{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:49:31Z","timestamp":1786981771802,"version":"build-2736575974"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T00:00:00Z","timestamp":1736294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T00:00:00Z","timestamp":1736294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011047","name":"AGE-WELL","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001804","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":[[2025,6]]},"DOI":"10.1007\/s11263-024-02336-9","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T15:18:46Z","timestamp":1736349526000},"page":"3392-3412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["LDTrack: Dynamic People Tracking by Service Robots Using Diffusion Models"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3669-4182","authenticated-orcid":false,"given":"Angus","family":"Fung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5097-3965","authenticated-orcid":false,"given":"Beno","family":"Benhabib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7080-6857","authenticated-orcid":false,"given":"Goldie","family":"Nejat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,8]]},"reference":[{"key":"2336_CR1","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1007\/978-981-15-3639-7_98","volume-title":"Advances in Mechanical Engineering","author":"K Agrawal","year":"2021","unstructured":"Agrawal, K., & Lal, R. (2021). Person following mobile robot using multiplexed detection and tracking. In V. R. Kalamkar & K. Monkova (Eds.), Advances in Mechanical Engineering (pp. 815\u2013822). Berlin: Springer."},{"issue":"1","key":"2336_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., & Stiefelhagen, R. (2008). Evaluating multiple object tracking performance: The CLEAR MOT metrics. EURASIP Journal on Image and Video Processing, 2008(1), 1\u201310.","journal-title":"EURASIP Journal on Image and Video Processing"},{"key":"2336_CR3","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. (2016). Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP) (pp. 3464\u20133468).","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"2336_CR4","doi-asserted-by":"crossref","unstructured":"Cai, J., Xu, M., Li, W., Xiong, Y., Xia, W., Tu, Z., & Soatto, S. (2022, March 31). MeMOT: multi-object tracking with memory. arXiv. https:\/\/arxiv.org\/abs\/2203.16761","DOI":"10.1109\/CVPR52688.2022.00792"},{"key":"2336_CR5","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer vision\u2014ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In A. Vedaldi, H. Bischof, T. Brox, & J.-M. Frahm (Eds.), Computer vision\u2014ECCV 2020 (Vol. 12346, pp. 213\u2013229). Berlin: Springer."},{"key":"2336_CR6","unstructured":"Chaabane, M., Zhang, P., Beveridge, J. R., & O\u2019Hara, S. (2021, June 6). DEFT: Detection embeddings for tracking. arXiv http:\/\/arxiv.org\/abs\/2102.02267."},{"key":"2336_CR7","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., & Luo, P. (2023). DiffusionDet: Diffusion model for object detection. In 2023 IEEE\/CVF international conference on computer vision (ICCV) (pp. 19773\u201319786). Paris: IEEE.","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"2336_CR8","unstructured":"Chuang, Z., Sifa, Z., Haoran, W., Ziqing, G., Wenchao, S., & Lei, Y. (2024, February 1). AttentionTrack: Multiple object tracking in traffic scenarios using features attention. https:\/\/ieeexplore.ieee.org\/abstract\/document\/10260285?casa_token=CKgXKurS06oAAAAA:Ghg0vJ0bQ1X3nftk2dCiyHnmWDS7_UFKQvR8EoH3HtG6Tu14-fBVYb_FaGowl4Y8nijjzEQcUYk."},{"key":"2336_CR9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3216514","author":"Z Dai","year":"2022","unstructured":"Dai, Z., Cai, B., Lin, Y., & Chen, J. (2022). UP-DETR: Unsupervised pre-training for object detection with transformers. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2022.3216514","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"2336_CR10","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s11263-020-01393-0","volume":"129","author":"P Dendorfer","year":"2021","unstructured":"Dendorfer, P., Osep, A., Milan, A., Schindler, K., Cremers, D., Reid, I., et al. (2021). MOTChallenge: A benchmark for single-camera multiple target tracking. International Journal of Computer Vision, 129(4), 845\u2013881.