{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T22:32:08Z","timestamp":1769725928126,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["MOST 110-2221-E-002-121"],"award-info":[{"award-number":["MOST 110-2221-E-002-121"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology of Taiwan","doi-asserted-by":"publisher","award":["110-2634-F-002-052"],"award-info":[{"award-number":["110-2634-F-002-052"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3268001","type":"journal-article","created":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T18:30:23Z","timestamp":1682101823000},"page":"2481-2492","source":"Crossref","is-referenced-by-count":9,"title":["Describe, Spot and Explain: Interpretable Representation Learning for Discriminative Visual Reasoning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9117-525X","authenticated-orcid":false,"given":"Ci-Siang","family":"Lin","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-157X","authenticated-orcid":false,"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and the Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00487"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_25"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6712"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/72.286929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00941"},{"key":"ref58","article-title":"Person re-identification: Past, present and future","author":"zheng","year":"2016","journal-title":"arXiv 1610 02984"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_26"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00978"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00530"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref19","article-title":"IA-RED2: Interpretability-aware redundancy reduction for vision transformers","author":"pan","year":"2021","journal-title":"arXiv 2106 12620"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01096"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.476"},{"key":"ref50","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref45","author":"wah","year":"2011","journal-title":"The caltech-ucsd birds-200–2011 dataset"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00454"},{"key":"ref47","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume":"2","author":"khosla","year":"2011","journal-title":"Proc CVPR Workshop Fine-Grained Vis Categorization (FGVC)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref41","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","article-title":"Barlow Twins: Self-supervised learning via redundancy reduction","author":"zbontar","year":"2021","journal-title":"arXiv 2103 03230"},{"key":"ref43","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref49","article-title":"Hybrid routing transformer for zero-shot learning","author":"cheng","year":"2022","journal-title":"arXiv 2203 15310"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00038"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00371"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"ref40","article-title":"Augmenting self-attention with persistent memory","author":"sukhbaatar","year":"2019","journal-title":"arXiv 1907 01470"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_17"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00304"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.374"},{"key":"ref30","article-title":"Understanding neural networks through deep visualization","author":"yosinski","year":"2015","journal-title":"arXiv 1506 06579"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00515"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref38","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00670"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00869"},{"key":"ref23","first-page":"842","article-title":"The application of two-level attention models in deep convolutional neural network for fine-grained image classification","author":"xiao","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_39"},{"key":"ref26","first-page":"8930","article-title":"This looks like that: Deep learning for interpretable image recognition","volume":"32","author":"chen","year":"2019","journal-title":"Proc Neural Inf Process Syst (NeurIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_23"},{"key":"ref63","first-page":"480","article-title":"Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline)","author":"sun","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref22","article-title":"Bird species categorization using pose normalized deep convolutional nets","author":"branson","year":"2014","journal-title":"arXiv 1406 2952"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3055952"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.129"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00730"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0911-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01469"},{"key":"ref29","author":"mordvintsev","year":"2015","journal-title":"Inceptionism Going deeper into neural networks"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_40"},{"key":"ref62","first-page":"1222","article-title":"FD-GAN: Pose-guided feature distilling GAN for robust person re-identification","volume":"31","author":"ge","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00243"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10106785.pdf?arnumber=10106785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:48:11Z","timestamp":1685382491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10106785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3268001","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}