{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:45:21Z","timestamp":1743047121672,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985548"},{"type":"electronic","value":"9789819985555"}],"license":[{"start":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T00:00:00Z","timestamp":1703721600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T00:00:00Z","timestamp":1703721600000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8555-5_6","type":"book-chapter","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T07:02:36Z","timestamp":1703660556000},"page":"68-80","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Feature Disentanglement and\u00a0Adaptive Fusion for\u00a0Improving Multi-modal Tracking"],"prefix":"10.1007","author":[{"given":"Zheng","family":"Li","sequence":"first","affiliation":[]},{"given":"Weibo","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Junhao","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Jianhuang","family":"Lai","sequence":"additional","affiliation":[]},{"given":"Xiaohua","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,28]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Van Gool, L., Timofte, R.: Learning discriminative model prediction for tracking. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 6181\u20136190 (2019)","DOI":"10.1109\/ICCV.2019.00628"},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End Object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Yan, B., Zhu, J., Wang, D., Yang, X., Lu, H.: Transformer tracking. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8122\u20138131 (2021)","DOI":"10.1109\/CVPR46437.2021.00803"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jiang, C., Wu, G., Wang, L.: Mixformer: end-to-end tracking with iterative mixed attention (2023)","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Khan, F.S., Felsberg, M.: Eco: efficient convolution operators for tracking. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6931\u20136939 (2017)","DOI":"10.1109\/CVPR.2017.733"},{"key":"6_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"6_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108945","volume":"249","author":"M Feng","year":"2022","unstructured":"Feng, M., Su, J.: Learning reliable modal weight with transformer for robust RGBT tracking. Knowl.-Based Syst. 249, 108945 (2022)","journal-title":"Knowl.-Based Syst."},{"key":"6_CR8","doi-asserted-by":"publisher","unstructured":"Gao, S., Yang, J., Li, Z., Zheng, F., Leonardis, A., Song, J.: Learning dual-fused modality-aware representations for RGBD tracking. In: Computer Vision - ECCV 2022 Workshops, pp. 478\u2013494. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25085-9_27","DOI":"10.1007\/978-3-031-25085-9_27"},{"key":"6_CR9","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1109\/TPAMI.2014.2345390","volume":"37","author":"JF Henriques","year":"2015","unstructured":"Henriques, J.F., Caseiro, R., Martins, P., Batista, J.: High-speed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. 37, 583\u2013596 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Hou, R., Ren, T., Wu, G.: Mirnet: a robust RGBT tracking jointly with multi-modal interaction and refinement. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2022)","DOI":"10.1109\/ICME52920.2022.9860018"},{"key":"6_CR11","unstructured":"Jiawen, Z., Simiao, l., Xin, C., Wang, D., Lu, H.: Visual prompt multi-modal tracking. In: CVPR (2023)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J., Yan, J.: Siamrpn++: evolution of siamese visual tracking with very deep networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4277\u20134286 (2019)","DOI":"10.1109\/CVPR.2019.00441"},{"key":"6_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.106977","volume":"96","author":"C Li","year":"2019","unstructured":"Li, C., Liang, X., Lu, Y., Zhao, N., Tang, J.: RGB-t object tracking: benchmark and baseline. Pattern Recogn. 96, 106977 (2019)","journal-title":"Pattern Recogn."},{"key":"6_CR14","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1109\/TIP.2021.3130533","volume":"31","author":"C Li","year":"2022","unstructured":"Li, C.: Lasher: a large-scale high-diversity benchmark for RGBT tracking. IEEE Trans. Image Process. 31, 392\u2013404 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR15","doi-asserted-by":"publisher","unstructured":"Li, F., Zha, Y., Zhang, L., Zhang, P., Chen, L.: Information lossless multi-modal image generation for RGB-T tracking. In: Yu, S., et al. (eds.) Pattern Recognition and Computer Vision, pp. 671\u2013683. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-18916-6_53","DOI":"10.1007\/978-3-031-18916-6_53"},{"key":"6_CR16","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TMM.2018.2863604","volume":"21","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Jing, X.Y., Nie, J., Gao, H., Liu, J., Jiang, G.P.: Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in RGB-D videos. IEEE Trans. Multimedia 21, 664\u2013677 (2019)","journal-title":"IEEE Trans. Multimedia"},{"key":"6_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"6_CR18","doi-asserted-by":"publisher","first-page":"5613","DOI":"10.1109\/TIP.2021.3087341","volume":"30","author":"A Lu","year":"2021","unstructured":"Lu, A., Li, C., Yan, Y., Tang, J., Luo, B.: RGBT tracking via multi-adapter network with hierarchical divergence loss. IEEE Trans. Image Process. 