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"2336_CR11","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s11263-022-01706-5","volume":"131","author":"D Dworakowski","year":"2023","unstructured":"Dworakowski, D., Fung, A., & Nejat, G. (2023). Robots understanding contextual information in human-centered environments using weakly supervised mask data distillation. International Journal of Computer Vision, 131(2), 407\u2013430.","journal-title":"International Journal of Computer Vision"},{"issue":"6","key":"2336_CR12","doi-asserted-by":"publisher","first-page":"3550","DOI":"10.1109\/LRA.2023.3269306","volume":"8","author":"A Fung","year":"2023","unstructured":"Fung, A., Benhabib, B., & Nejat, G. (2023). Robots autonomously detecting people: A multimodal deep contrastive learning method robust to intraclass variations. IEEE Robotics and Automation Letters, 8(6), 3550\u20133557.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"3","key":"2336_CR13","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s43154-020-00011-8","volume":"1","author":"A Fung","year":"2020","unstructured":"Fung, A., Wang, L. Y., Zhang, K., Nejat, G., & Benhabib, B. (2020). Using deep learning to find victims in unknown cluttered urban search and rescue environments. Current Robotics Reports, 1(3), 105\u2013115.","journal-title":"Current Robotics Reports"},{"key":"2336_CR14","unstructured":"Gao, R., Zhang, Y., & Wang, L. (2024, March 25). Multiple object tracking as ID prediction. arXiv http:\/\/arxiv.org\/abs\/2403.16848."},{"issue":"5","key":"2336_CR15","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1007\/s11263-019-01236-7","volume":"128","author":"S Gupta","year":"2020","unstructured":"Gupta, S., Tolani, V., Davidson, J., Levine, S., Sukthankar, R., & Malik, J. (2020). Cognitive mapping and planning for visual navigation. International Journal of Computer Vision, 128(5), 1311\u20131330.","journal-title":"International Journal of Computer Vision"},{"key":"2336_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2336_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. In 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 2980\u20132988).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2336_CR18","unstructured":"Ho, J., Jain, A., & Abbeel, P. (2020). Denoising diffusion probabilistic models. In Advances in neural information processing systems (Vol. 33, pp. 6840\u20136851). Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/4c5bcfec8584af0d967f1ab10179ca4b-Abstract.html"},{"key":"2336_CR19","unstructured":"Jiang, L., Wang, Z., Yin, S., Ma, G., Zhang, P., & Wu, B. (2024, August 28). ConsistencyTrack: A robust multi-object tracker with a generation strategy of consistency model. arXiv. https:\/\/arxiv.org\/abs\/2408.15548"},{"key":"2336_CR20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.robot.2019.01.011","volume":"114","author":"M Kollmitz","year":"2019","unstructured":"Kollmitz, M., Eitel, A., Vasquez, A., & Burgard, W. (2019). Deep 3D perception of people and their mobility aids. Robotics and Autonomous Systems, 114, 29\u201340.","journal-title":"Robotics and Autonomous Systems"},{"issue":"1\u20132","key":"2336_CR21","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1\u20132), 83\u201397.","journal-title":"Naval Research Logistics Quarterly"},{"issue":"2","key":"2336_CR22","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","volume":"42","author":"T-Y Lin","year":"2020","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2020). Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2), 318\u2013327.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"2336_CR23","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s11263-021-01529-w","volume":"130","author":"T Liu","year":"2022","unstructured":"Liu, T., Sun, J. J., Zhao, L., Zhao, J., Yuan, L., Wang, Y., et al. (2022). View-invariant, occlusion-robust probabilistic embedding for human pose. International Journal of Computer Vision, 130(1), 111\u2013135.","journal-title":"International Journal of Computer Vision"},{"key":"2336_CR24","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer vision\u2014ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016). SSD: Single shot MultiBox detector. In B. Leibe, J. Matas, N. Sebe, & M. Welling (Eds.), Computer vision\u2014ECCV 2016 (pp. 21\u201337). Berlin: Springer."},{"key":"2336_CR25","doi-asserted-by":"crossref","unstructured":"Lu, Z., Rathod, V., Votel, R., & Huang, J. (2020). RetinaTrack: Online single stage joint detection and tracking. In 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 14656\u201314666). Seattle, WA, USA: IEEE.","DOI":"10.1109\/CVPR42600.2020.01468"},{"key":"2336_CR26","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., & Van Gool, L. (2022). RePaint: Inpainting using denoising diffusion probabilistic models. In 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 11451\u201311461). New Orleans, LA, USA: IEEE.