Click on a measure to sort the table accordingly. See below for a more detailed description.
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
test_trker 1. | 59.7 | 0.0 ±0.0 | 0.0 | 0.0% | 100.0% | 7 | 182,326 | 0 (nan) | 0 (nan) | 22.3 | Public |
Anonymous submission | |||||||||||
DP_NMS 2. | 55.8 | 26.2 ±9.3 | 31.2 | 4.1% | 67.5% | 3,689 | 130,557 | 365 (12.9) | 638 (22.5) | 5.9 | Public |
H. Pirsiavash, D. Ramanan, C. Fowlkes. Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects. In CVPR, 2011. | |||||||||||
JPDA_m 3. | 56.4 | 26.2 ±6.1 | 0.0 | 4.1% | 67.5% | 3,689 | 130,549 | 365 (12.9) | 638 (22.5) | 22.2 | Public |
H. Rezatofighi, A. Milan, Z. Zhang, Q. Shi, A. Dick, I. Reid. Joint Probabilistic Data Association Revisited. In ICCV, 2015. | |||||||||||
MHT_ReID 4. | 63.6 | 27.1 ±47.2 | 36.4 | 30.6% | 31.4% | 13,068 | 118,829 | 1,071 (30.8) | 1,141 (32.8) | 0.5 | Public |
Anonymous submission | |||||||||||
DCOR 5. | 65.4 | 28.3 ±9.0 | 21.7 | 3.4% | 63.9% | 1,618 | 128,345 | 849 (28.7) | 2,592 (87.5) | 32.9 | Public |
Anonymous submission | |||||||||||
SMOT 6. | 90.6 | 29.7 ±7.3 | 0.0 | 5.3% | 47.7% | 17,426 | 107,552 | 3,108 (75.8) | 4,483 (109.3) | 0.2 | Public |
C. Dicle, O. Camps, M. Sznaier. The Way They Move: Tracking Targets with Similar Appearance. In ICCV, 2013. | |||||||||||
GMPHD_HDA 7. | 56.7 | 30.5 ±6.9 | 33.4 | 4.6% | 59.7% | 5,169 | 120,970 | 539 (16.0) | 731 (21.7) | 13.6 | Public |
Y. Song, M. Jeon. Online Multiple Object Tracking with the Hierarchically Adopted GM-PHD Filter using Motion and Appearance. In IEEE/IEIE The International Conference on Consumer Electronics (ICCE) Asia, 2016. | |||||||||||
CppSORT 8. | 65.3 | 31.5 ±9.0 | 27.7 | 4.3% | 59.9% | 3,048 | 120,278 | 1,587 (46.6) | 2,239 (65.8) | 687.1 | Public |
S. Murray. Real-Time Multiple Object Tracking - A Study on the Importance of Speed. In arXiv preprint arXiv:1709.03572, 2017. | |||||||||||
CEM 9. | 64.3 | 33.2 ±7.9 | 0.0 | 7.8% | 54.4% | 6,837 | 114,322 | 642 (17.2) | 731 (19.6) | 0.3 | Public |
A. Milan, S. Roth, K. Schindler. Continuous Energy Minimization for Multitarget Tracking. In IEEE TPAMI, 2014. | |||||||||||
GM_PHD_N1T 10. | 71.7 | 33.3 ±8.9 | 25.5 | 5.5% | 56.0% | 1,750 | 116,452 | 3,499 (96.8) | 3,594 (99.5) | 9.9 | Public |
N. Baisa, A. Wallace. Development of a N-type GM-PHD filter for multiple target, multiple type visual tracking. In Journal of Visual Communication and Image Representation, 2019. | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
KVIOU16 11. | 62.8 | 33.4 ±9.7 | 32.6 | 5.9% | 59.6% | 2,764 | 117,971 | 760 (21.5) | 1,473 (41.7) | 29.6 | Public |
Anonymous submission | |||||||||||
TBD 12. | 81.3 | 33.7 ±9.2 | 0.0 | 7.2% | 54.2% | 5,804 | 112,587 | 2,418 (63.2) | 2,252 (58.9) | 1.3 | Public |
