{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:13:51Z","timestamp":1774419231721,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784439","type":"print"},{"value":"9783031784446","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78444-6_22","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:40:42Z","timestamp":1733222442000},"page":"332-347","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning Explicit Modulation Vectors for\u00a0Disentangled Transformer Attention-Based RGB-D Visual Tracking"],"prefix":"10.1007","author":[{"given":"Yifan","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue-Feng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqing","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Bertinetto, L., Valmadre, J., Henriques, J.F., Vedaldi, A., Torr, P.H.: Fully-convolutional siamese networks for object tracking. In: Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II 14, pp. 850\u2013865. Springer (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L.V., Timofte, R.: Learning discriminative model prediction for tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6182\u20136191 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wang, L., Wu, G.M.: End-to-end tracking with iterative mixed attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA, pp. 18\u201324 (2022)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Atom: accurate tracking by overlap maximization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4660\u20134669 (2019)","DOI":"10.1109\/CVPR.2019.00479"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Xu, T., Feng, Z.H., Wu, X.J., Kittler, J.: Adaptive context-aware discriminative correlation filters for robust visual object tracking. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2514\u20132520. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412559"},{"key":"22_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Gao, S., Yang, J., Li, Z., Zheng, F., Leonardis, A., Song, J.: Learning dual-fused modality-aware representations for RGBD tracking. In: European Conference on Computer Vision, pp. 478\u2013494. Springer (2022)","DOI":"10.1007\/978-3-031-25085-9_27"},{"issue":"10","key":"22_CR10","doi-asserted-by":"publisher","first-page":"7120","DOI":"10.1109\/TCSVT.2022.3169842","volume":"32","author":"Y Hao","year":"2022","unstructured":"Hao, Y., et al.: Attention in attention: modeling context correlation for efficient video classification. IEEE Trans. Circuits Syst. Video Technol. 32(10), 7120\u20137132 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"22_CR12","unstructured":"Kristan, M., et\u00a0al.: The eighth visual object tracking vot2020 challenge results. In: Computer Vision\u2013ECCV 2020 Workshops: Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16, pp. 547\u2013601. Springer (2020)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Li, B., Yan, J., Wu, W., Zhu, Z., Hu, X.: High performance visual tracking with siamese region proposal network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8971\u20138980 (2018)","DOI":"10.1109\/CVPR.2018.00935"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Lukezic, A., et al.: CDTB: a color and depth visual object tracking dataset and benchmark. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10013\u201310022 (2019)","DOI":"10.1109\/ICCV.2019.01011"},{"key":"22_CR16","unstructured":"Luke\u017ei\u010d, A., Zajc, L.\u010c., Voj\u00ed\u0159, T., Matas, J., Kristan, M.: Now you see me: evaluating performance in long-term visual tracking. arXiv preprint arXiv:1804.07056 (2018)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Mayer, C., et al.: Transforming model prediction for tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8731\u20138740 (2022)","DOI":"10.1109\/CVPR52688.2022.00853"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yan, S., Luke\u017ei\u010d, A., Kristan, M., K\u00e4m\u00e4r\u00e4inen, J.K., Matas, J.: Dal: a deep depth-aware long-term tracker. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7825\u20137832. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412984"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"22_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Wei, Q., Zeng, B., Liu, J., He, L., Zeng, G.: Litetrack: layer pruning with asynchronous feature extraction for lightweight and efficient visual tracking. arXiv preprint arXiv:2309.09249 (2023)","DOI":"10.1109\/ICRA57147.2024.10610022"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10448\u201310457 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Yan, S., Yang, J., K\u00e4pyl\u00e4, J., Zheng, F., Leonardis, A., K\u00e4m\u00e4r\u00e4inen, J.K.: Depthtrack: unveiling the power of RGBD tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10725\u201310733 (2021)","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: European Conference on Computer Vision, pp. 341\u2013357. Springer (2022)","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, H., Chen, J., Wang, L., Lu, H.: Arkittrack: a new diverse dataset for tracking using mobile RGB-D data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5126\u20135135 (2023)","DOI":"10.1109\/CVPR52729.2023.00496"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Yang, J., Gao, S., Li, Z., Zheng, F., Leonardis, A.: Resource-efficient RGBD aerial tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13374\u201313383 (2023)","DOI":"10.1109\/CVPR52729.2023.01285"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, P., Liu, Q., Wang, W., Guo, Q.: TSDM: tracking by SiamRPN++ with a depth-refiner and a mask-generator. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 670\u2013676. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413315"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., Lu, H.: Visual prompt multi-modal tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9516\u20139526 (2023)","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, X.F., et al.: RGBD1K: a large-scale dataset and benchmark for RGB-D object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 3870\u20133878 (2023)","DOI":"10.1609\/aaai.v37i3.25500"},{"issue":"1","key":"22_CR31","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s44267-023-00002-1","volume":"1","author":"T Xu","year":"2023","unstructured":"Xu, T., Zhu, X.F., Wu, X.J.: Learning spatio-temporal discriminative model for affine subspace based visual object tracking. Vis. Intell. 1(1), 4 (2023)","journal-title":"Vis. Intell."},{"key":"22_CR32","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neunet.2023.01.003","volume":"161","author":"J Wen","year":"2023","unstructured":"Wen, J., Chu, H., Lai, Z., Xu, T., Shen, L.: Enhanced robust spatial feature selection and correlation filter learning for UAV tracking. Neural Netw. 161, 39\u201354 (2023)","journal-title":"Neural Netw."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78444-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:36:44Z","timestamp":1733225804000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78444-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031784439","9783031784446"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78444-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}