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"2336_CR27","unstructured":"Luo, R., Song, Z., Ma, L., Wei, J., Yang, W., & Yang, M. (2023, August 19). DiffusionTrack: Diffusion model for multi-object tracking. arXiv http:\/\/arxiv.org\/abs\/2308.09905"},{"key":"2336_CR28","doi-asserted-by":"crossref","unstructured":"Mees, O., Eitel, A., & Burgard, W. (2016). Choosing smartly: Adaptive multimodal fusion for object detection in changing environments. In 2016 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 151\u2013156). Daejeon, South Korea: IEEE.","DOI":"10.1109\/IROS.2016.7759048"},{"key":"2336_CR29","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., & Feichtenhofer, C. (2022). TrackFormer: Multi-object tracking with transformers. In 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 8834\u20138844), New Orleans, LA, USA: IEEE.","DOI":"10.1109\/CVPR52688.2022.00864"},{"issue":"1","key":"2336_CR30","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1109\/TCYB.2022.3166481","volume":"53","author":"SC Mohamed","year":"2023","unstructured":"Mohamed, S. C., Fung, A., & Nejat, G. (2023). A multirobot person search system for finding multiple dynamic users in human-centered environments. IEEE Transactions on Cybernetics, 53(1), 628\u2013640.","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"3","key":"2336_CR31","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s10514-014-9385-0","volume":"37","author":"M Munaro","year":"2014","unstructured":"Munaro, M., & Menegatti, E. (2014). Fast RGB-D people tracking for service robots. Autonomous Robots, 37(3), 227\u2013242.","journal-title":"Autonomous Robots"},{"key":"2336_CR32","unstructured":"Murray, S. (2017). Real-time multiple object tracking\u2014A study on the importance of speed. arXiv:1709.03572 [cs]"},{"issue":"2","key":"2336_CR33","doi-asserted-by":"publisher","first-page":"2965","DOI":"10.1109\/JSYST.2019.2942953","volume":"14","author":"L Pang","year":"2020","unstructured":"Pang, L., Cao, Z., Yu, J., Guan, P., Chen, X., & Zhang, W. (2020). A robust visual person-following approach for mobile robots in disturbing environments. IEEE Systems Journal, 14(2), 2965\u20132968.","journal-title":"IEEE Systems Journal"},{"issue":"3","key":"2336_CR34","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.3390\/app12031319","volume":"12","author":"R Pereira","year":"2022","unstructured":"Pereira, R., Carvalho, G., Garrote, L., & Nunes, U. J. (2022). Sort and deep-SORT based multi-object tracking for mobile robotics: Evaluation with new data association metrics. Applied Sciences, 12(3), 1319.","journal-title":"Applied Sciences"},{"key":"2336_CR35","doi-asserted-by":"crossref","unstructured":"Pinto, V., Bettencourt, R., & Ventura, R. (2023). People re-identification in service robots. In 2023 IEEE international conference on autonomous robot systems and competitions (ICARSC) (pp. 44\u201349), Tomar, Portugal: IEEE.","DOI":"10.1109\/ICARSC58346.2023.10129612"},{"key":"2336_CR36","doi-asserted-by":"crossref","unstructured":"Rebello, J., Fung, A., & Waslander, S. L. (2020). AC\/DCC\u202f: Accurate calibration of dynamic camera clusters for visual SLAM. In 2020 IEEE international conference on robotics and automation (ICRA) (pp. 6035\u20136041).","DOI":"10.1109\/ICRA40945.2020.9197217"},{"key":"2336_CR37","unstructured":"Redmon, J., & Farhadi, A. (2018, April 8). YOLOv3: An incremental improvement. arXiv. http:\/\/arxiv.org\/abs\/1804.02767"},{"key":"2336_CR38","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 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 658\u2013666).","DOI":"10.1109\/CVPR.2019.00075"},{"key":"2336_CR39","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 10674\u201310685), New Orleans, LA, USA: IEEE.","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"3","key":"2336_CR40","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s11263-006-0023-y","volume":"74","author":"E Royer","year":"2007","unstructured":"Royer, E., Lhuillier, M., Dhome, M., & Lavest, J.