{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:26:56Z","timestamp":1777656416011,"version":"3.51.4"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T00:00:00Z","timestamp":1692748800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T00:00:00Z","timestamp":1692748800000},"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":["U1803264"],"award-info":[{"award-number":["U1803264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072334"],"award-info":[{"award-number":["62072334"]}],"id":[{"id":"10.13039\/501100001809","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":[[2024,1]]},"DOI":"10.1007\/s11263-023-01857-z","type":"journal-article","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T03:21:57Z","timestamp":1692760917000},"page":"118-136","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Benchmarking the Complementary-View Multi-human Association and Tracking"],"prefix":"10.1007","volume":"132","author":[{"given":"Ruize","family":"Han","sequence":"first","affiliation":[]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Feifan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zekun","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Haomin","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Song","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,23]]},"reference":[{"key":"1857_CR1","doi-asserted-by":"crossref","unstructured":"Ardeshir, S., & Borji, A. (2016). Ego2top: Matching viewers in egocentric and top-view videos. In European conference on computer vision.","DOI":"10.1007\/978-3-319-46454-1_16"},{"issue":"6","key":"1857_CR2","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1109\/TPAMI.2018.2832121","volume":"41","author":"S Ardeshir","year":"2018","unstructured":"Ardeshir, S., & Borji, A. (2018). Egocentric meets top-view. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(6), 1353\u20131366.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1857_CR3","doi-asserted-by":"crossref","unstructured":"Ardeshir, S., & Borji, A. (2018b). Integrating egocentric videos in top-view surveillance videos: Joint identification and temporal alignment. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01252-6_18"},{"key":"1857_CR4","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L. (2019a). Tracking without bells and whistles. In IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00103"},{"key":"1857_CR5","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taix\u00e9, L. (2019b). Tracking without bells and whistles. In IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2019.00103"},{"key":"1857_CR6","doi-asserted-by":"crossref","unstructured":"Bernardin, K., & Stiefelhagen, R. (2008). Evaluating multiple object tracking performance. Journal on Image and Video Processing.","DOI":"10.1155\/2008\/246309"},{"key":"1857_CR7","unstructured":"Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J. (2011)."},{"key":"1857_CR8","doi-asserted-by":"crossref","unstructured":"Bras\u00f3, G., Leal-Taix\u00e9, L. (2020). Learning a neural solver for multiple object tracking. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"1857_CR9","unstructured":"Cai, J. F., Cand\u00e8s, E., Shen, Z. (2018). A singular value thresholding algorithm for matrix completio. SIAM Journal on Optimization."},{"key":"1857_CR10","doi-asserted-by":"crossref","unstructured":"Chu, Q., Ouyang, W., Li, H., Wang, X., Liu, B., Yu, N. (2017). Online multi-object tracking using cnn-based single object tracker with spatial-temporal attention mechanism. In IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.518"},{"key":"1857_CR11","doi-asserted-by":"crossref","unstructured":"Dehghan, A., Assari, S. M., Shah, M. (2015). GMMCP tracker: Globally optimal generalized maximum multi clique problem for multiple object tracking. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2015.7299036"},{"key":"1857_CR12","doi-asserted-by":"crossref","unstructured":"Dong, J., Jiang, W., Huang, Q., Bao, H., Zhou, X. (2019). Fast and robust multi-person 3d pose estimation from multiple views. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00798"},{"key":"1857_CR13","doi-asserted-by":"crossref","unstructured":"Dong, J., Fang, Q., Jiang, W., Yang, Y., Huang, Q., Bao, H., Zhou, X. (2021). Fast and robust multi-person 3d pose estimation and tracking from multiple views. IEEE transactions on pattern analysis and machine intelligence.","DOI":"10.1109\/TPAMI.2021.3098052"},{"issue":"10","key":"1857_CR14","doi-asserted-by":"publisher","first-page":"6981","DOI":"10.1109\/TPAMI.2021.3098052","volume":"44","author":"J Dong","year":"2022","unstructured":"Dong, J., Fang, Q., Jiang, W., Yang, Y., Huang, Q., Bao, H., & Zhou, X. (2022). Fast and robust multi-person 3d pose estimation and tracking from multiple views. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10), 6981\u20136992.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1857_CR15","doi-asserted-by":"crossref","unstructured":"Du, Y., Song, Y., Yang, B., Zhao, Y. (2022). Strongsort: Make deepsort great again. In arXiv","DOI":"10.1109\/TMM.2023.3240881"},{"key":"1857_CR16","doi-asserted-by":"crossref","unstructured":"Fabbri, M., Lanzi, F., Calderara, S., Palazzi, A., Vezzani, R., Cucchiara, R. (2018). Learning to detect and track visible and occluded body joints in a virtual world. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01225-0_27"},{"key":"1857_CR17","doi-asserted-by":"crossref","unstructured":"Fabbri, M., Bras\u00f3, G., Maugeri, G., Cetintas, O., Gasparini, R., Os\u0303ep, A., Calderara, S., Leal-Taix\u00e9, L., Cucchiara, R. (2021). Motsynth: How can synthetic data help pedestrian detection and tracking? In IEEE\/CVF international conference on computer vision.","DOI":"10.1109\/ICCV48922.2021.01067"},{"key":"1857_CR18","unstructured":"Ferryman, J. (2009). An overview of the pets2009 challenge. In Proceedings of international workshop on pets."},{"issue":"2","key":"1857_CR19","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1109\/TPAMI.2007.1174","volume":"30","author":"F Fleuret","year":"2008","unstructured":"Fleuret, F., Berclaz, J., Lengagne, R., & Fua, P. (2008). Multicamera people tracking with a probabilistic occupancy map. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(2), 267.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1857_CR20","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., Vig, E. (2016). Virtual worlds as proxy for multi-object tracking analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.470"},{"key":"1857_CR21","doi-asserted-by":"crossref","unstructured":"Gan, Y., Han, R., Yin, L., Feng, W., Wang, S. (2021). Self-supervised multi-view multi-human association and tracking. In ACM multimedia.","DOI":"10.1145\/3474085.3475177"},{"key":"1857_CR22","unstructured":"Gantmakher, F. R. (1959). The theory of matrices. American Mathematical Society."},{"key":"1857_CR23","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J. (2021). Yolox: Exceeding yolo series in 2021. In arXiv"},{"key":"1857_CR24","unstructured":"Han, R., Zhang, Y., Feng, W., Gong, C., Zhang, X., Zhao, J., Wan, L., Wang, S. (2019). Multiple human association between top and horizontal views by matching subjects\u2019 spatial distributions. In arXiv"},{"key":"1857_CR25","doi-asserted-by":"crossref","unstructured":"Han, R., Feng, W., Zhao, J., Niu, Z., Zhang, Y., Wan, L., Wang, S. (2020a). Complementary-view multiple human tracking. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v34i07.6724"},{"key":"1857_CR26","doi-asserted-by":"crossref","unstructured":"Han, R., Zhao, J., Feng, W., Gan, Y., Wan, L., Wang, S. (2020b). Complementary-view co-interest person detection. In ACM international conference on multimedia.","DOI":"10.1145\/3394171.3413659"},{"issue":"9","key":"1857_CR27","first-page":"5225","volume":"44","author":"R Han","year":"2022","unstructured":"Han, R., Feng, W., Zhang, Y., Zhao, J., & Wang, S. (2022). Multiple human association and tracking from egocentric and complementary top views. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 5225\u20135242.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1857_CR28","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1109\/TIP.2021.3139178","volume":"31","author":"R Han","year":"2022","unstructured":"Han, R., Wang, Y., Yan, H., Feng, W., & Wang, S. (2022). Multi-view multi-human association with deep assignment network. IEEE Transactions on Image Processing, 31, 1830\u20131840.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1857_CR29","unstructured":"He, L., Liao, X., Liu, W., Liu, X., Cheng, P., Mei, T. (2020). Fastreid: A pytorch toolbox for general instance re-identification. In arXiv."