A. Geiger, M. Lauer, C. Wojek, C. Stiller, R. Urtasun. 3D Traffic Scene Understanding from Movable Platforms. In Pattern Analysis and Machine Intelligence (PAMI), 2014. | |||||||||||
GM_PHD_e17 13. | 73.8 | 33.8 ±8.9 | 25.3 | 6.3% | 54.9% | 1,766 | 115,130 | 3,778 (102.5) | 3,874 (105.1) | 3.3 | Public |
Anonymous submission | |||||||||||
RNN_A_P 14. | 77.7 | 34.0 ±8.6 | 33.7 | 7.9% | 51.0% | 8,562 | 109,269 | 2,479 (61.9) | 3,393 (84.7) | 19.7 | Public |
Anonymous submission | |||||||||||
GM_PHD_Dl 15. | 73.3 | 34.3 ±9.1 | 20.5 | 7.1% | 51.5% | 2,350 | 111,886 | 5,605 (145.1) | 5,357 (138.7) | 3.5 | Public |
Anonymous submission | |||||||||||
GM_PHD_DAL 16. | 72.3 | 35.1 ±9.1 | 26.6 | 7.0% | 51.4% | 2,350 | 111,886 | 4,047 (104.8) | 5,338 (138.2) | 3.5 | Public |
N. Baisa. Online Multi-object Visual Tracking using a GM-PHD Filter with Deep Appearance Learning. In 22nd International Conference on Information Fusion, 2019. | |||||||||||
LP2D 17. | 61.0 | 35.7 ±10.1 | 34.2 | 8.7% | 50.7% | 5,084 | 111,163 | 915 (23.4) | 1,264 (32.4) | 49.3 | Public |
MOT baseline: Linear programming on 2D image coordinates. | |||||||||||
HISP_T 18. | 72.1 | 35.9 ±8.5 | 28.9 | 7.8% | 50.1% | 6,412 | 107,918 | 2,594 (63.6) | 2,298 (56.3) | 4.8 | Public |
N. Baisa. Online Multi-target Visual Tracking using a HISP Filter. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,, 2018. | |||||||||||
JCmin_MOT 19. | 56.5 | 36.7 ±9.1 | 36.2 | 7.5% | 54.4% | 2,936 | 111,890 | 667 (17.3) | 831 (21.5) | 14.8 | Public |
M. Abhijeet Boragule. Joint Cost Minimization for Multi-Object Tracking. In 2017 IEEE International Conference on Advanced Vide and Signale Based Surveillance, 2017. | |||||||||||
HISP_DAL 20. | 69.8 | 37.4 ±8.8 | 30.5 | 7.6% | 50.9% | 3,222 | 108,865 | 2,101 (52.1) | 2,151 (53.4) | 3.3 | Public |
N. Baisa. Robust Online Multi-target Visual Tracking using a HISP Filter with Discriminative Deep Appearance Learning. In CoRR, 2019. | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
GoturnM16 21. | 75.7 | 37.5 ±7.5 | 25.1 | 8.4% | 46.5% | 17,746 | 92,867 | 3,277 (66.8) | 2,994 (61.0) | 3.9 | Public |
Anonymous submission | |||||||||||
LTTSC-CRF 22. | 67.3 | 37.6 ±9.9 | 42.1 | 9.6% | 55.2% | 11,969 | 101,343 | 481 (10.8) | 1,012 (22.8) | 0.6 | Public |
N. Le, A. Heili, M. Odobez. Long-Term Time-Sensitive Costs for CRF-Based Tracking by Detection. In ECCVw, 2016. | |||||||||||
GMMCP 23. | 70.3 | 38.1 ±7.8 | 35.5 | 8.6% | 50.9% | 6,607 | 105,315 | 937 (22.2) | 1,669 (39.5) | 0.5 | Public |
A. Dehghan, S. Assari, M. Shah.. GMMCP-Tracker:Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking. In CVPR, 2015. | |||||||||||
HAM_ACT16 24. | 54.6 | 38.1 ±8.2 | 43.3 | 7.8% | 54.4% | 6,976 | 105,434 | 418 (9.9) | 707 (16.8) | 8.0 | Public |
OVBT 25. | 80.5 | 38.4 ±8.8 | 37.8 | 7.5% | 47.3% | 11,517 | 99,463 | 1,321 (29.1) | 2,140 (47.1) | 0.3 | Public |
