{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T20:56:46Z","timestamp":1773867406650,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T00:00:00Z","timestamp":1689206400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T00:00:00Z","timestamp":1689206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100022796","name":"Hubei Three Gorges Laboratory","doi-asserted-by":"crossref","award":["SK215002"],"award-info":[{"award-number":["SK215002"]}],"id":[{"id":"10.13039\/100022796","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s10489-023-04763-6","type":"journal-article","created":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T12:02:41Z","timestamp":1689249761000},"page":"23564-23581","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SwinEFT: a robust and powerful Swin Transformer based Event Frame Tracker"],"prefix":"10.1007","volume":"53","author":[{"given":"Zhaoyuan","family":"Zeng","sequence":"first","affiliation":[]},{"given":"Xiaopeng","family":"Li","sequence":"additional","affiliation":[]},{"given":"Cien","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Lian","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Ruan","family":"Chi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,13]]},"reference":[{"key":"4763_CR1","doi-asserted-by":"crossref","unstructured":"Javed S, Danelljan M, Shahbaz Khan F, Khan MH, Felsberg M, Matas J (2022) Visual object tracking with discriminative filters and siamese networks: a survey and outlook. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2022.3212594"},{"issue":"5","key":"4763_CR2","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TPAMI.2019.2957464","volume":"43","author":"L Huang","year":"2019","unstructured":"Huang L, Zhao X, Huang K (2019) Got-10k: a large high-diversity benchmark for generic object tracking in the wild. IEEE Trans Pattern Anal Mach Intell 43(5):1562\u20131577","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4763_CR3","doi-asserted-by":"crossref","unstructured":"Xiao Y, Yang M, Li C, Liu L, Tang J (2022) Attribute-based progressive fusion network for RGBT tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp 2831\u20132838","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"4763_CR4","doi-asserted-by":"crossref","unstructured":"Gao Y, Li C, Zhu Y, Tang J, He T, Wang F (2019) Deep adaptive fusion network for high performance RGBT tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops. pp 0\u20130","DOI":"10.1109\/ICCVW.2019.00017"},{"key":"4763_CR5","doi-asserted-by":"publisher","first-page":"5613","DOI":"10.1109\/TIP.2021.3087341","volume":"30","author":"L Andong","year":"2021","unstructured":"Andong L, Li C, Yan Y, Tang J, Luo B (2021) RGBT tracking via multi-adapter network with hierarchical divergence loss. IEEE Trans Image Process 30:5613\u20135625","journal-title":"IEEE Trans Image Process"},{"key":"4763_CR6","doi-asserted-by":"crossref","unstructured":"Zhao P, Liu Q, Wang W, Guo Q (2021) TSDM: tracking by SIAMRPN++ with a depth-refiner and a mask-generator. In: 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, pp 670\u2013676","DOI":"10.1109\/ICPR48806.2021.9413315"},{"key":"4763_CR7","doi-asserted-by":"crossref","unstructured":"Yan S, Yang J, K\u00e4pyl\u00e4 J, Zheng F, Leonardis A, K\u00e4m\u00e4r\u00e4inen J-K (2021) Depthtrack: unveiling the power of RGBD tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 10725\u201310733","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"4763_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113711","volume":"162","author":"A Kumar","year":"2020","unstructured":"Kumar A, Walia GS, Sharma K (2020) Recent trends in multicue based visual tracking: a review. Expert Syst Appl 162:113711","journal-title":"Expert Syst Appl"},{"issue":"1","key":"4763_CR9","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2020","unstructured":"Gallego G, Delbr\u00fcck T, Orchard G, Bartolozzi C, Taba B, Censi A, Leutenegger S, Davison AJ, Conradt J, Daniilidis K et al (2020) Event-based vision: a survey. IEEE Trans Pattern Anal Mach Intell 44(1):154\u2013180","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4763_CR10","doi-asserted-by":"crossref","unstructured":"Zhang J, Yang X, Fu Y, Wei X, Yin B, Dong B (2021) Object tracking by jointly exploiting frame and event domain. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 13043\u201313052","DOI":"10.1109\/ICCV48922.2021.01280"},{"key":"4763_CR11","unstructured":"Wang X, Li J, Zhu L, Zhang Z, Chen Z, Li X, Wang Y, Tian Y, Wu F (2021) Visevent: reliable object tracking via collaboration of frame and event flows. Preprint at http:\/\/arxiv.org\/abs\/2108.05015"},{"key":"4763_CR12","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Proces Syst 30"},{"key":"4763_CR13","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et\u00a0al (2020) An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations"},{"key":"4763_CR14","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"4763_CR15","doi-asserted-by":"crossref","unstructured":"Chen X, Yan B, Zhu J, Wang D, Yang X, Lu H (2021) Transformer tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 