-M. (2007). Monocular vision for mobile robot localization and autonomous navigation. International Journal of Computer Vision, 74(3), 237\u2013260.","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"2336_CR41","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., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2336_CR42","doi-asserted-by":"crossref","unstructured":"Sanz, D., Ahmad, A., & Lima, P. (2015). Onboard robust person detection and tracking for domestic service robots. In Robot 2015: Second iberian robotics conference (pp. 547\u2013559). Cham: Springer.","DOI":"10.1007\/978-3-319-27149-1_42"},{"key":"2336_CR43","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., & Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd international conference on machine learning (pp. 2256\u20132265)."},{"key":"2336_CR44","doi-asserted-by":"crossref","unstructured":"Sun, S., Zhao, X., & Tan, M. (2019). Fast and robust RGB-D multiple human tracking based on part model for mobile robots. In 2019 Chinese control conference (CCC) (pp. 4525\u20134530). Guangzhou, China: IEEE.","DOI":"10.23919\/ChiCC.2019.8866103"},{"key":"2336_CR45","doi-asserted-by":"crossref","unstructured":"Sun, Pei, Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., et al. (2020). Scalability in perception for autonomous driving: Waymo open dataset. In 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). Presented at the 2020 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 2443\u20132451).","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"2336_CR46","unstructured":"Sun, Peize, Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., et al. (2021, May 4). TransTrack: Multiple object tracking with transformer. arXiv. http:\/\/arxiv.org\/abs\/2012.15460"},{"key":"2336_CR47","unstructured":"Tan, A. H., Narasimhan, S., & Nejat, G. (2024, February 27). 4CNet: A confidence-aware, contrastive, conditional, consistency model for robot map prediction in multi-robot environments. arXiv. https:\/\/arxiv.org\/abs\/2402.17904"},{"issue":"1","key":"2336_CR48","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/LRA.2022.3224667","volume":"8","author":"AH Tan","year":"2023","unstructured":"Tan, A. H., Bejarano, F. P., Zhu, Y., Ren, R., & Nejat, G. (2023). Deep reinforcement learning for decentralized multi-robot exploration with macro actions. IEEE Robotics and Automation Letters, 8(1), 272\u2013279.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2336_CR49","doi-asserted-by":"crossref","unstructured":"Taylor, A., & Riek, L. D. (2022). REGROUP: A robot-centric group detection and tracking system. In 2022 17th ACM\/IEEE International Conference on Human-Robot Interaction (HRI) (pp. 412\u2013421). Sapporo, Japan: IEEE.","DOI":"10.1109\/HRI53351.2022.9889634"},{"key":"2336_CR50","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Li, J., Burgard, W., & Gaidon, A. (2021, September 30). Learning to track with object permanence. arXiv. http:\/\/arxiv.org\/abs\/2103.14258","DOI":"10.1109\/ICCV48922.2021.01068"},{"key":"2336_CR51","doi-asserted-by":"crossref","unstructured":"Vasquez, A., Kollmitz, M., Eitel, A., & Burgard, W. (2017). Deep Detection of People and their Mobility Aids for a Hospital Robot. In 2017 European conference on mobile robots (ECMR) (pp. 1\u20137). Paris: IEEE.","DOI":"10.1109\/ECMR.2017.8098665"},{"key":"2336_CR52","doi-asserted-by":"crossref","unstructured":"Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition (CVPR 2001) (Vol. 1, pp. I-511\u2013I-518). Kauai, HI: IEEE Comput. Soc.","DOI":"10.1109\/CVPR.2001.990517"},{"key":"2336_CR53","doi-asserted-by":"crossref","unstructured":"Vo, D. M., Jiang, L., & Zell, A. (2014). Real time person detection and tracking by mobile robots using RGB-D images. In 2014 IEEE international conference on robotics and biomimetics (ROBIO 2014) (pp. 689\u2013694). Bali, Indonesia: IEEE.","DOI":"10.1109\/ROBIO.2014.7090411"},{"key":"2336_CR54","doi-asserted-by":"crossref","unstructured":"Voigtlaender, P., Krause, M., Osep, A., Luiten, J., Sekar, B. B. G., Geiger, A., & Leibe, B. (2019). MOTS: Multi-object tracking and segmentation. In 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR) (pp. 7934\u20137943), Long Beach, CA, USA: IEEE.","DOI":"10.1109\/CVPR.2019.00813"},{"key":"2336_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Haitong, Tan, A. H., & Nejat, G. (2024, February 9). NavFormer: A transformer architecture for robot target-driven navigation in unknown and dynamic environments. arXiv http:\/\/arxiv.org\/abs\/2402.06838.","DOI":"10.1109\/LRA.2024.3412638"},{"issue":"12","key":"2336_CR56","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.1007\/s11263-018-1105-3","volume":"126","author":"H Wang","year":"2018","unstructured":"Wang, H., Zhu, X., Gong, S., & Xiang, T. (2018). Person re-identification in identity regression space. International Journal of Computer Vision, 126(12), 1288\u20131310.","journal-title":"International Journal of Computer Vision"},{"key":"2336_CR57","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-030-00308-1_13","volume-title":"RoboCup 2017: Robot World Cup XXI","author":"T Weber","year":"2018","unstructured":"Weber, T., Triputen, S., Danner, M., Braun, S., Schreve, K., & R\u00e4tsch, M. (2018). Follow me: Real-time in the wild person tracking application for autonomous robotics. In H. Akiyama, O. Obst, C. Sammut, & F. Tonidandel (Eds.), RoboCup 2017: Robot World Cup XXI (Vol. 11175, pp. 156\u2013167). Berlin: Springer."