{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T23:03:44Z","timestamp":1784675024893,"version":"3.55.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Spanish Ministry of Economy and Competitivity through the project","award":["RTI2018-100847-B-C21"],"award-info":[{"award-number":["RTI2018-100847-B-C21"]}]},{"name":"MIT International Science and Technology Initiatives (MISTI)-Spain through the project"},{"name":"Mohamed Bin Zayed International Robotics Challenge (MBZIRC) in the year 2020"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3006191","type":"journal-article","created":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T21:11:26Z","timestamp":1593637886000},"page":"124451-124466","source":"Crossref","is-referenced-by-count":38,"title":["Adaptive Inattentional Framework for Video Object Detection With Reward-Conditional Training"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3257-4602","authenticated-orcid":false,"given":"Alejandro","family":"Rodriguez-Ramos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0305-7806","authenticated-orcid":false,"given":"Javier","family":"Rodriguez-Vazquez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2414-2284","authenticated-orcid":false,"given":"Carlos","family":"Sampedro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9894-2009","authenticated-orcid":false,"given":"Pascual","family":"Campoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.135"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.258"},{"key":"ref71","first-page":"214","article-title":"R-CNN for small object detection","author":"chen","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00984"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.316"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.286"},{"key":"ref74","first-page":"4703","article-title":"SegDeepM: Exploiting segmentation and context in deep neural networks for object detection","author":"zhu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref39","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref75","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014","journal-title":"Arxiv 1412 7755"},{"key":"ref38","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref78","article-title":"Learning when and where to zoom with deep reinforcement learning","author":"uzkent","year":"2020","journal-title":"arXiv 2003 00425"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093447"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.40"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3707.001.0001"},{"key":"ref31","author":"purves","year":"2001","journal-title":"Neuroscience"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1167\/9.5.7"},{"key":"ref37","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref36","first-page":"3942","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref35","article-title":"You only train once: Loss-conditional training of deep networks","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00107"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018803"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018529"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.330"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_21"},{"key":"ref28","first-page":"13","article-title":"Simple anatomy of the retina","author":"kolb","year":"1995","journal-title":"Webvision The Organization of the Retina and Visual System"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00815"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198524793.001.0001"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00628"},{"key":"ref66","first-page":"109","article-title":"Depth-adaptive computational policies for efficient visual tracking","author":"ying","year":"2017","journal-title":"Proc Int Workshop Energy Minimization Methods Comput Vis Pattern Recognit"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1167\/11.5.13"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.43"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383267"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref2","article-title":"Learning spatial fusion for single-shot object detection","author":"liu","year":"2019","journal-title":"arXiv 1911 09516"},{"key":"ref1","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020","journal-title":"arXiv 2004 10934"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref22","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"hubara","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref21","first-page":"4107","article-title":"Binarized neural networks","author":"hubara","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293904"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-44534-8_10"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00133571"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.2889402"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00596"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2894261"},{"key":"ref59","article-title":"CaTDet: Cascaded tracked detector for efficient object detection from video","author":"mao","year":"2018","journal-title":"arXiv 1810 00434"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00678"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.95"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2736553"},{"key":"ref54","article-title":"Seq-NMS for video object detection","author":"han","year":"2016","journal-title":"arXiv 1602 08465"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref52","article-title":"Future semantic segmentation with convolutional LSTM","author":"nabavi","year":"2018","journal-title":"arXiv 1807 07946"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00726"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/INCIT.2017.8257866"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.441"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2016.2593643"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342100"},{"key":"ref14","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size","author":"iandola","year":"2016","journal-title":"arXiv 1602 07360"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref81","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref84","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc of USENIX Symp on Operating Systems Design and Implementation (OSDI)"},{"key":"ref18","first-page":"2815","article-title":"MnasNet: Platform-aware neural architecture search for mobile","author":"tan","year":"2018","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref83","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref80","first-page":"127","article-title":"Tree-structured reinforcement learning for sequential object localization","author":"jie","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","article-title":"EfficientDet: Scalable and efficient object detection","author":"tan","year":"2019","journal-title":"arXiv 1911 09070"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref6","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref5","article-title":"Objects as points","author":"zhou","year":"2019","journal-title":"arXiv 1904 07850"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8621865"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref49","article-title":"Looking fast and slow: Memory-guided mobile video object detection","author":"liu","year":"2019","journal-title":"arXiv 1903 10172"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00724"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00907"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00568"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_30"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.224"},{"key":"ref42","article-title":"Impression network for video object detection","author":"hetang","year":"2017","journal-title":"arXiv 1712 05896"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.52"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00064"},{"key":"ref43","article-title":"Towards high performance video object detection for mobiles","author":"zhu","year":"2018","journal-title":"arXiv 1804 05830"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09130680.pdf?arnumber=9130680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:57:27Z","timestamp":1642003047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9130680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3006191","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}