & Continua, pp 2827\u20132843","DOI":"10.32604\/cmc.2021.017266"},{"key":"4354_CR42","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"10","key":"4354_CR43","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1007\/s11263-017-1059-x","volume":"126","author":"J Zhang","year":"2018","unstructured":"Zhang J, Bargal SA, Lin Z et al (2018) Top-down neural attention by excitation backprop. Int J Comput Vis 126(10):1084\u20131102","journal-title":"Int J Comput Vis"},{"issue":"2","key":"4354_CR44","doi-asserted-by":"publisher","first-page":"3035","DOI":"10.32604\/cmc.2022.022304","volume":"71","author":"XR Zhang","year":"2022","unstructured":"Zhang XR, Sun X, Sun XM et al (2022) Robust reversible audio watermarking scheme for telemedicine and privacy protection. Comput Mater Continua 71(2):3035\u20133050","journal-title":"Comput Mater Continua"},{"issue":"3","key":"4354_CR45","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.32604\/csse.2022.022305","volume":"41","author":"XR Zhang","year":"2022","unstructured":"Zhang XR, Zhang WF, Sun W et al (2022) A robust 3-d medical watermarking based on wavelet transform for data protection. Comput Syst Sci Eng 41(3):1043\u20131056","journal-title":"Comput Syst Sci Eng"},{"key":"4354_CR46","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A et al (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921\u20132929","DOI":"10.1109\/CVPR.2016.319"},{"issue":"9","key":"4354_CR47","doi-asserted-by":"publisher","first-page":"2131","DOI":"10.1109\/TPAMI.2018.2858759","volume":"41","author":"B Zhou","year":"2018","unstructured":"Zhou B, Bau D, Oliva A et al (2018) Interpreting deep visual representations via network dissection. IEEE Trans Pattern Anal Mach Intell 41(9):2131\u20132145","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-022-04354-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-022-04354-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-022-04354-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T18:37:03Z","timestamp":1673635023000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-022-04354-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["4354"],"URL":"https:\/\/doi.org\/10.1007\/s12652-022-04354-2","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"20 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}