Y. Ban, S. Ba, X. Alameda-Pineda, R. Horaud. Tracking Multiple Persons Based on a Variational Bayesian Model. In BMTT 2016, . | |||||||||||
EAMTT_pub 26. | 64.7 | 38.8 ±8.5 | 42.4 | 7.9% | 49.1% | 8,114 | 102,452 | 965 (22.0) | 1,657 (37.8) | 11.8 | Public |
R. Sanchez-Matilla, F. Poiesi, A. Cavallaro "Multi-target tracking with strong and weak detections" in BMTT ECCVw 2016 | |||||||||||
SDMT 27. | 59.3 | 39.6 ±8.3 | 42.3 | 11.7% | 49.1% | 11,130 | 98,343 | 602 (13.1) | 772 (16.8) | 19.8 | Public |
M. Thoreau, N. Kottege. Deep Similarity Metric Learning for Real-Time Pedestrian Tracking. In arXiv, 2018. | |||||||||||
D_cost16 28. | 54.3 | 39.9 ±9.1 | 35.3 | 8.7% | 50.2% | 1,133 | 107,586 | 790 (19.3) | 824 (20.1) | 8.5 | Public |
Anonymous submission | |||||||||||
AM_ADM 29. | 62.3 | 40.1 ±10.1 | 43.8 | 7.1% | 46.2% | 8,503 | 99,891 | 789 (17.5) | 1,736 (38.4) | 5.8 | Public |
S. Lee, M. Kim, S. Bae, Learning Discriminative Appearance Models for Online Multi-Object Tracking with Appearance Discriminability Measures, In IEEE Access, 2018. | |||||||||||
PMPTracker 30. | 68.5 | 40.3 ±11.7 | 38.2 | 10.4% | 42.0% | 10,071 | 97,524 | 1,343 (28.9) | 2,764 (59.4) | 148.0 | Public |
Light version of PTZ camera Mutiple People Tracker | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
PHD_T 31. | 62.8 | 40.3 ±9.0 | 48.3 | 11.6% | 43.1% | 7,147 | 100,895 | 815 (18.2) | 2,446 (54.8) | 9.9 | Public |
Anonymous submission | |||||||||||
GMPHD_ReId 32. ![]() | 57.2 | 40.3 ±9.3 | 48.3 | 11.6% | 43.1% | 7,147 | 100,895 | 815 (18.2) | 2,446 (54.8) | 20.4 | Public |
Anonymous submission | |||||||||||
PHD_GSDL16 33. | 67.0 | 41.0 ±8.9 | 43.1 | 11.3% | 41.5% | 6,498 | 99,257 | 1,810 (39.7) | 3,650 (80.1) | 8.3 | Public |
Z. Fu, P. Feng, F. Angelini, J. Chambers, S. Naqvi. Particle PHD Filter based Multiple Human Tracking using Online Group-Structured Dictionary Learning. In IEEE Access, 2018. | |||||||||||
LINF1 34. | 56.3 | 41.0 ±9.5 | 45.7 | 11.6% | 51.3% | 7,896 | 99,224 | 430 (9.4) | 963 (21.1) | 4.2 | Public |
L. Fagot-Bouquet, R. Audigier, Y. Dhome, F. Lerasle. Improving Multi-Frame Data Association with Sparse Representations for Robust Near-Online Multi-Object Tracking. In ECCV, 2016. | |||||||||||
OST16 35. | 65.7 | 41.5 ±9.2 | 39.1 | 10.7% | 45.6% | 5,919 | 99,709 | 1,056 (23.3) | 1,487 (32.8) | 4.7 | Public |
Anonymous submission | |||||||||||
TestUnsup 36. | 57.8 | 41.5 ±9.0 | 44.9 | 13.7% | 43.5% | 12,596 | 93,404 | 643 (13.2) | 796 (16.3) | 19.7 | Public |
Multi Object Tracking using Deep Structural Cost Minimization in Data Association | |||||||||||
MHT_bLSTM6 37. | 60.5 | 42.1 ±9.7 | 47.8 | 14.9% | 44.4% | 11,637 | 93,172 | 753 (15.4) | 1,156 (23.6) | 1.8 | Public |
C. Kim, F. Li, J. Rehg. Multi-object Tracking with Neural Gating Using Bilinear LSTM. In ECCV, 2018. | |||||||||||
