{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T06:13:24Z","timestamp":1744179204569,"version":"3.40.3"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030695316"},{"type":"electronic","value":"9783030695323"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-69532-3_33","type":"book-chapter","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T08:04:33Z","timestamp":1614326673000},"page":"539-557","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A Two-Stage Minimum Cost Multicut Approach to Self-supervised Multiple Person Tracking"],"prefix":"10.1007","author":[{"given":"Kalun","family":"Ho","sequence":"first","affiliation":[]},{"given":"Amirhossein","family":"Kardoost","sequence":"additional","affiliation":[]},{"given":"Franz-Josef","family":"Pfreundt","sequence":"additional","affiliation":[]},{"given":"Janis","family":"Keuper","sequence":"additional","affiliation":[]},{"given":"Margret","family":"Keuper","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"33_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-642-33709-3_25","volume-title":"Computer Vision \u2013 ECCV 2012","author":"A Roshan Zamir","year":"2012","unstructured":"Roshan Zamir, A., Dehghan, A., Shah, M.: GMCP-tracker: global multi-object tracking using generalized minimum clique graphs. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7573, pp. 343\u2013356. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33709-3_25"},{"unstructured":"Henschel, R., Leal-Taix\u00e9, L., Cremers, D., Rosenhahn, B.: Improvements to Frank-wolfe optimization for multi-detector multi-object tracking. arXiv preprint arXiv:1705.08314 (2017)","key":"33_CR2"},{"key":"33_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-319-48881-3_8","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"S Tang","year":"2016","unstructured":"Tang, S., Andres, B., Andriluka, M., Schiele, B.: Multi-person tracking by multicut and deep matching. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9914, pp. 100\u2013111. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-48881-3_8"},{"doi-asserted-by":"crossref","unstructured":"Tang, S., Andriluka, M., Andres, B., Schiele, B.: Multiple people tracking by lifted multicut and person reidentification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3539\u20133548 (2017)","key":"33_CR4","DOI":"10.1109\/CVPR.2017.394"},{"unstructured":"Luo, W., et al.: Multiple object tracking: a literature review. arXiv preprint arXiv:1409.7618 (2014)","key":"33_CR5"},{"unstructured":"Milan, A., Leal-Taix\u00e9, L., Reid, I., Roth, S., Schindler, K.: MOT16: a benchmark for multi-object tracking. arXiv:1603.00831 [cs] (2016) arXiv: 1603.00831","key":"33_CR6"},{"doi-asserted-by":"crossref","unstructured":"Yoon, Y.C., Boragule, A., Song, Y.M., Yoon, K., Jeon, M.: Online multi-object tracking with historical appearance matching and scene adaptive detection filtering. In: 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE (2018)","key":"33_CR7","DOI":"10.1109\/AVSS.2018.8639078"},{"unstructured":"Feng, W., Hu, Z., Wu, W., Yan, J., Ouyang, W.: Multi-object tracking with multiple cues and switcher-aware classification. arXiv preprint arXiv:1901.06129 (2019)","key":"33_CR8"},{"doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Zhai, X., Beyer, L.: Revisiting self-supervised visual representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1920\u20131929 (2019)","key":"33_CR9","DOI":"10.1109\/CVPR.2019.00202"},{"doi-asserted-by":"crossref","unstructured":"Pathak, D., Girshick, R., Doll\u00e1r, P., Darrell, T., Hariharan, B.: Learning features by watching objects move. In: CVPR (2017)","key":"33_CR10","DOI":"10.1109\/CVPR.2017.638"},{"key":"33_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-030-20873-8_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"A Mahendran","year":"2019","unstructured":"Mahendran, A., Thewlis, J., Vedaldi, A.: Cross pixel optical-flow similarity for self-supervised learning. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11365, pp. 99\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20873-8_7"},{"unstructured":"Hendrycks, D., Mazeika, M., Kadavath, S., Song, D.: Using self-supervised learning can improve model robustness and uncertainty. In: Advances in Neural Information Processing Systems, pp. 15637\u201315648 (2019)","key":"33_CR12"},{"doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: Self-learning scene-specific pedestrian detectors using a progressive latent model, pp. 2057\u20132066 (2017)","key":"33_CR13","DOI":"10.1109\/CVPR.2017.222"},{"doi-asserted-by":"crossref","unstructured":"Lee, W., Na, J., Kim, G.: Multi-task self-supervised object detection via recycling of bounding box annotations. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","key":"33_CR14","DOI":"10.1109\/CVPR.2019.00512"},{"doi-asserted-by":"crossref","unstructured":"Vondrick, C.M., Shrivastava, A., Fathi, A., Guadarrama, S., Murphy, K.: Tracking emerges by colorizing videos (2018)","key":"33_CR15","DOI":"10.1007\/978-3-030-01261-8_24"},{"doi-asserted-by":"crossref","unstructured":"Leal-Taix\u00e9, L., Canton-Ferrer, C., Schindler, K.: Learning by tracking: siamese CNN for robust target association. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 33\u201340 (2016)","key":"33_CR16","DOI":"10.1109\/CVPRW.2016.59"},{"doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Ramanan, D., Fowlkes, C.C.: Globally-optimal greedy algorithms for tracking a variable number of objects. In: CVPR (2011)","key":"33_CR17","DOI":"10.1109\/CVPR.2011.5995604"},{"doi-asserted-by":"crossref","unstructured":"Andriyenko, A., Schindler, K., Roth, S.: Discrete-continuous optimization for multi-target tracking. In: CVPR (2012)","key":"33_CR18","DOI":"10.1109\/CVPR.2012.6247893"},{"key":"33_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1007\/978-3-540-88688-4_58","volume-title":"Computer Vision \u2013 ECCV 2008","author":"C Huang","year":"2008","unstructured":"Huang, C., Wu, B., Nevatia, R.: Robust object tracking by hierarchical association of detection responses. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5303, pp. 788\u2013801. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88688-4_58"},{"doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., Schiele, B.: Monocular 3d pose estimation and tracking by detection. In: CVPR (2010)","key":"33_CR20","DOI":"10.1109\/CVPR.2010.5540156"},{"key":"33_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1007\/978-3-642-33715-4_40","volume-title":"Computer Vision \u2013 ECCV 2012","author":"K Fragkiadaki","year":"2012","unstructured":"Fragkiadaki, K., Zhang, W., Zhang, G., Shi, J.: Two-granularity tracking: mediating trajectory and detection graphs for tracking under occlusions. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 552\u2013565. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_40"},{"doi-asserted-by":"crossref","unstructured":"Henschel, R., Leal-Taixe, L., Rosenhahn, B.: Efficient multiple people tracking using minimum cost arborescences. In: GCPR (2014)","key":"33_CR22","DOI":"10.1007\/978-3-319-11752-2_21"},{"key":"33_CR23","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s11263-013-0664-6","volume":"110","author":"S Tang","year":"2014","unstructured":"Tang, S., Andriluka, M., Schiele, B.: Detection and tracking of occluded people. IJCV 110, 58\u201369 (2014)","journal-title":"IJCV"},{"unstructured":"Henschel, R., Leal-Taix\u00e9, L., Cremers, D., Rosenhahn, B.: Improvements to Frank-Wolfe optimization for multi-detector multi-object tracking. CoRR abs\/1705.08314 (2017)","key":"33_CR24"},{"unstructured":"Shitrit, H.B., Berclaz, J., Fleuret, F., Fua, P.: Tracking multiple people under global appearance constraints. In: ICCV (2011)","key":"33_CR25"},{"key":"33_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-319-10590-1_2","volume-title":"Computer Vision \u2013 ECCV 2014","author":"X Wang","year":"2014","unstructured":"Wang, X., T\u00fcretken, E., Fleuret, F., Fua, P.: Tracking interacting objects optimally using integer programming. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 17\u201332. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_2"},{"key":"33_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-16817-3_29","volume-title":"Computer Vision \u2013 ACCV 2014","author":"R Kumar","year":"2015","unstructured":"Kumar, R., Charpiat, G., Thonnat, M.: Multiple object tracking by efficient graph partitioning. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 445\u2013460. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16817-3_29"},{"key":"33_CR28","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1049\/iet-cvi.2015.0297","volume":"10","author":"YT Tesfaye","year":"2016","unstructured":"Tesfaye, Y.T., Zemene, E., Pelillo, M., Prati, A.: Multi-object tracking using dominant sets. IET Comput. Vis. 10, 289\u2013297 (2016)","journal-title":"IET Comput. Vis."},{"key":"33_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-642-15561-1_34","volume-title":"Computer Vision \u2013 ECCV 2010","author":"C Wojek","year":"2010","unstructured":"Wojek, C., Roth, S., Schindler, K., Schiele, B.: Monocular 3D scene modeling and inference: understanding multi-object traffic scenes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 467\u2013481. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_34"},{"key":"33_CR30","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1109\/TPAMI.2012.174","volume":"35","author":"C Wojek","year":"2013","unstructured":"Wojek, C., Walk, S., Roth, S., Schindler, K., Schiele, B.: Monocular visual scene understanding: understanding multi-object traffic scenes. IEEE TPAMI 35, 882\u2013897 (2013)","journal-title":"IEEE TPAMI"},{"doi-asserted-by":"crossref","unstructured":"Chari, V., Lacoste-Julien, S., Laptev, I., Sivic, J.: On pairwise costs for network flow multi-object tracking. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5537\u20135545 (2015)","key":"33_CR31","DOI":"10.1109\/CVPR.2015.7299193"},{"doi-asserted-by":"crossref","unstructured":"Hornakova, A., Henschel, R., Rosenhahn, B., Swoboda, P.: Lifted disjoint paths with application in multiple object tracking. arXiv preprint arXiv:2006.14550 (2020)","key":"33_CR32","DOI":"10.51202\/9783186875105-130"},{"doi-asserted-by":"crossref","unstructured":"Bras\u00f3, G., Leal-Taix\u00e9, L.: Learning a neural solver for multiple object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6247\u20136257 (2020)","key":"33_CR33","DOI":"10.1109\/CVPR42600.2020.00628"},{"key":"33_CR34","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1109\/TPAMI.2018.2876253","volume":"42","author":"M Keuper","year":"2018","unstructured":"Keuper, M., Tang, S., Andres, B., Brox, T., Schiele, B.: Motion segmentation & multiple object tracking by correlation co-clustering. IEEE Trans. Pattern Anal. Mach. Intell. 42, 140\u2013153 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Henschel, R., Leal-Taix\u00e9, L., Cremers, D., Rosenhahn, B.: Fusion of head and full-body detectors for multi-object tracking. In: Computer Vision and Pattern Recognition Workshops (CVPRW) (2018)","key":"33_CR35","DOI":"10.1109\/CVPRW.2018.00192"},{"doi-asserted-by":"crossref","unstructured":"Henschel, R., Zou, Y., Rosenhahn, B.: Multiple people tracking using body and joint detections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019)","key":"33_CR36","DOI":"10.1109\/CVPRW.2019.00105"},{"doi-asserted-by":"crossref","unstructured":"Keuper, M., Levinkov, E., Bonneel, N., Lavou\u00e9, G., Brox, T., Andres, B.: Efficient decomposition of image and mesh graphs by lifted multicuts. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1751\u20131759 (2015)","key":"33_CR37","DOI":"10.1109\/ICCV.2015.204"},{"unstructured":"Keuper, M., Tang, S., Zhongjie, Y., Andres, B., Brox, T., Schiele, B.: A multi-cut formulation for joint segmentation and tracking of multiple objects. arXiv preprint arXiv:1607.06317 (2016)","key":"33_CR38"},{"key":"33_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-16817-3_29","volume-title":"Computer Vision \u2013 ACCV 2014","author":"R Kumar","year":"2015","unstructured":"Kumar, R., Charpiat, G., Thonnat, M.: Multiple object tracking by efficient graph partitioning. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 445\u2013460. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16817-3_29"},{"doi-asserted-by":"crossref","unstructured":"Ma, C., et al.: Trajectory factory: tracklet cleaving and re-connection by deep siamese bi-GRU for multiple object tracking. arXiv preprint arXiv:1804.04555 (2018)","key":"33_CR40","DOI":"10.1109\/ICME.2018.8486454"},{"doi-asserted-by":"crossref","unstructured":"Bergmann, P., Meinhardt, T., Leal-Taixe, L.: Tracking without bells and whistles. arXiv preprint arXiv:1903.05625 (2019)","key":"33_CR41","DOI":"10.1109\/ICCV.2019.00103"},{"doi-asserted-by":"crossref","unstructured":"Kim, C., Li, F., Ciptadi, A., Rehg, J.M.: Multiple hypothesis tracking revisited. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4696\u20134704 (2015)","key":"33_CR42","DOI":"10.1109\/ICCV.2015.533"},{"key":"33_CR43","doi-asserted-by":"publisher","first-page":"3660","DOI":"10.1109\/TCSVT.2018.2881123","volume":"29","author":"H Sheng","year":"2018","unstructured":"Sheng, H., Chen, J., Zhang, Y., Ke, W., Xiong, Z., Yu, J.: Iterative multiple hypothesis tracking with tracklet-level association. IEEE Trans. Circuits Syst. Video Technol. 29, 3660\u20133672 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"doi-asserted-by":"crossref","unstructured":"Chen, J., Sheng, H., Zhang, Y., Xiong, Z.: Enhancing detection model for multiple hypothesis tracking. In: Conference on Computer Vision and Pattern Recognition Workshops, pp. 2143\u20132152 (2017)","key":"33_CR44","DOI":"10.1109\/CVPRW.2017.266"},{"key":"33_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1007\/978-3-030-01225-0_45","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Li","year":"2018","unstructured":"Li, M., Zhu, X., Gong, S.: Unsupervised person re-identification by deep learning tracklet association. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 772\u2013788. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_45"},{"doi-asserted-by":"crossref","unstructured":"Lv, J., Chen, W., Li, Q., Yang, C.: Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7948\u20137956 (2018)","key":"33_CR46","DOI":"10.1109\/CVPR.2018.00829"},{"unstructured":"Karthik, S., Prabhu, A., Gandhi, V.: Simple unsupervised multi-object tracking. arXiv preprint arXiv:2006.02609 (2020)","key":"33_CR47"},{"doi-asserted-by":"crossref","unstructured":"Jing, L., Tian, Y.: Self-supervised visual feature learning with deep neural networks: a survey. arXiv preprint arXiv:1902.06162 (2019)","key":"33_CR48","DOI":"10.1109\/TPAMI.2020.2992393"},{"doi-asserted-by":"crossref","unstructured":"Pathak, D., Girshick, R., Doll\u00e1r, P., Darrell, T., Hariharan, B.: Learning features by watching objects move. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2701\u20132710 (2017)","key":"33_CR49","DOI":"10.1109\/CVPR.2017.638"},{"doi-asserted-by":"crossref","unstructured":"Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1422\u20131430 (2015)","key":"33_CR50","DOI":"10.1109\/ICCV.2015.167"},{"doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: Feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","key":"33_CR51","DOI":"10.1109\/CVPR.2016.278"},{"doi-asserted-by":"crossref","unstructured":"Lee, W., Na, J., Kim, G.: Multi-task self-supervised object detection via recycling of bounding box annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4984\u20134993 (2019)","key":"33_CR52","DOI":"10.1109\/CVPR.2019.00512"},{"doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: Self-learning scene-specific pedestrian detectors using a progressive latent model. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 509\u2013518 (2017)","key":"33_CR53","DOI":"10.1109\/CVPR.2017.222"},{"key":"33_CR54","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.tcs.2006.05.008","volume":"361","author":"ED Demaine","year":"2006","unstructured":"Demaine, E.D., Emanuel, D., Fiat, A., Immorlica, N.: Correlation clustering in general weighted graphs. Theoret. Comput. Sci. 361, 172\u2013187 (2006)","journal-title":"Theoret. Comput. Sci."},{"doi-asserted-by":"crossref","unstructured":"Keuper, M., Levinkov, E., Bonneel, N., Lavoue, G., Brox, T., Andres, B.: Efficient decomposition of image and mesh graphs by lifted multicuts. In: ICCV (2015)","key":"33_CR55","DOI":"10.1109\/ICCV.2015.204"},{"key":"33_CR56","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/BF01581239","volume":"59","author":"S Chopra","year":"1993","unstructured":"Chopra, S., Rao, M.: The partition problem. Math. Program. 