{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:19:45Z","timestamp":1791303585245,"version":"4.1.0"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"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":["62020106012; 62106089; 62332008; 62336004; U1836218"],"award-info":[{"award-number":["62020106012; 62106089; 62332008; 62336004; U1836218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 Project of Ministry of Education of China","award":["B12018"],"award-info":[{"award-number":["B12018"]}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/V002856\/1; EP\/T022205\/1"],"award-info":[{"award-number":["EP\/V002856\/1; EP\/T022205\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11263-024-01999-8","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T11:06:19Z","timestamp":1708599979000},"page":"2845-2860","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["UniMod1K: Towards a More Universal Large-Scale Dataset and Benchmark for Multi-modal Learning"],"prefix":"10.1007","volume":"132","author":[{"given":"Xue-Feng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongtao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangyong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Kittler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"issue":"2","key":"1999_CR1","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C., & Morency, L. P. (2018). Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 423\u2013443.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1999_CR2","doi-asserted-by":"crossref","unstructured":"Bhat, G., Danelljan, M., Gool, L. V. & 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":"1999_CR3","unstructured":"Bhat, S. F., Birkl, R., Wofk, D., Wonka, P. & M\u00fcller, M. (2023). Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 pp 01\u201320."},{"key":"1999_CR4","first-page":"01","volume":"3","author":"M Camplani","year":"2015","unstructured":"Camplani, M., Hannuna, S. L., Mirmehdi, M., Damen, D., Paiement, A., Tao, L., & Burghardt, T. (2015). Real-time RGB-D tracking with depth scaling kernelised correlation filters and occlusion handling. BMVC, 3, 01\u201312.","journal-title":"BMVC"},{"key":"1999_CR5","doi-asserted-by":"crossref","unstructured":"Chang, A., Dai, A., Funkhouser, T., Halber, M., Niebner, M., Savva, M., Song, S., Zeng, A., & Zhang, Y. (2017). Matterport3d: Learning from RGB-D data in indoor environments. In 2017 International conference on 3D vision (3DV), IEEE Computer Society (pp. 667\u2013676).","DOI":"10.1109\/3DV.2017.00081"},{"key":"1999_CR6","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":"1999_CR7","doi-asserted-by":"crossref","unstructured":"Danelljan, M., Bhat, G., Shahbaz\u00a0Khan, F. & Felsberg, M. (2017). Eco: Efficient convolution operators for tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6638\u20136646).","DOI":"10.1109\/CVPR.2017.733"},{"key":"1999_CR8","doi-asserted-by":"crossref","unstructured":"Ding, P., & Song, Y. (2015). Robust object tracking using color and depth images with a depth based occlusion handling and recovery. In 2015 12th International conference on fuzzy systems and knowledge discovery (FSKD). IEEE (pp. 930\u2013935).","DOI":"10.1109\/FSKD.2015.7382068"},{"key":"1999_CR9","doi-asserted-by":"crossref","unstructured":"Eigen, D., & Fergus, R. (2015). Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In Proceedings of the IEEE international conference on computer vision (pp. 2650\u20132658).","DOI":"10.1109\/ICCV.2015.304"},{"key":"1999_CR10","first-page":"01","volume":"27","author":"D Eigen","year":"2014","unstructured":"Eigen, D., Puhrsch, C., & Fergus, R. (2014). Depth map prediction from a single image using a multi-scale deep network. Advances in Neural Information Processing Systems, 27, 01\u201309.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1999_CR11","doi-asserted-by":"crossref","unstructured":"Fan, H., Lin, L., Yang, F., Chu, P., Deng, G., Yu, S., Bai, H., Xu, Y., Liao, C. & Ling, H. (2019). Lasot: A high-quality benchmark for large-scale single object tracking. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5374\u20135383).","DOI":"10.1109\/CVPR.2019.00552"},{"issue":"3","key":"1999_CR12","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng, D., Haase-Sch\u00fctz, C., Rosenbaum, L., Hertlein, H., Glaeser, C., Timm, F., Wiesbeck, W., & Dietmayer, K. (2020). Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Transactions on Intelligent Transportation Systems, 22(3), 1341\u20131360.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"1999_CR13","doi-asserted-by":"crossref","unstructured":"Feng, Q., Ablavsky, V., Bai, Q., Li, G. & Sclaroff, S. (2020b). Real-time visual object tracking with natural language description. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 700\u2013709).","DOI":"10.1109\/WACV45572.2020.9093425"},{"key":"1999_CR14","doi-asserted-by":"crossref","unstructured":"Feng, Q., Ablavsky, V., Bai, Q. & Sclaroff, S. (2021). Siamese natural language tracker: Tracking by natural language descriptions with siamese trackers. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 5851\u20135860).","DOI":"10.1109\/CVPR46437.2021.00579"},{"key":"1999_CR15","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., Batmanghelich, K. & Tao, D. (2018). Deep ordinal regression network for monocular depth estimation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2002\u20132011).","DOI":"10.1109\/CVPR.2018.00214"},{"key":"1999_CR16","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P. & Urtasun, R. (2012). Are we ready for autonomous driving? The kitti vision benchmark suite. In 2012 IEEE conference on computer vision and pattern recognition. IEEE (pp. 3354\u20133361).","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1999_CR17","first-page":"4446","volume":"35","author":"M Guo","year":"2022","unstructured":"Guo, M., Zhang, Z., Fan, H., & Jing, L. (2022). Divert more attention to vision-language tracking. Advances in Neural Information Processing Systems, 35, 4446\u20134460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"1999_CR18","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"},{"key":"1999_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 16000\u201316009).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"1999_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2018.09.014","volume":"50","author":"J Mx","year":"2019","unstructured":"Mx, J., Deng, C., Js, S., Yy, W., Yj, J., & Sun, X. (2019). Hierarchical multi-modal fusion FCN with attention model for RGB-D tracking. Information Fusion, 50, 1\u20138.","journal-title":"Information Fusion"},{"key":"1999_CR21","doi-asserted-by":"crossref","unstructured":"Jung, I., Son, J., Baek, M. & Han, B. (2018). Real-time mdnet. In Proceedings of the European conference on computer vision. Springer (pp. 83\u201398).","DOI":"10.1007\/978-3-030-01225-0_6"},{"key":"1999_CR22","doi-asserted-by":"crossref","unstructured":"Kart, U., Kamarainen, J. K. & Matas, J. (2018). How to make an RGBD tracker? In Proceedings of the european conference on computer vision (ECCV) Workshops (pp. 01\u201315).","DOI":"10.1007\/978-3-030-11009-3_8"},{"key":"1999_CR23","doi-asserted-by":"crossref","unstructured":"Kart, U., Lukezic, A., Kristan, M., Kamarainen, J. K., & Matas, J. (2019). Object tracking by reconstruction with view-specific discriminative correlation filters. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 1339\u20131348).","DOI":"10.1109\/CVPR.2019.00143"},{"key":"1999_CR24","unstructured":"Kenton, J. D. M. W. C., & Toutanova, L. K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT (pp. 4171\u20134186)."},{"key":"1999_CR25","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., Cehovin\u00a0Zajc, L., Vojir, T., Bhat, G., Lukezic, A., & Eldesokey, A., et\u00a0al. (2018). The sixth visual object tracking vot2018 challenge results. In Proceedings of the European conference on computer vision workshops. Springer (pp. 01\u201352)."