{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T11:34:43Z","timestamp":1784806483538,"version":"3.55.0"},"reference-count":102,"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, Xi’an Jiaotong University","award":["HMHAI-202404"],"award-info":[{"award-number":["HMHAI-202404"]}]},{"name":"National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University","award":["HMHAI-202405"],"award-info":[{"award-number":["HMHAI-202405"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3604963","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:31:43Z","timestamp":1756834303000},"page":"8016-8028","source":"Crossref","is-referenced-by-count":1,"title":["Semantic-Aware Wavelet Transformer for Pyramid 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\/TNNLS.2018.2876865"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3347644"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3136907"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3039392"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01825"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3381377"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02529"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3096333"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3307896"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02663"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3169061"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3270479"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521850"},{"key":"ref20","first-page":"33319","article-title":"ShiftAddViT: Mixture of multiplication primitives towards efficient vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"You","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3367901"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3359480"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00357"},{"key":"ref26","first-page":"1","article-title":"LambdaNetworks: Modeling long-range interactions without attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bello","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref28","first-page":"15475","article-title":"Rest: An efficient transformer for visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref30","article-title":"Wavelet convolutional neural networks","author":"Fujieda","year":"2018"},{"key":"ref31","first-page":"1","article-title":"Wavelet pooling for convolutional neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Williams","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3218735"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_19"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3289958"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293770"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3353909"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130195"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3325824"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3321554"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_6"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3275538"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3101395"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26351-4_4"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3007032"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108418"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3162069"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref48","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":"ref49","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choromanski","year":"2021"},{"key":"ref50","first-page":"1","article-title":"Random feature attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Peng","year":"2021"},{"key":"ref51","first-page":"1","article-title":"cosFormer: Rethinking softmax in attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Qin","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120873"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475708"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3272826"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3299190"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3221755"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292030"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.04.005"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248966"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.006"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00608"},{"key":"ref68","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref69","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3067439"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3075323"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106641"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3340065"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241993"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109098"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3162099"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3305289"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00580"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3412947"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00529"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3211734"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref87","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref91","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":"ref92","article-title":"DSSD : Deconvolutional single shot detector","author":"Fu","year":"2017"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028196"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3040539"},{"key":"ref96","first-page":"379","article-title":"R-FCN: Object detection via region-based fully convolutional networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai","year":"2016"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.444"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2865280"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107593"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01261"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref102","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ali","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11146693.pdf?arnumber=11146693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:54Z","timestamp":1763059494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3604963","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}