59, 87\u2013115 (1993)","journal-title":"Math. Program."},{"key":"33_CR57","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1023\/B:MACH.0000033116.57574.95","volume":"56","author":"N Bansal","year":"2004","unstructured":"Bansal, N., Blum, A., Chawla, S.: Correlation clustering. Mach. Learn. 56, 89\u2013113 (2004)","journal-title":"Mach. Learn."},{"unstructured":"Hor\u0148\u00e1kov\u00e1, A., Lange, J.H., Andres, B.: Analysis and optimization of graph decompositions by lifted multicuts. In: ICML (2017)","key":"33_CR58"},{"key":"33_CR59","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1007\/978-3-642-33712-3_56","volume-title":"Computer Vision \u2013 ECCV 2012","author":"B Andres","year":"2012","unstructured":"Andres, B., et al.: Globally optimal closed-surface segmentation for connectomics. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 778\u2013791. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_56"},{"doi-asserted-by":"crossref","unstructured":"Beier, T., Kroeger, T., Kappes, J., Kothe, U., Hamprecht, F.: Cut, glue, & cut: a fast, approximate solver for multicut partitioning. In: CVPR (2014)","key":"33_CR60","DOI":"10.1109\/CVPR.2014.17"},{"key":"33_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"doi-asserted-by":"crossref","unstructured":"Kardoost, A., Keuper, M.: Solving minimum cost lifted multicut problems by node agglomeration. In: ACCV 2018, 14th Asian Conference on Computer Vision, Perth, Australia (2018)","key":"33_CR62","DOI":"10.1007\/978-3-030-20870-7_5"},{"unstructured":"Revaud, J., Weinzaepfel, P., Harchaoui, Z., Schmid, C.: Deep convolutional matching. CoRR abs\/1506.07656 (2015)","key":"33_CR63"},{"unstructured":"Yang, B., Fu, X., Sidiropoulos, N.D., Hong, M.: Towards k-means-friendly spaces: simultaneous deep learning and clustering. arXiv preprint arXiv:1610.04794 (2016)","key":"33_CR64"},{"unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)","key":"33_CR65"},{"unstructured":"Maaten, L.v.d., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","key":"33_CR66"},{"doi-asserted-by":"crossref","unstructured":"Yang, F., Choi, W., Lin, Y.: Exploit all the layers: fast and accurate CNN object detector with scale dependent pooling and cascaded rejection classifiers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2129\u20132137 (2016)","key":"33_CR67","DOI":"10.1109\/CVPR.2016.234"},{"key":"33_CR68","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)","key":"33_CR69"},{"unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., Schindler, K.: Motchallenge 2015: towards a benchmark for multi-target tracking. arXiv:1504.01942 (2015)","key":"33_CR70"},{"key":"33_CR71","doi-asserted-by":"publisher","first-page":"3269","DOI":"10.1109\/TCSVT.2018.2882192","volume":"29","author":"H Sheng","year":"2018","unstructured":"Sheng, H., Zhang, Y., Chen, J., Xiong, Z., Zhang, J.: Heterogeneous association graph fusion for target association in multiple object tracking. IEEE Trans. Circuits Syst. Video Technol. 29, 3269\u20133280 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"unstructured":"Shen, H., Huang, L., Huang, C., Xu, W.: Tracklet association tracker: an end-to-end learning-based association approach for multi-object tracking. arXiv preprint arXiv:1808.01562 (2018)","key":"33_CR72"},{"doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468. IEEE (2016)","key":"33_CR73","DOI":"10.1109\/ICIP.2016.7533003"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2020"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-69532-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T02:38:58Z","timestamp":1671417538000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-69532-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030695316","9783030695323"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-69532-3_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"27 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/accv2020.kyoto\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"768","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"254","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}