{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:39:35Z","timestamp":1780317575624,"version":"3.54.1"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2054"],"award-info":[{"award-number":["U22B2054"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076192"],"award-info":[{"award-number":["62076192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276199"],"award-info":[{"award-number":["62276199"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62431020"],"award-info":[{"award-number":["62431020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276201"],"award-info":[{"award-number":["62276201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61977052"],"award-info":[{"award-number":["61977052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Program for Cheung Kong Scholars and Innovative Research Team in University","award":["IRT 15R53"],"award-info":[{"award-number":["IRT 15R53"]}]},{"name":"Science and Technology Innovation Project from the Chinese Ministry of Education"},{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence"},{"DOI":"10.13039\/501100002412","name":"Xi'an Jiaotong University","doi-asserted-by":"publisher","award":["HMHAI-202404"],"award-info":[{"award-number":["HMHAI-202404"]}],"id":[{"id":"10.13039\/501100002412","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002412","name":"Xi'an Jiaotong University","doi-asserted-by":"publisher","award":["HMHAI-202405"],"award-info":[{"award-number":["HMHAI-202405"]}],"id":[{"id":"10.13039\/501100002412","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521850","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:23:06Z","timestamp":1734981786000},"page":"2281-2292","source":"Crossref","is-referenced-by-count":3,"title":["LGSNet: Local-Global Semantics Learning Object Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3083-0227","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8780-5455","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5669-9354","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6130-2518","authenticated-orcid":false,"given":"Lingling","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5472-1426","authenticated-orcid":false,"given":"Puhua","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of the Ministry of Education of China, International Research Center of Intelligent Perception and Computation, School of Artificial Intelligence, Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3068840"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943753"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3096333"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3173131"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3075323"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120873"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00462"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00519"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169061"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.13350"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108418"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3164787"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref24","article-title":"LinFormer: Self-attention with linear complexity","author":"Wang","year":"2020"},{"key":"ref25","first-page":"2441","article-title":"Linear unified nested attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ma","year":"2021"},{"key":"ref26","first-page":"3530","article-title":"Efficient attention: Attention with linear complexities","volume-title":"Proc. IEEE Workshop\/Winter Conf. Appl. Comput. Vis.","author":"Shen","year":"2021"},{"key":"ref27","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choromanski","year":"2021"},{"key":"ref28","first-page":"1","article-title":"Random feature attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Peng","year":"2021"},{"key":"ref29","first-page":"1","article-title":"LambdaNetworks: Modeling long-range interactions without attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bello","year":"2021"},{"key":"ref30","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos","year":"2020"},{"key":"ref31","first-page":"1","article-title":"cosformer: Rethinking softmax in attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qin","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01177"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00359"},{"key":"ref35","first-page":"1177","article-title":"Random features for large-scale kernel machines","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rahimi","year":"2007"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00259"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref39","first-page":"21297","article-title":"SOFT: Softmax-free transformer with linear complexity","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109270"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00003-0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048630"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3040539"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2938879"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3068576"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3157453"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3204337"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3181-9"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.04.005"},{"key":"ref57","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3097917"},{"key":"ref59","first-page":"4898","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Luo","year":"2016"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref61","first-page":"350","article-title":"A$^{2}$-nets: Double attention networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2018"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref65","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050494"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3002345"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162099"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3211734"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00091"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3099733"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00944"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3067439"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3299190"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref85","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref86","article-title":"DSDD : Deconvolutional single shot detector","author":"Fu","year":"2017"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028196"},{"key":"ref89","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dai","year":"2016"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.444"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865280"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107593"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10812852.pdf?arnumber=10812852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:47:52Z","timestamp":1747158472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521850","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}