},{"key":"1999_CR26","doi-asserted-by":"crossref","unstructured":"Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Pflugfelder, R., Kamarainen, J. K., Cehovin\u00a0Zajc, L., Drbohlav, O., Lukezic, A., & Berg, A., et\u00a0al. (2019). The seventh visual object tracking vot2019 challenge results. In Proceedings of the IEEE\/CVF international conference on computer vision workshops (pp. 01\u201336).","DOI":"10.1109\/ICCVW.2019.00276"},{"key":"1999_CR27","doi-asserted-by":"crossref","unstructured":"Kristan, M., Leonardis, A., Matas, J., Felsberg, M., Pflugfelder, R., K\u00e4m\u00e4r\u00e4inen, J. K., Danelljan, M., Zajc, L\u010c., Luke\u017ei\u010d, A., & Drbohlav, O., et\u00a0al. (2020). The eighth visual object tracking vot2020 challenge results. In European conference on computer vision. Springer (pp. 547\u2013601).","DOI":"10.1007\/978-3-030-68238-5_39"},{"key":"1999_CR28","doi-asserted-by":"crossref","unstructured":"Kristan, M., Matas, J., Leonardis, A., Felsberg, M., Pflugfelder, R., K\u00e4m\u00e4r\u00e4inen, J. K., Chang, H. J., Danelljan, M., Cehovin, L., & Luke\u017ei\u010d, A., et\u00a0al. (2021). The ninth visual object tracking vot2021 challenge results. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 2711\u20132738).","DOI":"10.1109\/ICCVW54120.2021.00305"},{"key":"1999_CR29","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., Tombari, F., & Navab, N. (2016). Deeper depth prediction with fully convolutional residual networks. In 2016 Fourth international conference on 3D vision (3DV). IEEE (pp. 239\u2013248).","DOI":"10.1109\/3DV.2016.32"},{"key":"1999_CR30","doi-asserted-by":"crossref","unstructured":"Levin, A., Lischinski, D., & Weiss, Y. (2004). Colorization using optimization. ACM SIGGRAPH 2004 Papers (pp. 689\u2013694). NY, USA: ACM New York.","DOI":"10.1145\/1186562.1015780"},{"key":"1999_CR31","doi-asserted-by":"crossref","unstructured":"Li, B., Wu, W., Wang, Q., Zhang, F., Xing, J. & Yan, J. (2019). Siamrpn++: Evolution of siamese visual tracking with very deep networks. In IEEE conference on computer vision and pattern recognition (pp. 4282\u20134291).","DOI":"10.1109\/CVPR.2019.00441"},{"key":"1999_CR32","doi-asserted-by":"crossref","unstructured":"Li, Z., Tao, R., Gavves, E., Snoek, C. G., & Smeulders, A. W. (2017). Tracking by natural language specification. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6495\u20136503).","DOI":"10.1109\/CVPR.2017.777"},{"key":"1999_CR33","unstructured":"Liu, C., Kumar, S., Gu, S., Timofte, R., & Van\u00a0Gool, L. (2023). Va-depthnet: A variational approach to single image depth prediction. arXiv preprint arXiv:2302.06556 pp 01\u201321."},{"key":"1999_CR34","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s11263-019-01247-4","volume":"128","author":"L Liu","year":"2020","unstructured":"Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietik\u00e4inen, M. (2020). Deep learning for generic object detection: A survey. International Journal of Computer Vision, 128, 261\u2013318.","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"1999_CR35","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TMM.2018.2863604","volume":"21","author":"Y Liu","year":"2018","unstructured":"Liu, Y., Jing, X. Y., Nie, J., Gao, H., Liu, J., & Jiang, G. P. (2018). Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in RGB-D videos. IEEE Transactions on Multimedia, 21(3), 664\u2013677.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1999_CR36","unstructured":"Luke\u017ei\u010d, A., Zajc, L\u010c., Voj\u00ed\u0159, T., Matas, J., & Kristan, M. (2018). Now you see me: Evaluating performance in long-term visual tracking. arXiv preprint arXiv:1804.07056 pp 01\u201316."},{"key":"1999_CR37","doi-asserted-by":"crossref","unstructured":"Lukezic, A., Kart, U., Kapyla, J., Durmush, A., Kamarainen, J. K., Matas, J., & Kristan, M. (2019). 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).","DOI":"10.1109\/ICCV.2019.01011"},{"issue":"5","key":"1999_CR38","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/TITS.2020.3046478","volume":"23","author":"SM Marvasti-Zadeh","year":"2021","unstructured":"Marvasti-Zadeh, S. M., Cheng, L., Ghanei-Yakhdan, H., & Kasaei, S. (2021). Deep learning for visual tracking: A comprehensive survey. IEEE Transactions on Intelligent Transportation Systems, 23(5), 3943\u20133968.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"1999_CR39","unstructured":"Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A. D., & van\u00a0de Weijer, J. (2022). Class-incremental learning: Survey and performance evaluation on image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 1\u201320."