{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T01:01:19Z","timestamp":1783645279128,"version":"3.55.0"},"reference-count":76,"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":[{"name":"National Key Research and Development Program of China","award":["2021YFF1200800"],"award-info":[{"award-number":["2021YFF1200800"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402252"],"award-info":[{"award-number":["62402252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen International Research Cooperation Project","award":["GJHZ20220913142611021"],"award-info":[{"award-number":["GJHZ20220913142611021"]}]},{"name":"Pengcheng Laboratory Research Project","award":["PCL2023A08"],"award-info":[{"award-number":["PCL2023A08"]}]},{"name":"Pengcheng Laboratory Research Project","award":["PCL2024Y02"],"award-info":[{"award-number":["PCL2024Y02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3599074","type":"journal-article","created":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:01:05Z","timestamp":1755910865000},"page":"7369-7379","source":"Crossref","is-referenced-by-count":2,"title":["Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0682-2158","authenticated-orcid":false,"given":"Guiping","family":"Cao","sequence":"first","affiliation":[{"name":"Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2408-8302","authenticated-orcid":false,"given":"Wenjian","family":"Huang","sequence":"additional","affiliation":[{"name":"Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8564-0346","authenticated-orcid":false,"given":"Xiangyuan","family":"Lan","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9317-0268","authenticated-orcid":false,"given":"Jianguo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-8499","authenticated-orcid":false,"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology at Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_1"},{"key":"ref4","first-page":"3","article-title":"MLP-DINO: Category modeling and query graphing with deep MLP for object detection","volume-title":"Proc. 33rd Int. Joint Conf. Artif. Intell.","author":"Cao","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00144"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19893"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290594"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"ref14","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref16","article-title":"DSSD: Deconvolutional single shot detector","author":"Fu","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102793"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284161"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00891-0"},{"key":"ref22","article-title":"Gaussian error linear units (GELUS)","author":"Hendrycks","year":"2016"},{"key":"ref23","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_17"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5121\/csit.2019.91713"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100520"},{"key":"ref32","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00597"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602"},{"key":"ref37","first-page":"103031","article-title":"VMamba: Visual state space model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Liu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref40","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref41","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Luo","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251100"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00751"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3758090"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref49","article-title":"Detrex: Benchmarking detection transformers","author":"Ren","year":"2023"},{"key":"ref50","article-title":"Sparse DETR: Efficient end-to-end object detection with learnable sparsity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Roh","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-73973-7_33"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/5863782"},{"key":"ref53","article-title":"SNIPER: Efficient multi-scale training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Singh","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01066"},{"key":"ref56","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref58","article-title":"A normalized Gaussian wasserstein distance for tiny object detection","author":"Wang","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_31"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01330"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00975"},{"key":"ref64","article-title":"Efficient DETR: Improving end-to-end object detector with dense prior","author":"Yao","year":"2021"},{"key":"ref65","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00581"},{"key":"ref67","article-title":"DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhang","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929005"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref73","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00621"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_34"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11134787.pdf?arnumber=11134787","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:25:37Z","timestamp":1761153937000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11134787\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3599074","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}