},{"key":"1857_CR30","doi-asserted-by":"crossref","unstructured":"Kuo, C.H, Huang, C., Nevatia, R. (2010). Inter-camera association of multi-target tracks by on-line learned appearance affinity models. In European conference on computer vision.","DOI":"10.1109\/CVPR.2010.5540148"},{"key":"1857_CR31","unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., Schindler, K. (2015). Motchallenge 2015: Towards a benchmark for multi-target tracking. In arXiv."},{"key":"1857_CR32","doi-asserted-by":"crossref","unstructured":"Lealtaixe, L., Cantonferrer, C., Schindler, K. (2016). Learning by tracking: Siamese CNN for robust target association. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPRW.2016.59"},{"key":"1857_CR33","doi-asserted-by":"crossref","unstructured":"Liang, G., Lan, X., Zheng, K., Wang, S., Zheng, N. (2018). Cross-view person identification by matching human poses estimated with confidence on each body joint. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.12236"},{"issue":"8","key":"1857_CR34","doi-asserted-by":"publisher","first-page":"3821","DOI":"10.1109\/TIP.2019.2899782","volume":"28","author":"G Liang","year":"2019","unstructured":"Liang, G., Lan, X., Chen, X., Zheng, K., Wang, S., & Zheng, N. (2019). Cross-view person identification based on confidence-weighted human pose matching. IEEE Transactions on Image Processing, 28(8), 3821\u20133835.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1857_CR35","doi-asserted-by":"crossref","unstructured":"Lin, Y., Ezzeldeen, K., Zhou, Y., Fan, X., Yu, H., Qian, H., Wang, S. (2015). Co-interest person detection from multiple wearable camera videos. In IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.503"},{"key":"1857_CR36","doi-asserted-by":"crossref","unstructured":"Luiten, J., Osep, A., Dendorfer, P., Torr, P., Leibe, B. (2020). HOTA: A higher order metric for evaluating multi-object tracking. International Journal of Computer Vision, pp. 1\u201331.","DOI":"10.1007\/s11263-020-01375-2"},{"key":"1857_CR37","doi-asserted-by":"crossref","unstructured":"Ma, F., Shou, M.Z., Zhu, L., Fan, H., Xu, Y., Yang, Y., Yan, Z. (2022). Unified transformer tracker for object tracking. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.00858"},{"key":"1857_CR38","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C. (2022). Trackformer: Multi-object tracking with transformers. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"1857_CR39","unstructured":"Ng, A. Y, Jordan, M. I., Weiss, Y. (2002). On spectral clustering: Analysis and an algorithm. In Conference on neural information processing systems."},{"key":"1857_CR40","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S. K., Girshick, R. B., Farhadi, A. (2016). You only look once: Unified, real-time object detection. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.91"},{"key":"1857_CR41","doi-asserted-by":"crossref","unstructured":"Ristani, E., Tomasi, C. (2018). Features for multi-target multi-camera tracking and re-identification. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2018.00632"},{"key":"1857_CR42","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R.S., Cucchiara, R., Tomasi, C. (2016). Performance measures and a data set for multi-target, multi-camera tracking. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"1857_CR43","doi-asserted-by":"crossref","unstructured":"Sun, X., Zheng, L. (2020). Dissecting person re-identification from the viewpoint of viewpoint. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2019.00070"},{"key":"1857_CR44","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. In IEEE international conference on image processing.","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"1857_CR45","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 IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR46437.2021.01217"},{"key":"1857_CR46","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Alahi, A., Savarese, S. (2015). Learning to track: Online multi-object tracking by decision making. In IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2015.534"},{"key":"1857_CR47","doi-asserted-by":"crossref","unstructured":"Xu, Y., Liu, X., Liu, Y., Zhu, S. (2016). Multi-view people tracking via hierarchical trajectory composition. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR.2016.461"},{"key":"1857_CR48","doi-asserted-by":"crossref","unstructured":"Xu, Y., Liu, X., Qin, L., Zhu, S. (2017). Cross-view people tracking by scene-centered spatio-temporal parsing. In AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v31i1.11190"},{"key":"1857_CR49","unstructured":"Yang, B., & Nevatia, R. (2012a). Multi-target tracking by online learning of non-linear motion patterns and robust appearance models. In IEEE conference on computer vision and pattern recognition."},{"key":"1857_CR50","unstructured":"Yang, B., & Nevatia, R. (2012b). An online learned crf model for multi-target tracking. In IEEE conference on computer vision and pattern recognition."},{"key":"1857_CR51","unstructured":"Zamir, A. R, Dehghan, A., Shah, M. (2012). Gmcp-tracker: Global multi-object tracking using generalized minimum clique graphs. In European conference on computer vision."},{"key":"1857_CR52","unstructured":"Zelnik-Manor, L., Perona, P. (2004). Self-tuning spectral clustering. In Conference on neural information processing systems."},{"key":"1857_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, S., Staudt, E., Faltemier, T., Roy-Chowdhury, A. K. (2015). A camera network tracking (CamNeT) dataset and performance baseline. In Winter conference on applications of computer vision.","DOI":"10.1109\/WACV.2015.55"},{"key":"1857_CR54","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., & Liu, W. (2021). Fairmot: On the fairness of detection and re-identification in multiple object tracking. International Journal of Computer Vision, 129, 3069\u20133087.","journal-title":"International Journal of Computer Vision"},{"key":"1857_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., Wang, X. (2022). Bytetrack: Multi-object tracking by associating every detection box. In European conference on computer vision.","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"1857_CR56","doi-asserted-by":"crossref","unstructured":"Zhao, J., Han, R., Gan, Y., Wan, L., Feng, W., Wang, S. (2020). Human identification and interaction detection in cross-view multi-person videos with wearable cameras. In ACM international conference on multimedia.","DOI":"10.1145\/3394171.3413903"},{"key":"1857_CR57","unstructured":"Zheng, K., Lin, Y., Zhou, Y., Salvi, D., Fan, X., Guo, D., Meng, Z., Wang, S. (2014). Video-based action detection using multiple wearable cameras. In European conference on computer vision workshop."},{"key":"1857_CR58","doi-asserted-by":"crossref","unstructured":"Zheng, K., Fan, X., Lin, Y., Guo, H., Wang, S. (2017). Learning view-invariant features for person identification in temporally synchronized videos taken by wearable cameras. In IEEE international conference on computer vision.","DOI":"10.1109\/ICCV.2017.311"},{"key":"1857_CR59","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P. (2020). Tracking objects as points. In European conference on computer vision.","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"1857_CR60","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yin, T., Koltun, V., Kr\u00e4henb\u00fchl, P. (2022). Global tracking transformers. In IEEE conference on computer vision and pattern recognition.","DOI":"10.1109\/CVPR52688.2022.00857"},{"key":"1857_CR61","doi-asserted-by":"crossref","unstructured":"Zhu, J., Yang, H., Liu, N., Kim, M., Zhang, W., Yang, M. (2018). Online multi-object tracking with dual matching attention networks. In European conference on computer vision.","DOI":"10.1007\/978-3-030-01228-1_23"},{"key":"1857_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, P., Wen, L., Du, D., Bian, X., Fan, H., Hu, Q., & Ling, H. (2022). Detection and tracking meet drones challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11), 7380\u20137399.","DOI":"10.1109\/TPAMI.2021.3119563"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01857-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01857-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01857-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T03:09:47Z","timestamp":1705892987000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01857-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,23]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["1857"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01857-z","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,23]]},"assertion":[{"value":"3 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}