},{"key":"1999_CR40","doi-asserted-by":"crossref","unstructured":"Mayer, C., Danelljan, M., Paudel, D. P., & Van\u00a0Gool, L. (2021). Learning target candidate association to keep track of what not to track. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 13444\u201313454).","DOI":"10.1109\/ICCV48922.2021.01319"},{"key":"1999_CR41","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.cviu.2016.05.011","volume":"150","author":"K Meshgi","year":"2016","unstructured":"Meshgi, K., Si, M., Oba, S., Skibbe, H., Yz, L., & Ishii, S. (2016). An occlusion-aware particle filter tracker to handle complex and persistent occlusions. Computer Vision and Image Understanding, 150, 81\u201394.","journal-title":"Computer Vision and Image Understanding"},{"issue":"7","key":"1999_CR42","first-page":"3523","volume":"44","author":"S Minaee","year":"2021","unstructured":"Minaee, S., Boykov, Y. Y., Porikli, F., Plaza, A. J., Kehtarnavaz, N., & Terzopoulos, D. (2021). Image segmentation using deep learning: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7), 3523\u20133542.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1999_CR43","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.neucom.2020.12.089","volume":"438","author":"Y Ming","year":"2021","unstructured":"Ming, Y., Meng, X., Fan, C., & Yu, H. (2021). Deep learning for monocular depth estimation: A review. Neurocomputing, 438, 14\u201333.","journal-title":"Neurocomputing"},{"issue":"9","key":"1999_CR44","doi-asserted-by":"publisher","first-page":"2093","DOI":"10.1109\/TMM.2017.2729400","volume":"19","author":"H M\u00fcller","year":"2017","unstructured":"M\u00fcller, H., & Unay, D. (2017). Retrieval from and understanding of large-scale multi-modal medical datasets: A review. IEEE Transactions on Multimedia, 19(9), 2093\u20132104.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1999_CR45","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s11263-016-0901-x","volume":"118","author":"C Palmero","year":"2016","unstructured":"Palmero, C., Clap\u00e9s, A., Bahnsen, C., M\u00f8gelmose, A., Moeslund, T. B., & Escalera, S. (2016). Multi-modal RGB-depth-thermal human body segmentation. International Journal of Computer Vision, 118, 217\u2013239.","journal-title":"International Journal of Computer Vision"},{"key":"1999_CR46","doi-asserted-by":"crossref","unstructured":"Qian, Y., Yan, S., Luke\u017ei\u010d, A., Kristan, M., K\u00e4m\u00e4r\u00e4inen, J. K., & Matas, J. (2021). Dal: A deep depth-aware long-term tracker. In 2020 25th International conference on pattern recognition (ICPR). IEEE (pp. 7825\u20137832).","DOI":"10.1109\/ICPR48806.2021.9412984"},{"key":"1999_CR47","doi-asserted-by":"crossref","unstructured":"Ramamonjisoa, M., Firman, M., Watson, J., Lepetit, V. & Turmukhambetov, D. (2021). Single image depth prediction with wavelet decomposition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 11089\u201311098).","DOI":"10.1109\/CVPR46437.2021.01094"},{"key":"1999_CR48","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021). Vision transformers for dense prediction. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 12179\u201312188).","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"1999_CR49","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"issue":"5","key":"1999_CR50","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TPAMI.2008.132","volume":"31","author":"A Saxena","year":"2008","unstructured":"Saxena, A., Sun, M., & Ng, A. Y. (2008). Make3d: Learning 3d scene structure from a single still image. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(5), 824\u2013840.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7576","key":"1999_CR51","first-page":"746","volume":"5","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012). Indoor segmentation and support inference from RGBD images. ECCV, 5(7576), 746\u2013760.","journal-title":"ECCV"},{"issue":"11","key":"1999_CR52","doi-asserted-by":"publisher","first-page":"4381","DOI":"10.1109\/TCSVT.2021.3049869","volume":"31","author":"M Song","year":"2021","unstructured":"Song, M., Lim, S., & Kim, W. (2021). Monocular depth estimation using Laplacian pyramid-based depth residuals. IEEE Transactions on Circuits and Systems for Video Technology, 31(11), 4381\u20134393.