},{"key":"2336_CR58","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. In 2017 IEEE international conference on image processing (ICIP) (pp. 3645\u20133649).","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"2336_CR59","doi-asserted-by":"crossref","unstructured":"Wu, J., Cao, J., Song, L., Wang, Y., Yang, M., & Yuan, J. (2021). Track to detect and segment: An online multi-object tracker. In: Presented at the Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition  (pp. 12352\u201312361).","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"2336_CR60","unstructured":"Xu, Y., Ban, Y., Delorme, G., Gan, C., Rus, D., & Alameda-Pineda, X. (2022, September 30). TransCenter: Transformers with dense representations for multiple-object tracking. arXiv http:\/\/arxiv.org\/abs\/2103.15145."},{"issue":"3","key":"2336_CR61","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1007\/s11263-023-01925-4","volume":"132","author":"F Xue","year":"2024","unstructured":"Xue, F., Chang, Y., Wang, T., Zhou, Y., & Ming, A. (2024). Indoor obstacle discovery on reflective ground via monocular camera. International Journal of Computer Vision, 132(3), 987\u20131007.","journal-title":"International Journal of Computer Vision"},{"issue":"7","key":"2336_CR62","doi-asserted-by":"publisher","first-page":"1642","DOI":"10.1007\/s11263-023-01772-3","volume":"131","author":"Y Yan","year":"2023","unstructured":"Yan, Y., Li, J., Qin, J., Zheng, P., Liao, S., & Yang, X. (2023). Efficient person search: An anchor-free approach. International Journal of Computer Vision, 131(7), 1642\u20131661.","journal-title":"International Journal of Computer Vision"},{"key":"2336_CR63","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, W., Yang, Y., & Wang, Z. (2020). In defense of the triplet loss again: learning robust person re-identification with fast approximated triplet loss and label distillation. In 2020 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW) (pp. 1454\u20131463). Seattle, WA, USA: IEEE.","DOI":"10.1109\/CVPRW50498.2020.00185"},{"key":"2336_CR64","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-031-19812-0_38","volume-title":"Computer vision\u2014ECCV 2022","author":"F Zeng","year":"2022","unstructured":"Zeng, F., Dong, B., Zhang, Y., Wang, T., Zhang, X., & Wei, Y. (2022). MOTR: End-to-end multiple-object tracking with transformer. In S. Avidan, G. Brostow, M. Ciss\u00e9, G. M. Farinella, & T. Hassner (Eds.), Computer vision\u2014ECCV 2022 (Vol. 13687, pp. 659\u2013675). Cham: Springer."},{"key":"2336_CR65","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-030-58548-8_28","volume-title":"Computer vision\u2014ECCV 2020","author":"X Zhou","year":"2020","unstructured":"Zhou, X., Koltun, V., & Kr\u00e4henb\u00fchl, P. (2020). Tracking objects as points. In A. Vedaldi, H. Bischof, T. Brox, & J.-M. Frahm (Eds.), Computer vision\u2014ECCV 2020 (pp. 474\u2013490). Berlin: Springer."},{"key":"2336_CR66","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., & Dai, J. (2021, March 17). Deformable DETR: Deformable transformers for end-to-end object detection. arXiv. http:\/\/arxiv.org\/abs\/2010.04159."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02336-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02336-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02336-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T02:54:43Z","timestamp":1746845683000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02336-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,8]]},"references-count":66,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2336"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02336-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,8]]},"assertion":[{"value":"24 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We have no known conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}