AEb 38. | 39.3 | 42.9 ±11.0 | 48.7 | 15.3% | 49.0% | 4,487 | 99,310 | 375 (8.2) | 1,334 (29.3) | 22.3 | Public |
Anonymous submission | |||||||||||
oICF 39. | 59.0 | 43.2 ±10.2 | 49.3 | 11.3% | 48.5% | 6,651 | 96,515 | 381 (8.1) | 1,404 (29.8) | 0.4 | Public |
H. Kieritz, S. Becker, W. Hübner, M. Arens. Online Multi-Person Tracking using Integral Channel Features. In IEEE Advanced Video and Signal-based Surveillance (AVSS) 2016, 2016. | |||||||||||
LFNF16 40. | 61.4 | 43.6 ±11.0 | 41.6 | 13.3% | 45.7% | 6,616 | 95,363 | 836 (17.5) | 938 (19.7) | 0.6 | Public |
Sheng H, Hao L, Chen J, et al. Robust Local Effective Matching Model for Multi-Target Tracking. In PCM, 2017 | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
CDA_DDALv2 41. | 58.3 | 43.9 ±7.8 | 45.1 | 10.7% | 44.4% | 6,450 | 95,175 | 676 (14.1) | 1,795 (37.6) | 0.5 | Public |
S. Bae and K. Yoon, Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking , In IEEE TPAMI, 2017. | |||||||||||
SRPN 42. | 63.5 | 44.0 ±10.7 | 36.6 | 15.5% | 45.7% | 18,784 | 82,318 | 1,047 (19.1) | 1,118 (20.4) | 3.9 | Public |
Anonymous submission | |||||||||||
QuadMOT16 43. | 59.8 | 44.1 ±9.4 | 38.3 | 14.6% | 44.9% | 6,388 | 94,775 | 745 (15.5) | 1,096 (22.8) | 1.8 | Public |
J. Son, M. Baek, M. Cho, B. Han. Multi-Object Tracking with Quadruplet Convolutional Neural Networks. In CVPR, 2017. | |||||||||||
OTCD_1 44. | 57.8 | 44.4 ±10.8 | 45.6 | 11.6% | 47.6% | 5,759 | 94,927 | 759 (15.8) | 1,787 (37.3) | 17.6 | Public |
Q. Liu, B. Liu, Y. Wu, W. Li, N. Yu. Real-Time Online Multi-Object Tracking in Compressed Domain. In IEEE Access, 2019. | |||||||||||
TBSS 45. | 61.1 | 44.6 ±9.3 | 42.6 | 12.3% | 43.9% | 4,136 | 96,128 | 790 (16.7) | 1,419 (30.0) | 3.0 | Public |
X. Zhou, P. Jiang, Z. Wei, H. Dong, F. Wang. Online Multi-Object Tracking with Structural Invariance Constraint. In BMVC, 2018. | |||||||||||
DCCRF16 46. | 58.4 | 44.8 ±9.8 | 39.7 | 14.1% | 42.3% | 5,613 | 94,133 | 968 (20.0) | 1,378 (28.5) | 0.1 | Public |
H. Zhou, W. Ouyang, J. Cheng, X. Wang, H. Li. Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking. In IEEE Transactions on Circuits and Systems for Video Technology, 2018. | |||||||||||
EDMT 47. | 47.1 | 45.3 ±9.1 | 47.9 | 17.0% | 39.9% | 11,122 | 87,890 | 639 (12.3) | 946 (18.3) | 1.8 | Public |
J. Chen, H. Sheng, Y. Zhang, Z. Xiong. Enhancing Detection Model for Multiple Hypothesis Tracking. In BMTT-PETS CVPRw, 2017. | |||||||||||
INTERA_MOT 48. | 44.2 | 45.4 ±8.6 | 47.7 | 18.1% | 38.7% | 13,407 | 85,547 | 600 (11.3) | 930 (17.5) | 4.3 | Public |
L. Lan, X. Wang, S. Zhang, D. Tao, W. Gao, T. Huang. Interacting Tracklets for Multi-object Tracking. In IEEE Transactions on Image Processing, 2018. | |||||||||||
MTDF 49. | 65.0 | 45.7 ±11.2 | 40.1 | 14.1% | 36.4% | 12,018 | 84,970 | 1,987 (37.2) | 3,377 (63.2) | 1.5 | Public |
