{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T15:14:44Z","timestamp":1751555684266,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T00:00:00Z","timestamp":1675296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T00:00:00Z","timestamp":1675296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172417"],"award-info":[{"award-number":["62172417"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20201346"],"award-info":[{"award-number":["BK20201346"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101555"],"award-info":[{"award-number":["62101555"]}],"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":["62106268"],"award-info":[{"award-number":["62106268"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11042-023-14362-9","type":"journal-article","created":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T12:07:01Z","timestamp":1675339621000},"page":"23595-23613","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised RGB-T object tracking with attentional multi-modal feature fusion"],"prefix":"10.1007","volume":"82","author":[{"given":"Shenglan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2734-915X","authenticated-orcid":false,"given":"Rui","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hancheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwen","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,2]]},"reference":[{"key":"14362_CR1","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. 3rd International Conference on Learning Representations, ICLR 2015; Conference date: 07-05-2015 Through 09-05-2015"},{"key":"14362_CR2","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.patcog.2018.08.007","volume":"86","author":"H Chen","year":"2019","unstructured":"Chen H, Li Y, Su D (2019) Multi-modal fusion network with multi-scale multi-path and cross-modal interactions for RGB-D salient object detection. Pattern Recog 86:376\u2013385. https:\/\/doi.org\/10.1016\/j.patcog.2018.08.007, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320318303054","journal-title":"Pattern Recog"},{"key":"14362_CR3","doi-asserted-by":"crossref","unstructured":"Chen Y, Zhu X, Gong S (2018) Semi-supervised deep learning with memory. In: Proceedings of the european conference on computer vision (ECCV)","DOI":"10.1007\/978-3-030-01246-5_17"},{"key":"14362_CR4","unstructured":"Dai Y, Gieseke F, Oehmcke S, Wu Y, Barnard K Attentional feature fusion. arXiv:2009.14082"},{"key":"14362_CR5","doi-asserted-by":"publisher","unstructured":"Fu Z, Liu Q, Fu Z, Wang Y (2021) Stmtrack: Template-free visual tracking with space-time memory networks. In: 2021 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01356, pp 13769\u201313778","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"14362_CR6","doi-asserted-by":"publisher","unstructured":"Gao Y, Li C, Zhu Y, Tang J, He T, Wang F (2019) Deep adaptive fusion network for high performance RGBT tracking. In: 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW). https:\/\/doi.org\/10.1109\/ICCVW.2019.00017, pp 91\u201399","DOI":"10.1109\/ICCVW.2019.00017"},{"key":"14362_CR7","doi-asserted-by":"publisher","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2018.00745, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"issue":"8","key":"14362_CR8","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TPAMI.2019.2913372","volume":"42","author":"J Hu","year":"2020","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42 (8):2011\u20132023. https:\/\/doi.org\/10.1109\/TPAMI.2019.2913372","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14362_CR9","unstructured":"Kristan M, Matas J, Leonardis A, Vojir T, Pflugfelder RP, Fern\u00e1ndez G, Nebehay G, Porikli F, Cehovin L A novel performance evaluation methodology for single-target trackers. arXiv:1503.01313"},{"issue":"12","key":"14362_CR10","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, Hu S, Liu X, Tang J, Lin L (2016) Learning collaborative sparse representation for grayscale-thermal tracking. IEEE Trans Image Process 25(12):5743\u20135756. https:\/\/doi.org\/10.1109\/TIP.2016.2614135","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"14362_CR11","doi-asserted-by":"publisher","first-page":"2913","DOI":"10.1109\/TCSVT.2018.2874312","volume":"29","author":"C Li","year":"2019","unstructured":"Li C, Zhu C, Zhang J, Luo B, Wu X, Tang J (2019) Learning local-global multi-graph descriptors for RGB-T object tracking. IEEE Trans Circ Syst Video Technol 29(10):2913\u20132926. https:\/\/doi.org\/10.1109\/TCSVT.2018.2874312","journal-title":"IEEE Trans Circ Syst Video Technol"},{"key":"14362_CR12","doi-asserted-by":"publisher","unstructured":"Li CL, Lu A, Zheng AH, Tu Z, Tang J (2019) Multi-adapter RGBT tracking. In: 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW). https:\/\/doi.org\/10.1109\/ICCVW.2019.00279, pp 2262\u20132270","DOI":"10.1109\/ICCVW.2019.00279"},{"key":"14362_CR13","unstructured":"Li C, Liang X, Lu Y, Zhao N, Tang J RGB-T object tracking: Benchmark and baseline. arXiv:1805.08982"},{"key":"14362_CR14","unstructured":"Li C, Zhu C, Huang Y, Tang J, Wang L Cross-modal ranking with soft consistency and noisy labels for robust RGB-T tracking"},{"key":"14362_CR15","unstructured":"Lu X, Wang W, Danelljan M, Zhou T, Shen J, Gool LV Video object segmentation with episodic graph memory networks. arXiv:2007.07020"},{"key":"14362_CR16","unstructured":"Mnih V, Heess N, Graves A, Kavukcuoglu K (2014) Recurrent models of visual attention. In: Proceedings of the 27th international conference on neural information processing systems - Volume 2, NIPS\u201914. MIT Press, Cambridge, pp 