{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:56:58Z","timestamp":1790269018003,"version":"4.1.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s00530-024-01420-x","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T06:01:40Z","timestamp":1722232900000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Coordinate-aligned multi-camera collaboration for active multi-object tracking"],"prefix":"10.1007","volume":"30","author":[{"given":"Zeyu","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenbo","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,29]]},"reference":[{"key":"1420_CR1","unstructured":"Luo, W., Sun, P., Zhong, F., Liu, W., Zhang, T., Wang, Y.: End-to-end active object tracking via reinforcement learning. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 3286\u20133295. PMLR (2018)"},{"key":"1420_CR2","unstructured":"Zhong, F., Sun, P., Luo, W., Yan, T., Wang, Y.: AD-VAT: an asymmetric dueling mechanism for learning visual active tracking. In: Proceedings of the International Conference on Learning Representations (ICLR) (2018)"},{"key":"1420_CR3","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, J., Zhong, F., Kong, X., Qiao, Y., Wang, Y.: Pose-assisted multi-camera collaboration for active object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 34, pp. 759\u2013766 (2020)","DOI":"10.1609\/aaai.v34i01.5419"},{"key":"1420_CR4","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Scaled-YOLOv4: scaling cross stage partial network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13029\u201313038 (2021)","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"1420_CR5","doi-asserted-by":"publisher","unstructured":"Sturm, P.F., Maybank, S.J.: On plane-based camera calibration: a general algorithm, singularities, applications. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 432\u20134371 (1999). https:\/\/doi.org\/10.1109\/CVPR.1999.786974","DOI":"10.1109\/CVPR.1999.786974"},{"key":"1420_CR6","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"1420_CR7","doi-asserted-by":"crossref","unstructured":"Qiu, W., Zhong, F., Zhang, Y., Qiao, S., Xiao, Z., Kim, T.S., Wang, Y., Yuille, A.: UnrealCV: virtual worlds for computer vision. In: ACM Multimedia Open Source Software Competition (2017)","DOI":"10.1145\/3123266.3129396"},{"key":"1420_CR8","first-page":"10053","volume":"33","author":"J Xu","year":"2020","unstructured":"Xu, J., Zhong, F., Wang, Y.: Learning multi-agent coordination for enhancing target coverage in directional sensor networks. Adv. Neural Inf. Process. Syst. (NEURIPS) 33, 10053\u201310064 (2020)","journal-title":"Adv. Neural Inf. Process. Syst. (NEURIPS)"},{"key":"1420_CR9","doi-asserted-by":"crossref","unstructured":"Denzler, J., Paulus, D.W.: Active motion detection and object tracking. In: Proceedings of the IEEE International Conference on Image Processing (ICIP), vol. 3, pp. 635\u2013639 (1994)","DOI":"10.1109\/ICIP.1994.413812"},{"key":"1420_CR10","doi-asserted-by":"publisher","unstructured":"Kim, K.K., Cho, S.H., Kim, H.J., Lee, J.Y.: Detecting and tracking moving object using an active camera. In: Proceedings of the International Conference on Advanced Communication Technology (ICACT), vol. 2, pp. 817\u2013820 (2005). https:\/\/doi.org\/10.1109\/ICACT.2005.246077","DOI":"10.1109\/ICACT.2005.246077"},{"key":"1420_CR11","doi-asserted-by":"publisher","unstructured":"Comaniciu, D., Ramesh, V.: Robust detection and tracking of human faces with an active camera. In: Proceedings of the IEEE International Workshop on Visual Surveillance (VS), pp. 11\u201318 (2000). https:\/\/doi.org\/10.1109\/VS.2000.856853","DOI":"10.1109\/VS.2000.856853"},{"issue":"2","key":"1420_CR12","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/s00530-024-01304-0","volume":"30","author":"C Liu","year":"2024","unstructured":"Liu, C., Li, H., Wang, Z., Xu, R.: Reconciling global and local optimal label assignments for heavily occluded pedestrian detection. Multimedia Syst. 30(2), 100 (2024)","journal-title":"Multimedia Syst."},{"key":"1420_CR13","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv Preprint arXiv:2004.10934 (2020)"},{"key":"1420_CR14","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.: Deep learning for generic object detection: a survey. Int. J. Comput. Vis. 128, 261\u2013318 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"1420_CR15","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.patcog.2017.11.007","volume":"76","author":"P Li","year":"2018","unstructured":"Li, P., Wang, D., Wang, L., Lu, H.: Deep visual tracking: review and experimental comparison. Pattern Recognit. 76, 323\u2013338 (2018)","journal-title":"Pattern Recognit."