Z. Fu, F. Angelini, J. Chambers, S. Naqvi. Multi-Level Cooperative Fusion of GM-PHD Filters for Online Multiple Human Tracking. In IEEE Transactions on Multimedia, 2019. | |||||||||||
MHT_DAM 50. | 48.8 | 45.8 ±8.9 | 46.1 | 16.2% | 43.2% | 6,412 | 91,758 | 590 (11.9) | 781 (15.7) | 0.8 | Public |
C. Kim, F. Li, A. Ciptadi, J. Rehg. Multiple Hypothesis Tracking Revisited. In ICCV, 2015. | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
RAR16pub 51. | 58.3 | 45.9 ±9.7 | 48.8 | 13.2% | 41.9% | 6,871 | 91,173 | 648 (13.0) | 1,992 (39.8) | 0.9 | Public |
K. Fang, Y. Xiang, X. Li, S. Savarese. Recurrent Autoregressive Networks for Online Multi-Object Tracking. In The IEEE Winter Conference on Applications of Computer Vision (WACV), 2018. | |||||||||||
deepS2 52. | 45.4 | 46.0 ±8.2 | 46.5 | 15.5% | 42.6% | 5,124 | 92,697 | 693 (14.1) | 759 (15.4) | 0.7 | Public |
ID 32 | |||||||||||
STAM16 53. | 56.9 | 46.0 ±9.1 | 50.0 | 14.6% | 43.6% | 6,895 | 91,117 | 473 (9.5) | 1,422 (28.4) | 0.2 | Public |
Q. Chu, W. Ouyang, H. Li, X. Wang, B. Liu, N. Yu. Online Multi-object Tracking Using CNN-Based Single Object Tracker with Spatial-Temporal Attention Mechanism. In 2017 IEEE International Conference on Computer Vision (ICCV), 2017. | |||||||||||
DMAN 54. | 46.2 | 46.1 ±11.1 | 54.8 | 17.4% | 42.7% | 7,909 | 89,874 | 532 (10.5) | 1,616 (31.9) | 0.3 | Public |
J. Zhu, H. Yang, N. Liu, M. Kim, W. Zhang, M. Yang. Online Multi-Object Tracking with Dual Matching Attention Networks. In ECCV, 2018. | |||||||||||
DD_TAMA16 55. | 42.2 | 46.2 ±8.4 | 49.4 | 14.1% | 44.0% | 5,126 | 92,367 | 598 (12.1) | 1,127 (22.8) | 6.5 | Public |
Y. Yoon, D. Kim, K. Yoon, Y. Song, M. Jeon. Online Multiple Pedestrian Tracking using Deep Temporal Appearance Matching Association. In arXiv:1907.00831, 2019. | |||||||||||
JMC 56. | 47.8 | 46.3 ±9.0 | 46.3 | 15.5% | 39.7% | 6,373 | 90,914 | 657 (13.1) | 1,114 (22.2) | 0.8 | Public |
S. Tang, B. Andres, M. Andriluka, B. Schiele. Multi-Person Tracking by Multicuts and Deep Matching. In BMTT, 2016. | |||||||||||
NOMT 57. | 39.6 | 46.4 ±9.9 | 53.3 | 18.3% | 41.4% | 9,753 | 87,565 | 359 (6.9) | 504 (9.7) | 2.6 | Public |
W. Choi. Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor. In ICCV, 2015. | |||||||||||
YOONKJ16 58. | 50.8 | 47.0 ±8.4 | 50.1 | 16.5% | 41.8% | 7,901 | 88,179 | 627 (12.1) | 945 (18.3) | 3.5 | Public |
Anonymous submission | |||||||||||
MCjoint 59. | 39.6 | 47.1 ±10.8 | 52.3 | 20.4% | 46.9% | 6,703 | 89,368 | 370 (7.3) | 598 (11.7) | 0.6 | Public |
}@article{DBLP:journals/corr/KeuperTYABS16, author = {Margret Keuper and Siyu Tang and Zhongjie Yu and Bjoern Andres and Thomas Brox and Bernt Schiele}, title = {A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects}, journal = {CoRR}, volume = {abs/1607.06317}, year = {2016}, url = {http://arxiv.org/abs/1607.06317}, timestamp = {Wed, 07 Jun 2017 14:41:31 +0200}, biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/KeuperTYABS16}, bibsource = {dblp computer science bibliography, http://dblp.org} } | |||||||||||