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1999_CR53","doi-asserted-by":"crossref","unstructured":"Song, S., & Xiao, J. (2013). Tracking revisited using rgbd camera: Unified benchmark and baselines. In Proceedings of the IEEE international conference on computer vision (pp. 233\u2013240).","DOI":"10.1109\/ICCV.2013.36"},{"key":"1999_CR54","unstructured":"Summaira, J., Li, X., Shoib, A. M., Li, S., & Abdul, J. (2021). Recent advances and trends in multimodal deep learning: A review. arXiv preprint arXiv:2105.11087 pp 01\u201335."},{"issue":"11","key":"1999_CR55","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1007\/s11263-022-01646-0","volume":"130","author":"P Sun","year":"2022","unstructured":"Sun, P., Zhang, W., Li, S., Guo, Y., Song, C., & Li, X. (2022). Learnable depth-sensitive attention for deep rgb-d saliency detection with multi-modal fusion architecture search. International Journal of Computer Vision, 130(11), 2822\u20132841.","journal-title":"International Journal of Computer Vision"},{"key":"1999_CR56","doi-asserted-by":"crossref","unstructured":"Valmadre, J., Bertinetto, L., Henriques, J. F., Tao, R., Vedaldi, A., Smeulders, A. W., Torr, P. H., & Gavves, E. (2018). Long-term tracking in the wild: A benchmark. In Proceedings of the European conference on computer vision (ECCV) (pp. 670\u2013685).","DOI":"10.1007\/978-3-030-01219-9_41"},{"key":"1999_CR57","unstructured":"Wang, X., Li, C., Yang, R., Zhang, T., Tang, J., & Luo, B. (2018). Describe and attend to track: Learning natural language guided structural representation and visual attention for object tracking. arXiv preprint arXiv:1811.10014 pp 01\u201312."},{"key":"1999_CR58","doi-asserted-by":"crossref","unstructured":"Wang, X., Shu, X., Zhang, Z., Jiang, B., Wang, Y., Tian, Y., & Wu, F. (2021). Towards more flexible and accurate object tracking with natural language: Algorithms and benchmark. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13763\u201313773).","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"1999_CR59","doi-asserted-by":"crossref","unstructured":"Wu, C. Y., Wang, J., Hall, M., Neumann, U., & Su, S. (2022). Toward practical monocular indoor depth estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3814\u20133824).","DOI":"10.1109\/CVPR52688.2022.00379"},{"issue":"9","key":"1999_CR60","doi-asserted-by":"publisher","first-page":"1834","DOI":"10.1109\/TPAMI.2014.2388226","volume":"37","author":"Y Wu","year":"2015","unstructured":"Wu, Y., Lim, J., & Yang, M. H. (2015). Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9), 1834\u20131848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"1999_CR61","first-page":"3121","volume":"45","author":"W Xia","year":"2022","unstructured":"Xia, W., Zhang, Y., Yang, Y., Xue, J. H., Zhou, B., & Yang, M. H. (2022). Gan inversion: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 3121\u20133138.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"8","key":"1999_CR62","doi-asserted-by":"publisher","first-page":"2485","DOI":"10.1109\/TCYB.2017.2740952","volume":"48","author":"J Xiao","year":"2017","unstructured":"Xiao, J., Stolkin, R., Gao, Y., & Leonardis, A. (2017). Robust fusion of color and depth data for rgb-d target tracking using adaptive range-invariant depth models and spatio-temporal consistency constraints. IEEE Transactions on Cybernetics, 48(8), 2485\u20132499.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"1999_CR63","doi-asserted-by":"crossref","unstructured":"Xie, Z., Geng, Z., Hu, J., Zhang, Z., Hu, H., & Cao, Y. (2023). Revealing the dark secrets of masked image modeling. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 14475\u201314485).","DOI":"10.1109\/CVPR52729.2023.01391"},{"issue":"1","key":"1999_CR64","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. (2023). Learning spatio-temporal discriminative model for affine subspace based visual object tracking. Visual Intelligence, 1(1), 4.","journal-title":"Visual Intelligence"},{"key":"1999_CR65","doi-asserted-by":"crossref","unstructured":"Yan, B., Peng, H., Fu, J., Wang, D., & Lu, H. (2021a). 