},{"issue":"3","key":"1420_CR16","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1007\/s00530-022-00895-w","volume":"28","author":"W Guo","year":"2022","unstructured":"Guo, W., Jin, Y., Shan, B., Ding, X., Wang, M.: Multi-cue multi-hypothesis tracking with re-identification for multi-object tracking. Multimedia Syst. 28(3), 925\u2013937 (2022)","journal-title":"Multimedia Syst."},{"issue":"5","key":"1420_CR17","doi-asserted-by":"publisher","first-page":"1543","DOI":"10.1007\/s00530-021-00845-y","volume":"28","author":"R Wu","year":"2022","unstructured":"Wu, R., Wen, X., Liu, Z., Yuan, L., Xu, H.: STASiamRPN: visual tracking based on spatiotemporal and attention. Multimedia Syst. 28(5), 1543\u20131555 (2022)","journal-title":"Multimedia Syst."},{"key":"1420_CR18","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4293\u20134302 (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"1420_CR19","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\u201310 and 15-16, Proceedings, Part II 14, pp. 850\u2013865. Springer (2016)","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"1420_CR20","doi-asserted-by":"publisher","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8971\u20138980 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00935","DOI":"10.1109\/CVPR.2018.00935"},{"key":"1420_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3053971","volume":"70","author":"M Jiang","year":"2021","unstructured":"Jiang, M., Sogabe, R., Shimasaki, K., Hu, S., Senoo, T., Ishii, I.: 500-fps omnidirectional visual tracking using three-axis active vision system. IEEE Trans. Instrum. Meas. 70, 1\u201311 (2021). https:\/\/doi.org\/10.1109\/TIM.2021.3053971","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"1420_CR22","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv Preprint arXiv:1312.5602 (2013)"},{"issue":"7540","key":"1420_CR23","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"1420_CR24","doi-asserted-by":"crossref","unstructured":"Hessel, M., Modayil, J., Van\u00a0Hasselt, H., Schaul, T., Ostrovski, G., Dabney, W., Horgan, D., Piot, B., Azar, M., Silver, D.: Rainbow: combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"1420_CR25","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 4295\u20134304. PMLR (2018)"},{"key":"1420_CR26","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-030-60990-0_12","volume-title":"Handbook of Reinforcement Learning and Control","author":"K Zhang","year":"2021","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. In: Handbook of Reinforcement Learning and Control, pp. 321\u2013384. Springer, Cham (2021)"},{"key":"1420_CR27","unstructured":"Wu, Y., Tian, Y.: Training agent for first-person shooter game with actor-critic curriculum learning. In: Proceedings of the International Conference on Learning Representations (ICLR) (2017)"},{"key":"1420_CR28","doi-asserted-by":"crossref","unstructured":"Pan, X., You, Y., Wang, Z., Lu, C.: Virtual to real reinforcement learning for autonomous driving. In: Proceedings of the British Machine Vision Conference (BMVC) (2017)","DOI":"10.5244\/C.31.11"},{"key":"1420_CR29","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Mottaghi, R., Kolve, E., Lim, J.J., Gupta, A., Li, F.-F., Farhadi, A.: Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 3357\u20133364 (2017)","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"1420_CR30","doi-asserted-by":"crossref","unstructured":"Hong, Z.-W., Chen, Y.-M., Su, S.-Y., Shann, T.-Y., Chang, Y.-H., Yang, H.-K., Ho, B.H.-L., Tu, C.-C., Chang, Y.-C., Hsiao, T.-C., et al.: Virtual-to-real: learning to control in visual semantic segmentation. arXiv Preprint arXiv:1802.00285 (2018)","DOI":"10.24963\/ijcai.2018\/682"},{"key":"1420_CR31","doi-asserted-by":"crossref","unstructured":"Fang, Z., Zhao, J., Zhou, W., Li, H.: Implementing first-person shooter game AI in WILD-SCAV with rule-enhanced deep reinforcement learning. In: IEEE Conference on Games (CoG), pp. 1\u20138. IEEE (2023)","DOI":"10.1109\/CoG57401.2023.10333171"},{"key":"1420_CR32","unstructured":"Mnih, V., Badia, A.P., Mirza, M., Graves, A., Lillicrap, T., Harley, T., Silver, D., Kavukcuoglu, K.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the international conference on machine learning (ICML), pp. 1928\u20131937. PMLR (2016)"},{"key":"1420_CR33","doi-asserted-by":"crossref","unstructured":"Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Jaskowski, W.: ViZDoom: a doom-based AI research platform for visual reinforcement learning. In: IEEE Conference on Computational Intelligence and Games (CIG), pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/CIG.2016.7860433"},{"issue":"5","key":"1420_CR34","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1109\/TPAMI.2019.2952590","volume":"43","author":"F Zhong","year":"2021","unstructured":"Zhong, F., Sun, P., Luo, W., Yan, T., Wang, Y.: AD-VAT+: an asymmetric dueling mechanism for learning and understanding visual active tracking. IEEE Trans. Pattern Anal. Mach. Intell. 