2204\u20132212"},{"key":"14362_CR17","unstructured":"Oh SW, Lee J, Xu N, Kim SJ Video object segmentation using space-time memory networks. arXiv:1904.00607"},{"key":"14362_CR18","doi-asserted-by":"publisher","first-page":"1948","DOI":"10.1145\/3394171.3413611","volume-title":"S2SiamFC: self-supervised fully convolutional siamese network for visual tracking","author":"CH Sio","year":"2020","unstructured":"Sio CH, Ma Y-J, Shuai H-H, Chen J-C, Cheng W-H (2020) S2SiamFC: self-supervised fully convolutional siamese network for visual tracking. Association for Computing Machinery, New York, pp 1948\u20131957. https:\/\/doi.org\/10.1145\/3394171.3413611"},{"key":"14362_CR19","doi-asserted-by":"crossref","unstructured":"Shen Q, Qiao L, Guo J, Li P, Li X, Li B, Feng W, Gan W, Wu W, Ouyang W (2022) Unsupervised learning of accurate siamese tracking. arXiv:2204.01475","DOI":"10.1109\/CVPR52688.2022.00793"},{"key":"14362_CR20","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems, NIPS\u201917. Curran Associates Inc., Red Hook, pp 6000\u20136010"},{"key":"14362_CR21","unstructured":"Wang N, Yan Yeung D (2013) Learning a deep compact image representation for visual tracking. In: In NIPS, pp 809\u2013817"},{"key":"14362_CR22","unstructured":"Wang X, Jabri A, Efros AA Learning correspondence from the cycle-consistency of time. arXiv:1903.07593"},{"key":"14362_CR23","unstructured":"Wang N, Song Y, Ma C, Zhou W, Liu W, Li H Unsupervised deep tracking. arXiv:1904.01828"},{"key":"14362_CR24","unstructured":"Wang X, Shu X, Zhang S, Jiang B, Wang Y, Tian Y, Wu F MFGNet: dynamic modality-aware filter generation for RGB-T tracking. arXiv:2107.10433"},{"key":"14362_CR25","unstructured":"Wang Q, Gao J, Xing J, Zhang M, Hu W DCFNet: discriminant correlation filters network for visual tracking. arXiv:1704.04057"},{"key":"14362_CR26","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) CBAM: convolutional block attention module. arXiv:1807.06521","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"14362_CR27","doi-asserted-by":"publisher","unstructured":"Xu Q, Mei Y, Liu J, Li C (2021) Multimodal cross-layer bilinear pooling for RGBT tracking. IEEE Trans Multimed :1\u20131. https:\/\/doi.org\/10.1109\/TMM.2021.3055362","DOI":"10.1109\/TMM.2021.3055362"},{"key":"14362_CR28","doi-asserted-by":"publisher","unstructured":"Yang R, Zhu Y, Wang X, Li C, Tang J (2019) Learning target-oriented dual attention for robust RGB-T tracking. In: 2019 IEEE international conference on image processing (ICIP). https:\/\/doi.org\/10.1109\/ICIP.2019.8803528, pp 3975\u20133979","DOI":"10.1109\/ICIP.2019.8803528"},{"key":"14362_CR29","doi-asserted-by":"crossref","unstructured":"Yuan W, Wang MY, Chen Q (2020) Self-supervised object tracking with cycle-consistent siamese networks. 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp 10351\u201310358","DOI":"10.1109\/IROS45743.2020.9341621"},{"key":"14362_CR30","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1109\/TIP.2020.3037518","volume":"30","author":"D Yuan","year":"2021","unstructured":"Yuan D, Chang X, Huang P-Y, Liu Q, He Z (2021) Self-supervised deep correlation tracking. IEEE Trans Image Process 30:976\u2013985. https:\/\/doi.org\/10.1109\/TIP.2020.3037518","journal-title":"IEEE Trans Image Process"},{"key":"14362_CR31","doi-asserted-by":"publisher","first-page":"8326","DOI":"10.1109\/TIP.2020.3013162","volume":"29","author":"T Zhou","year":"2020","unstructured":"Zhou T, Li J, Wang S, Tao R, Shen J (2020) MATNet: motion-attentive transition network for zero-shot video object segmentation. IEEE Trans Image Process 29:8326\u20138338. https:\/\/doi.org\/10.1109\/TIP.2020.3013162","journal-title":"IEEE Trans Image Process"},{"key":"14362_CR32","unstructured":"Zhou T, Li J, Li X, Shao L Target-aware object discovery and association for unsupervised video multi-object segmentation. arXiv:2104.04782"},{"key":"14362_CR33","unstructured":"Zhou T, Wang W, Qi S, Ling H, Shen J Cascaded human-object interaction recognition. arXiv:2003.04262"},{"key":"14362_CR34","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1109\/TIP.2021.3132834","volume":"31","author":"T Zhou","year":"2022","unstructured":"Zhou T, Li L, Li X, Feng C-M, Li J, Shao L (2022) Group-wise learning for weakly supervised semantic segmentation. IEEE Trans Image Process 31:799\u2013811. https:\/\/doi.org\/10.1109\/TIP.2021.3132834","journal-title":"IEEE Trans Image Process"},{"key":"14362_CR35","doi-asserted-by":"crossref","unstructured":"Zheng J, Ma C, Peng H, Yang X (2021) Learning to track objects from unlabeled videos. In: Proceedings of the IEEE\/CVF international conference on computer vision","DOI":"10.1109\/ICCV48922.2021.01329"},{"key":"14362_CR36","doi-asserted-by":"publisher","unstructured":"Zhang P, Wang D, Lu H, Yang X Learning adaptive attribute-driven representation for real-time RGB-T tracking. Int J Comput Vis :129. https:\/\/doi.org\/10.1007\/s11263-021-01495-3","DOI":"10.1007\/s11263-021-01495-3"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14362-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14362-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14362-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T09:30:45Z","timestamp":1685439045000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14362-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,2]]},"references-count":36,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["14362"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14362-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,2,2]]},"assertion":[{"value":"1 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}