AMIR 60. | 48.6 | 47.2 ±7.7 | 46.3 | 14.0% | 41.6% | 2,681 | 92,856 | 774 (15.8) | 1,675 (34.1) | 1.0 | Public |
A. Sadeghian, A. Alahi, S. Savarese. Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies. In ICCV, 2017. | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
eHAF16 61. | 41.3 | 47.2 ±16.8 | 52.4 | 18.6% | 42.8% | 12,586 | 83,107 | 542 (10.0) | 787 (14.5) | 0.5 | Public |
H. Sheng, Y. Zhang, J. Chen, Z. Xiong, J. Zhang. Heterogeneous Association Graph Fusion for Target Association in Multiple Object Tracking. In IEEE Transactions on Circuits and Systems for Video Technology, 2018. | |||||||||||
ASTT 62. | 42.4 | 47.2 ±9.6 | 44.3 | 16.3% | 41.6% | 4,680 | 90,877 | 633 (12.6) | 814 (16.2) | 0.5 | Public |
Yi Tao el al., “Adaptive Spatio-temporal Model Based Multiple Object Tracking Considering a Moving Camera[C]”, International Conference on Universal Village (UV), 2018. | |||||||||||
JCSTD 63. | 55.1 | 47.4 ±8.3 | 41.1 | 14.4% | 36.4% | 8,076 | 86,638 | 1,266 (24.1) | 2,697 (51.4) | 8.8 | Public |
W. Tian, M. Lauer, L. Chen. Online Multi-Object Tracking Using Joint Domain Information in Traffic Scenarios. In IEEE Transactions on Intelligent Transportation Systems, 2019. | |||||||||||
EAGS16 64. | 35.8 | 47.4 ±10.4 | 50.1 | 17.3% | 42.7% | 8,369 | 86,931 | 575 (11.0) | 913 (17.5) | 197.3 | Public |
H. Sheng, X. Zhang, Y. Zhang, Y. Wu, J. Chen. Enhanced Association with Supervoxels in Multiple Hypothesis Tracking. In IEEE Access, 2018. | |||||||||||
NLLMPa 65. | 40.4 | 47.6 ±10.6 | 47.3 | 17.0% | 40.4% | 5,844 | 89,093 | 629 (12.3) | 768 (15.0) | 8.3 | Public |
E. Levinkov, J. Uhrig, S. Tang, M. Omran, E. Insafutdinov, A. Kirillov, C. Rother, T. Brox, B. Schiele, B. Andres. Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications. In CVPR, 2017. | |||||||||||
MOTDT 66. | 46.8 | 47.6 ±8.2 | 50.9 | 15.2% | 38.3% | 9,253 | 85,431 | 792 (14.9) | 1,858 (35.0) | 20.6 | Public |
C. Long, A. Haizhou, Z. Zijie, S. Chong. Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-identification. In ICME, 2018. | |||||||||||
FWT 67. | 49.8 | 47.8 ±9.4 | 44.3 | 19.1% | 38.2% | 8,886 | 85,487 | 852 (16.0) | 1,534 (28.9) | 0.6 | Public |
R. Henschel, L. Leal-Taixé, D. Cremers, B. Rosenhahn. Fusion of Head and Full-Body Detectors for Multi-Object Tracking. In Trajnet CVPRW, 2018. | |||||||||||
SRPN16 68. | 53.7 | 48.2 ±8.5 | 51.3 | 14.2% | 36.8% | 7,767 | 85,973 | 790 (14.9) | 2,006 (38.0) | 1.4 | Public |
Anonymous submission | |||||||||||
GCRA 69. | 46.1 | 48.2 ±8.3 | 48.6 | 12.9% | 41.1% | 5,104 | 88,586 | 821 (16.0) | 1,117 (21.7) | 2.8 | Public |
