{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:23:02Z","timestamp":1778257382395,"version":"3.51.4"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"General Research Fund of Hong Kong","award":["27208720"],"award-info":[{"award-number":["27208720"]}]},{"name":"General Research Fund of Hong Kong","award":["17212120"],"award-info":[{"award-number":["17212120"]}]},{"name":"General Research Fund of Hong Kong","award":["17200622"],"award-info":[{"award-number":["17200622"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2023.3251693","type":"journal-article","created":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T17:49:13Z","timestamp":1689702553000},"page":"1726-1739","source":"Crossref","is-referenced-by-count":27,"title":["Rethinking Attentive Object Detection via Neural Attention Learning"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1142-9171","authenticated-orcid":false,"given":"Chongjian","family":"Ge","sequence":"first","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3667-531X","authenticated-orcid":false,"given":"Yibing","family":"Song","sequence":"additional","affiliation":[{"name":"AI3 Institute, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8459-2845","authenticated-orcid":false,"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuankai","family":"Qi","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, The University of Adelaide, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00968"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00199"},{"key":"ref6","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv:1612.03928"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2023.3238524"},{"key":"ref10","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.54097\/hset.v17i.2576"},{"key":"ref15","first-page":"1","article-title":"OverFeat: Integrated recognition, localization and detection using convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sermanet"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref19","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.214"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref27","first-page":"1","author":"Dai","year":"2016","journal-title":"R-FCN: Object detection via region-based fully convolutional networks"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref30","article-title":"Light-headR-CNN: In defense of two-stage object detector","author":"Li","year":"2017","journal-title":"arXiv:1711.07264"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00682"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/35058500"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.539"},{"key":"ref36","article-title":"Deep attentive tracking via reciprocative learning","author":"Pu","year":"2018","journal-title":"arXiv:1810.03851"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.468"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.518"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.513"},{"key":"ref40","article-title":"Hierarchical attentive recurrent tracking","author":"Kosiorek","year":"2017","journal-title":"arXiv:1706.09262"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00386"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00046"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.402"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2547588"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref47","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref48","article-title":"UP-DETR: Unsupervised pre-training for object detection with transformers","author":"Dai","year":"2020","journal-title":"arXiv:2011.09094"},{"key":"ref49","article-title":"RelationNet++: Bridging visual representations for object detection via transformer decoder","author":"Chi","year":"2020","journal-title":"arXiv:2010.15831"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539906"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.749"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00609"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.03.030"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"key":"ref59","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2014","journal-title":"arXiv:1312.6034"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9939-1990-0969514-3"},{"key":"ref61","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap","year":"2018","journal-title":"arXiv:1803.08375"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref63","volume-title":"Detectron","author":"Girshick","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref65","volume-title":"MaskRCNN-benchmark: Fast, modular reference implementation of instance segmentation and object detection algorithms in PyTorch","author":"Massa","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01418"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01160"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/72.165600"},{"key":"ref72","article-title":"Benchmarking robustness in object detection: Autonomous driving when winter is coming","author":"Michaelis","year":"2019","journal-title":"arXiv:1907.07484"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/10346232\/10186342.pdf?arnumber=10186342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:37:17Z","timestamp":1725165437000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10186342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3251693","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}