30, 5613\u20135625 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Lu, A., Qian, C., Li, C., Tang, J., Wang, L.: Duality-gated mutual condition network for RGBT tracking. IEEE Trans. Neural Netw. Learn. Syst. (2022)","DOI":"10.1109\/TNNLS.2022.3157594"},{"issue":"12","key":"6_CR20","doi-asserted-by":"publisher","first-page":"6305","DOI":"10.1109\/TCYB.2020.2980618","volume":"51","author":"A Luke\u017ai\u010d","year":"2021","unstructured":"Luke\u017ai\u010d, A., Zajc, L.V., Voj\u00ed\u0159, T., Matas, J., Kristan, M.: Performance evaluation methodology for long-term single-object tracking. IEEE Trans. Cybern. 51(12), 6305\u20136318 (2021)","journal-title":"IEEE Trans. Cybern."},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"6_CR22","unstructured":"Pengyu, Z., Zhao, J., Wang, D., Lu, H., Ruan, X.: Visible-thermal UAV tracking: a large-scale benchmark and new baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2022)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yan, S., Luke\u017ei\u010d, A., Kristan, M., K\u00e1m\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 (2021)","DOI":"10.1109\/ICPR48806.2021.9412984"},{"key":"6_CR24","unstructured":"Thangavel, J., Kokul, T., Ramanan, A., Fernando, S.: Transformers in single object tracking: an experimental survey. arXiv preprint arXiv:2302.11867 (2023)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: Cross-modal pattern-propagation for RGB-T tracking. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7062\u20137071 (2020)","DOI":"10.1109\/CVPR42600.2020.00709"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Wu, Y., He, K.: Group normalization. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4784\u20134793 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Xiao, Y., Yang, M., Li, C., Liu, L., Tang, J.: Attribute-based progressive fusion network for RGBT tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 3, pp. 2831\u20132838 (2022)","DOI":"10.1609\/aaai.v36i3.20187"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., Lu, H.: Learning spatio-temporal transformer for visual tracking. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10428\u201310437 (2021)","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Depthtrack: unveiling the power of RGBD tracking. In: ICCV, pp. 10705\u201310713 (2021)","DOI":"10.1109\/ICCV48922.2021.01055"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, Z., Zheng, F., Leonardis, A., Song, J.: Prompting for multi-modal tracking. In: Proceedings of the 30th ACM International Conference on Multimedia, MM 2022, p. 3492\u20133500. Association for Computing Machinery (2022)","DOI":"10.1145\/3503161.3547851"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"Ye, B., Chang, H., Ma, B., Shan, S., Chen, X.: Joint feature learning and relation modeling for tracking: a one-stream framework. In: Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 341\u2013357. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_20","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"6_CR33","doi-asserted-by":"publisher","unstructured":"You, H., et al.: Learning visual representation from modality-shared contrastive language-image pre-training. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, pp. 69\u201387. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_5","DOI":"10.1007\/978-3-031-19812-0_5"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, L., Danelljan, M., Gonzalez-Garcia, A., van de Weijer, J., Khan, F.S.: Multi-modal fusion for end-to-end RGB-T tracking. 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCVW.2019.00278"},{"key":"6_CR35","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, C., Wang, D., Lu, H., Yang, X.: Jointly modeling motion and appearance cues for robust RGB-T tracking. IEEE Trans. Image Process. 30, 3335\u20133347 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"6_CR36","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1109\/TCSVT.2021.3072207","volume":"32","author":"T Zhang","year":"2022","unstructured":"Zhang, T., Liu, X., Zhang, Q., Han, J.: Siamcda: complementarity- and distractor-aware RGB-T tracking based on siamese network. IEEE Trans. Circuits Syst. Video Technol. 32(3), 1403\u20131417 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"6_CR37","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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00496"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"6_CR39","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Rgbd1k: a large-scale dataset and benchmark for RGB-D object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence (2023)"},{"key":"6_CR40","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021)"},{"issue":"1","key":"6_CR41","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TIV.2020.2980735","volume":"6","author":"Y Zhu","year":"2021","unstructured":"Zhu, Y., Li, C., Tang, J., Luo, B.: Quality-aware feature aggregation network for robust RGBT tracking. IEEE Trans. Intell. Veh. 6(1), 121\u2013130 (2021)","journal-title":"IEEE Trans. Intell. Veh."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8555-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T07:03:36Z","timestamp":1703660616000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8555-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,28]]},"ISBN":["9789819985548","9789819985555"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8555-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,28]]},"assertion":[{"value":"28 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}