C. Ma, C. Yang, F. Yang, Y. Zhuang, Z. Zhang, H. Jia, X. Xie. Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking. In ICME, 2018. | |||||||||||
AOReid 70. | 41.9 | 48.2 ±8.7 | 50.8 | 15.3% | 36.8% | 10,283 | 83,301 | 821 (15.1) | 1,963 (36.1) | 11.2 | Public |
Anonymous submission | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
MOTPP 71. | 41.4 | 48.3 ±8.7 | 45.4 | 18.6% | 40.1% | 7,378 | 86,181 | 661 (12.5) | 834 (15.8) | 11.8 | Public |
Anonymous submission | |||||||||||
MOTPPF 72. | 36.8 | 48.4 ±8.8 | 48.5 | 19.1% | 39.8% | 9,152 | 84,266 | 595 (11.1) | 802 (14.9) | 11.8 | Public |
Anonymous submission | |||||||||||
STRN_MOT16 73. | 45.4 | 48.5 ±8.5 | 53.9 | 17.0% | 34.9% | 9,038 | 84,178 | 747 (13.9) | 2,919 (54.2) | 13.5 | Public |
J. Xu, Y. Cao, Z. Zhang, H. Hu. Spatial-Temporal Relation Networks for Multi-Object Tracking. In ICCV, 2019. | |||||||||||
TLMHT 74. | 40.2 | 48.7 ±8.6 | 55.3 | 15.7% | 44.5% | 6,632 | 86,504 | 413 (7.9) | 642 (12.2) | 4.8 | Public |
H. Sheng, J. Chen, Y. Zhang, W. Ke, Z. Xiong, J. Yu. Iterative Multiple Hypothesis Tracking with Tracklet-level Association. In IEEE Transactions on Circuits and Systems for Video Technology, 2018. | |||||||||||
DeepMP16 75. | 34.7 | 48.7 ±10.3 | 50.1 | 15.0% | 43.6% | 4,111 | 88,862 | 535 (10.4) | 873 (17.0) | 9.9 | Public |
Anonymous submission | |||||||||||
LMP 76. | 36.8 | 48.8 ±9.8 | 51.3 | 18.2% | 40.1% | 6,654 | 86,245 | 481 (9.1) | 595 (11.3) | 0.5 | Public |
S. Tang, M. Andriluka, B. Andres, B. Schiele. Multiple People Tracking with Lifted Multicut and Person Re-identification. In CVPR, 2017. | |||||||||||
KCF16 77. | 48.8 | 48.8 ±9.6 | 47.2 | 15.8% | 38.1% | 5,875 | 86,567 | 906 (17.3) | 1,116 (21.2) | 0.1 | Public |
P. Chu, H. Fan, C. Tan, H. Ling. Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment. In WACV, 2019. | |||||||||||
DAST 78. | 40.5 | 48.9 ±8.4 | 53.2 | 15.2% | 36.2% | 9,987 | 82,427 | 838 (15.3) | 1,936 (35.3) | 8.7 | Public |
Anonymous submission | |||||||||||
CRF_RNN16 79. | 33.9 | 49.0 ±7.2 | 53.9 | 18.1% | 35.8% | 8,495 | 83,838 | 621 (11.5) | 1,252 (23.2) | 1.5 | Public |
Anonymous submission | |||||||||||
AFN 80. | 41.3 | 49.0 ±10.2 | 48.2 | 19.1% | 35.7% | 9,508 | 82,506 | 899 (16.4) | 1,383 (25.3) | 0.6 | Public |
H. Shen, L. Huang, C. Huang, W. Xu. Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking. In CoRR, 2018. | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
MOTHP 81. | 37.7 | 49.1 ±9.1 | 46.9 | 20.0% | 38.9% | 9,038 | 83,031 | 679 (12.5) | 850 (15.6) | 11.8 | Public |
Anonymous submission | |||||||||||
eTC 82. | 36.5 | 49.2 ±9.1 | 56.1 | 17.3% | 40.3% | 8,400 | 83,702 | 606 (11.2) | 882 (16.3) | 0.7 | Public |
G. Wang, Y. Wang, H. Zhang, R. Gu, J. Hwang. Exploit the connectivity: Multi-object tracking with trackletnet. In Proceedings of the 27th ACM International Conference on Multimedia, 2019. | |||||||||||