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":"1999_CR66","doi-asserted-by":"crossref","unstructured":"Yan, S., Yang, J., K\u00e4pyl\u00e4, J., Zheng, F., Leonardis, A., & K\u00e4m\u00e4r\u00e4inen, J. K. (2021b). 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":"1999_CR67","unstructured":"Yang, J., Li, Z., Yan, S., Zheng, F., Leonardis, A., K\u00e4m\u00e4r\u00e4inen, J. K., & Shao, L. (2022). Rgbd object tracking: An in-depth review. arXiv preprint arXiv:2203.14134 pp 01\u201335."},{"issue":"9","key":"1999_CR68","doi-asserted-by":"publisher","first-page":"3433","DOI":"10.1109\/TCSVT.2020.3038720","volume":"31","author":"Z Yang","year":"2020","unstructured":"Yang, Z., Kumar, T., Chen, T., Su, J., & Luo, J. (2020). Grounding-tracking-integration. IEEE Transactions on Circuits and Systems for Video Technology, 31(9), 3433\u20133443.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"1999_CR69","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":"1999_CR70","doi-asserted-by":"crossref","unstructured":"Yuan, W., Gu, X., Dai, Z., Zhu, S., & Tan, P. (2022). New crfs: Neural window fully-connected crfs for monocular depth estimation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 01\u201310).","DOI":"10.1109\/CVPR52688.2022.00389"},{"key":"1999_CR71","unstructured":"Zhang, P., Wang, D., &, Lu, H. (2020). Multi-modal visual tracking: Review and experimental comparison. arXiv preprint arXiv:2012.04176 pp 01\u201340."},{"key":"1999_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhao, J., Wang, D., Lu, H., & Ruan, X. (2022). Visible-thermal uav tracking: A large-scale benchmark and new baseline. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8886\u20138895).","DOI":"10.1109\/CVPR52688.2022.00868"},{"key":"1999_CR73","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.patrec.2023.02.023","volume":"168","author":"H Zhao","year":"2023","unstructured":"Zhao, H., Wang, X., Wang, D., Lu, H., & Ruan, X. (2023). Transformer vision-language tracking via proxy token guided cross-modal fusion. Pattern Recognition Letters, 168, 10\u201316.","journal-title":"Pattern Recognition Letters"},{"key":"1999_CR74","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":"1999_CR75","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., & Lu, J. (2023b). Unleashing text-to-image diffusion models for visual perception. In Proceedings of the IEEE international conference on computer vision (pp. 01\u201310).","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"1999_CR76","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Z., Mao, K., & He, Z. (2023). Joint visual grounding and tracking with natural language specification. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 23151\u201323160).","DOI":"10.1109\/CVPR52729.2023.02217"},{"key":"1999_CR77","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., & Lu, H. (2023a). Visual prompt multi-modal tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9516\u20139526).","DOI":"10.1109\/CVPR52729.2023.00918"},{"key":"1999_CR78","doi-asserted-by":"publisher","first-page":"3870","DOI":"10.1609\/aaai.v37i3.25500","volume":"37","author":"XF Zhu","year":"2023","unstructured":"Zhu, X. F., Xu, T., Tang, Z., Wu, Z., Liu, H., Yang, X., Wu, X. J., & Kittler, J. (2023). Rgbd1k: A large-scale dataset and benchmark for rgb-d object tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 37, 3870\u20133878.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-01999-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-01999-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-01999-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T14:14:46Z","timestamp":1720707286000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-01999-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":78,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1999"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-01999-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,22]]},"assertion":[{"value":"3 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}