8126\u20138135","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"4763_CR16","doi-asserted-by":"crossref","unstructured":"Wang N, Zhou W, Wang J, Li H (2021) Transformer meets tracker: exploiting temporal context for robust visual tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 1571\u20131580","DOI":"10.1109\/CVPR46437.2021.00162"},{"key":"4763_CR17","unstructured":"Lin L, Fan H, Zhang Z, Xu Y, Ling H (2022) Swintrack: a simple and strong baseline for transformer tracking. In: Advances in Neural Information Processing Systems"},{"key":"4763_CR18","doi-asserted-by":"crossref","unstructured":"Mayer C, Danelljan M, Bhat G, Paul M, Paudel DP, Yu F, Van\u00a0Gool L (2022) Transforming model prediction for tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 8731\u20138740","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"4763_CR19","doi-asserted-by":"crossref","unstructured":"Ye B, Chang H, Ma B, Shan S, Chen X (2022) Joint feature learning and relation modeling for tracking: a one-stream framework. In: European Conference on Computer Vision. Springer, pp 341\u2013357","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"4763_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3230378","volume":"60","author":"C Zhao","year":"2022","unstructured":"Zhao C, Liu H, Nan S, Yan Y (2022) TFTN: a transformer-based fusion tracking framework of hyperspectral and RGB. IEEE Trans Geosci Remote Sens 60:1\u201315","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"4763_CR21","doi-asserted-by":"crossref","unstructured":"Feng M, Su J (2022) Learning reliable modal weight with transformer for robust RGBT tracking. Knowl-Based Syst 108945","DOI":"10.1016\/j.knosys.2022.108945"},{"issue":"12","key":"4763_CR22","doi-asserted-by":"publisher","first-page":"5743","DOI":"10.1109\/TIP.2016.2614135","volume":"25","author":"C Li","year":"2016","unstructured":"Li C, Cheng H, Shiyi H, Liu X, Tang J, Lin L (2016) Learning collaborative sparse representation for grayscale-thermal tracking. IEEE Trans Image Process 25(12):5743\u20135756","journal-title":"IEEE Trans Image Process"},{"key":"4763_CR23","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.patrec.2018.10.002","volume":"130","author":"X Lan","year":"2020","unstructured":"Lan X, Ye M, Zhang S, Zhou H, Yuen PC (2020) Modality-correlation-aware sparse representation for RGB-infrared object tracking. Pattern Recogn Lett 130:12\u201320","journal-title":"Pattern Recogn Lett"},{"key":"4763_CR24","first-page":"567","volume":"24","author":"X Qin","year":"2021","unstructured":"Qin X, Mei Y, Liu J, Li C (2021) Multimodal cross-layer bilinear pooling for RGBT tracking. IEEE Trans Multimedia 24:567\u2013580","journal-title":"IEEE Trans Multimedia"},{"key":"4763_CR25","doi-asserted-by":"publisher","first-page":"3335","DOI":"10.1109\/TIP.2021.3060862","volume":"30","author":"P Zhang","year":"2021","unstructured":"Zhang P, Zhao J, Bo Chunjuan, Wang Dong, Huchuan Lu, Yang Xiaoyun (2021) Jointly modeling motion and appearance cues for robust RGB-t tracking. IEEE Trans Image Process 30:3335\u20133347","journal-title":"IEEE Trans Image Process"},{"key":"4763_CR26","first-page":"85","volume":"31","author":"T Zhengzheng","year":"2021","unstructured":"Zhengzheng T, Lin C, Zhao W, Li C, Tang J (2021) M 5 l: multi-modal multi-margin metric learning for RGBT tracking. IEEE Trans Image Process 31:85\u201398","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"4763_CR27","doi-asserted-by":"publisher","first-page":"2147","DOI":"10.1007\/s10489-022-03540-1","volume":"53","author":"Yu Hu","year":"2023","unstructured":"Hu Yu, Li X, Fan C, Zou L, Yuanmei W (2023) MSDA: multi-scale domain adaptation dehazing network. Appl Intell 53(2):2147\u20132160","journal-title":"Appl Intell"},{"key":"4763_CR28","doi-asserted-by":"crossref","unstructured":"Li X, Fan C, Zhao C, Zou L, Tian S (2022) NIRN: self-supervised noisy image reconstruction network for real-world image denoising. Appl Intell 1\u201318","DOI":"10.1007\/s10489-022-03333-6"},{"key":"4763_CR29","doi-asserted-by":"crossref","unstructured":"Li X, Yu H, Zhao C, Fan C, Zou L (2023) DADRNet: cross-domain image dehazing via domain adaptation and disentangled representation. Neurocomputing 126242","DOI":"10.1016\/j.neucom.2023.126242"},{"issue":"3","key":"4763_CR30","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s11263-019-01209-w","volume":"128","author":"D Gehrig","year":"2020","unstructured":"Gehrig D, Rebecq H, Gallego G, Scaramuzza D (2020) EKLT: asynchronous photometric feature tracking using events and frames. Int J Comput Vision 128(3):601\u2013618","journal-title":"Int J Comput Vision"},{"issue":"9","key":"4763_CR31","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TCSVT.2018.2841516","volume":"28","author":"J Huang","year":"2018","unstructured":"Huang J, Wang S, Guo M, Chen S (2018) Event-guided structured output tracking of fast-moving objects using a celex sensor. IEEE Trans Circuits Syst Video Technol 28(9):2413\u20132417","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4763_CR32","unstructured":"Yang Z, Wu Y, Wang G, Yang Y, Li G, Deng L, Zhu J, Shi L (2019) DashNet: a hybrid artificial and spiking neural network for high-speed object tracking. Preprint at http:\/\/arxiv.org\/abs\/1909.12942"},{"key":"4763_CR33","doi-asserted-by":"crossref","unstructured":"Rebecq H, Horstschaefer T, Scaramuzza D (2017) Real-time visual-inertial odometry for event cameras using keyframe-based nonlinear optimization. In: Proceedings of the British Machine Vision Conference (BMVC). pp 16\u20131","DOI":"10.5244\/C.31.16"},{"key":"4763_CR34","doi-asserted-by":"crossref","unstructured":"Maqueda AI, Loquercio A, Gallego G, Garc\u00eda N, Scaramuzza D (2018) Event-based vision meets deep learning on steering prediction for self-driving cars. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 5419\u20135427","DOI":"10.1109\/CVPR.2018.00568"},{"key":"4763_CR35","doi-asserted-by":"crossref","unstructured":"Zhu AZ, Yuan L (2018) EV-flownet: self-supervised optical flow estimation for event-based cameras. In: Robotics: Science and Systems. pp 1\u20139","DOI":"10.15607\/RSS.2018.XIV.062"},{"issue":"2","key":"4763_CR36","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/TNNLS.2013.2273537","volume":"25","author":"R Benosman","year":"2013","unstructured":"Benosman R, Clercq C, Lagorce X, Ieng S-H, Bartolozzi C (2013) Event-based visual flow. IEEE Trans Neural Netw Learn Syst 25(2):407\u2013417","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4763_CR37","doi-asserted-by":"crossref","unstructured":"Zhu AZ, Yuan L, Chaney K, Daniilidis K (2019) Unsupervised event-based learning of optical flow, depth, and egomotion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 989\u2013997","DOI":"10.1109\/CVPR.2019.00108"},{"key":"4763_CR38","doi-asserted-by":"crossref","unstructured":"Sironi A, Brambilla M, Bourdis N, Lagorce X, Benosman R (2018) Hats: histograms of averaged time surfaces for robust event-based object classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 1731\u20131740","DOI":"10.1109\/CVPR.2018.00186"},{"key":"4763_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108417","volume":"124","author":"ST Zhou","year":"2022","unstructured":"Zhou ST, Ruan PV, Canu S (2022) A tri-attention fusion guided multi-modal segmentation network. Pattern Recogn 124:108417","journal-title":"Pattern Recogn"},{"key":"4763_CR40","doi-asserted-by":"crossref","unstructured":"Zhang H, Wang Y, Dayoub F, Sunderhauf N (2021) Varifocalnet: an iou-aware dense object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 8514\u20138523","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"4763_CR41","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"4763_CR42","doi-asserted-by":"crossref","unstructured":"Danelljan M, Bhat G, Shahbaz Khan F, Felsberg M (2019) Atom: accurate tracking by overlap maximization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 4660\u20134669","DOI":"10.1109\/CVPR.2019.00479"},{"key":"4763_CR43","doi-asserted-by":"crossref","unstructured":"Bhat G, Danelljan M, Van Gool L, Timofte R (2019) Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 6182\u20136191","DOI":"10.1109\/ICCV.2019.00628"},{"key":"4763_CR44","doi-asserted-by":"crossref","unstructured":"Xu Y, Wang Z, Li Z, Yuan Y, Yu G (2020) SIAMFC++: towards robust and accurate visual tracking with target estimation guidelines. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp 12549\u201312556","DOI":"10.1609\/aaai.v34i07.6944"},{"key":"4763_CR45","doi-asserted-by":"crossref","unstructured":"Yan B, Peng H, Fu J, Wang D, Lu H (2021) Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp 10448\u201310457","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"4763_CR46","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. Preprint at http:\/\/arxiv.org\/abs\/1711.05101"},{"issue":"7","key":"4763_CR47","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1109\/TPAMI.2016.2574707","volume":"39","author":"X Lagorce","year":"2016","unstructured":"Lagorce X, Orchard G, Galluppi F, Shi BE, Benosman RB (2016) Hots: a hierarchy of event-based time-surfaces for pattern recognition. IEEE Trans Pattern Anal Mach Intell 39(7):1346\u20131359","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4763_CR48","doi-asserted-by":"crossref","unstructured":"Haosheng Chen, David Suter, Qiangqiang Wu, and Hanzi Wang (2020) End-to-end learning of object motion estimation from retinal events for event-based object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp 10534\u201310541","DOI":"10.1609\/aaai.v34i07.6625"},{"key":"4763_CR49","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04763-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-023-04763-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-023-04763-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T16:15:01Z","timestamp":1697904901000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-023-04763-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,13]]},"references-count":49,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["4763"],"URL":"https:\/\/doi.org\/10.1007\/s10489-023-04763-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,13]]},"assertion":[{"value":"2 June 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that there are no conflict of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}