{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T11:56:50Z","timestamp":1782561410005,"version":"3.54.5"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Council Hong Kong","award":["#C7129-20G"],"award-info":[{"award-number":["#C7129-20G"]}]},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["7005995"],"award-info":[{"award-number":["7005995"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tpami.2024.3380604","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T18:04:45Z","timestamp":1711130685000},"page":"5967-5985","source":"Crossref","is-referenced-by-count":23,"title":["Gradient-Based Instance-Specific Visual Explanations for Object Specification and Object Discrimination"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2233-8494","authenticated-orcid":false,"given":"Chenyang","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2271-8710","authenticated-orcid":false,"given":"Janet H.","family":"Hsiao","sequence":"additional","affiliation":[{"name":"Division of Social Science, Hong Kong University of Science & Technology, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-2513","authenticated-orcid":false,"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_25"},{"key":"ref4","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref6","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2013"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref9","article-title":"Rise: Randomized input sampling for explanation of black-box models","author":"Petsiuk","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref13","article-title":"SS-CAM: Smoothed score-cam for sharper visual feature localization","author":"Wang","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.334"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00156"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01128"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref19","article-title":"ODAM: Gradient-based instance-specific visual explanations for object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chenyang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.7312\/haza92762-003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref29","article-title":"Local explanation methods for deep neural networks lack sensitivity to parameter values","author":"Adebayo","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00510"},{"key":"ref31","article-title":"SmoothGrad: Removing noise by adding noise","author":"Smilkov","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.008"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref36","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref37","first-page":"6970","article-title":"Real time image saliency for black box classifiers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dabkowski"},{"key":"ref38","article-title":"Explaining image classifiers by counterfactual generation","author":"Chang","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00931"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_8"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref43","first-page":"4124","article-title":"Full-gradient representation for neural network visualization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Srinivas"},{"key":"ref44","first-page":"983","article-title":"Ablation-CAM: Visual explanations for deep convolutional network via gradient-free localization","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.","author":"Ramaswamy"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00400"},{"key":"ref46","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref47","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref48","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2883743"},{"key":"ref51","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref52","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.776"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00507"},{"key":"ref56","article-title":"Distilling object detectors with task adaptive regularization","author":"Sun","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00219"},{"key":"ref58","article-title":"Improve object detection with feature-based knowledge distillation: Towards accurate and efficient detectors","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00662"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412930"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref72","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref74","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref75","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2599820"},{"key":"ref77","article-title":"Visual explanation by interpretation: Improving visual feedback capabilities of deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Oramas Mogrovejo"},{"issue":"45","key":"ref78","article-title":"Individual differences in explanation strategies for image classification and implications for explainable AI","volume-title":"Proc. Annu. Meeting Cogn. Sci. Soc.","volume":"45","author":"Qi"},{"key":"ref79","article-title":"Explanation strategies for image classification in humans versus current explainable AI","author":"Qi","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12272"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00726"},{"key":"ref85","article-title":"Contrastive representation distillation","author":"Tian","year":"2019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_2"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01223"},{"key":"ref90","article-title":"Boosting adversarial robustness from the perspective of effective margin regularization","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10627928\/10478163.pdf?arnumber=10478163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T17:45:26Z","timestamp":1723052726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10478163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":90,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3380604","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}