43(5), 1467\u20131482 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2019.2952590","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1420_CR35","unstructured":"Zhong, F., Sun, P., Luo, W., Yan, T., Wang, Y.: Towards distraction-robust active visual tracking. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 12782\u201312792. PMLR (2021)"},{"key":"1420_CR36","doi-asserted-by":"publisher","unstructured":"Xi, M., Zhou, Y., Chen, Z., Zhou, W., Li, H.: Anti-distractor active object tracking in 3D environments. IEEE Trans. Circuits Syst. Video Technol. https:\/\/doi.org\/10.1109\/TCSVT2021.3107153","DOI":"10.1109\/TCSVT2021.3107153"},{"key":"1420_CR37","doi-asserted-by":"crossref","unstructured":"Zhong, F., Bi, X., Zhang, Y., Zhang, W., Wang, Y.: RSPT: reconstruct surroundings and predict trajectory for generalizable active object tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 3705\u20133714 (2023)","DOI":"10.1609\/aaai.v37i3.25482"},{"key":"1420_CR38","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10878-006-5975-x","volume":"11","author":"J Ai","year":"2006","unstructured":"Ai, J., Abouzeid, A.A.: Coverage by directional sensors in randomly deployed wireless sensor networks. J. Combin. Optim. 11, 21\u201341 (2006)","journal-title":"J. Combin. Optim."},{"key":"1420_CR39","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1109\/FGCN.2007.94","volume":"1","author":"Y Cai","year":"2007","unstructured":"Cai, Y., Lou, W., Li, M.: Cover set problem in directional sensor networks. Future Gener. Commun. Netw. (FGCN) 1, 274\u2013278 (2007). https:\/\/doi.org\/10.1109\/FGCN.2007.94","journal-title":"Future Gener. Commun. Netw. (FGCN)"},{"issue":"11\u201312","key":"1420_CR40","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1016\/j.camwa.2008.10.019","volume":"57","author":"J Wang","year":"2009","unstructured":"Wang, J., Niu, C., Shen, R.: Priority-based target coverage in directional sensor networks using a genetic algorithm. Comput. Math. Appl. 57(11\u201312), 1915\u20131922 (2009)","journal-title":"Comput. Math. Appl."},{"key":"1420_CR41","doi-asserted-by":"crossref","unstructured":"Chen, U.-R., Chiou, B.-S., Chen, J.-M., Lin, W.: An adjustable target coverage method in directional sensor networks. In: IEEE Asia-Pacific Services Computing Conference, pp. 174\u2013180. IEEE (2008)","DOI":"10.1109\/APSCC.2008.37"},{"key":"1420_CR42","unstructured":"Wang, Y., Zhong, F., Xu, J., Wang, Y.: ToM2C: target-oriented multi-agent communication and cooperation with theory of mind. arXiv preprint arXiv:2111.09189 (2021)"},{"issue":"4","key":"1420_CR43","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Math. Oper. Res. 27(4), 819\u2013840 (2002)","journal-title":"Math. Oper. Res."},{"issue":"11","key":"1420_CR44","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/34.888718","volume":"22","author":"Z Zhang","year":"2000","unstructured":"Zhang, Z.: A flexible new technique for camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1330\u20131334 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1420_CR45","first-page":"2613","volume":"23","author":"H Hasselt","year":"2010","unstructured":"Hasselt, H.: Double q-learning. Adv. Neural Inf. Process. Syst. 23, 2613\u20132621 (2010)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"1420_CR46","unstructured":"Zhong, F., Qiu, W., Yan, T., Yuille, A., Wang, Y.: Gym-UnrealCV: realistic virtual worlds for visual reinforcement learning. Web Page (2017). https:\/\/github.com\/unrealcv\/gym-unrealcv"},{"key":"1420_CR47","unstructured":"Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: OpenAI gym. arXiv Preprint arXiv:1606.01540 (2016)"},{"key":"1420_CR48","doi-asserted-by":"crossref","unstructured":"Scott, A., Uchida, I., Onishi, M., Kameda, Y., Fukui, K., Fujii, K.: SoccerTrack: a dataset and tracking algorithm for soccer with fish-eye and drone videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3569\u20133579 (2022)","DOI":"10.1109\/CVPRW56347.2022.00401"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01420-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01420-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01420-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T08:35:00Z","timestamp":1724315700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01420-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,29]]},"references-count":48,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1420"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01420-x","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,29]]},"assertion":[{"value":"27 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"221"}}