LSST16O 83. | 46.1 | 49.2 ±10.2 | 56.5 | 13.4% | 41.4% | 7,187 | 84,875 | 606 (11.3) | 2,497 (46.7) | 2.0 | Public |
Anonymous submission | |||||||||||
HCC 84. | 32.2 | 49.3 ±10.2 | 50.7 | 17.8% | 39.9% | 5,333 | 86,795 | 391 (7.5) | 535 (10.2) | 0.8 | Public |
L. Ma, S. Tang, M. Black, L. Gool. Customized Multi-Person Tracker. In Computer Vision -- ACCV 2018, 2018. | |||||||||||
STCG 85. | 35.9 | 49.3 ±8.6 | 52.0 | 16.2% | 41.4% | 6,886 | 84,979 | 515 (9.6) | 775 (14.5) | 22.3 | Public |
Anonymous submission | |||||||||||
siameseCos 86. | 40.3 | 49.4 ±8.4 | 49.8 | 19.1% | 39.4% | 6,281 | 85,384 | 679 (12.8) | 823 (15.5) | 0.8 | Public |
In preparation | |||||||||||
TLO16 87. | 44.2 | 49.8 ±10.0 | 47.8 | 16.6% | 40.6% | 6,085 | 84,623 | 782 (14.6) | 1,278 (23.8) | 12.4 | Public |
Anonymous submission | |||||||||||
CMT16 88. | 28.0 | 49.8 ±9.0 | 59.2 | 16.6% | 43.6% | 9,229 | 81,882 | 365 (6.6) | 617 (11.2) | 6.3 | Public |
#Submission: TIP-21190-2019 | |||||||||||
NOTA 89. | 32.8 | 49.8 ±8.3 | 55.3 | 17.9% | 37.7% | 7,248 | 83,614 | 614 (11.3) | 1,372 (25.3) | 19.2 | Public |
L. Chen, H. Ai, R. Chen, Z. Zhuang. Aggregate Tracklet Appearance Features for Multi-Object Tracking. In IEEE Signal Processing Letters, 2019. | |||||||||||
OMHT16 90. | 44.6 | 49.8 ±9.9 | 46.7 | 16.1% | 40.4% | 6,244 | 84,342 | 888 (16.5) | 1,332 (24.8) | 12.4 | Public |
Anonymous submission | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
MMHT16 91. | 41.9 | 49.9 ±9.8 | 47.3 | 16.2% | 40.7% | 6,110 | 84,455 | 823 (15.3) | 1,289 (24.0) | 12.4 | Public |
Anonymous submission | |||||||||||
RTT 92. | 47.9 | 49.9 ±8.0 | 49.3 | 19.0% | 32.8% | 9,927 | 80,406 | 955 (17.1) | 2,247 (40.2) | 1.8 | Public |
Anonymous submission | |||||||||||
ENFT 93. | 25.1 | 50.0 ±8.2 | 54.6 | 17.8% | 41.1% | 8,214 | 82,541 | 479 (8.8) | 724 (13.2) | 22.3 | Public |
Anonymous submission | |||||||||||
pairwise16 94. | 32.0 | 50.0 ±65.9 | 52.4 | 19.4% | 38.7% | 10,995 | 79,568 | 628 (11.1) | 939 (16.7) | 22.3 | Public |
Anonymous submission | |||||||||||
SCNet 95. | 51.9 | 50.0 ±8.9 | 51.1 | 15.5% | 34.1% | 10,526 | 79,755 | 866 (15.4) | 2,141 (38.1) | 0.3 | Public |
Anonymous submission | |||||||||||
MEN 96. | 41.0 | 50.0 ±9.1 | 52.8 | 15.0% | 37.0% | 6,117 | 84,271 | 706 (13.1) | 1,797 (33.4) | 2.0 | Public |
Anonymous submission | |||||||||||
TLO 97. | 45.3 | 50.1 ±9.9 | 48.1 | 16.3% | 40.7% | 5,582 | 84,629 | 786 (14.7) | 1,294 (24.1) | 5.6 | Public |
Anonymous submission | |||||||||||
MOT_FILTER 98. | 35.8 | 50.2 ±12.9 | 46.8 | 17.9% | 39.7% | 5,267 | 84,812 | 664 (12.4) | 978 (18.3) | 11.8 | Public |
Anonymous submission | |||||||||||
ENFT16 99. | 29.2 | 50.3 ±8.3 | 55.0 | 19.2% | 39.8% | 8,341 | 81,843 | 490 (8.9) | 754 (13.7) | 0.4 | Public |
BUAA | |||||||||||
HTBT16 100. | 31.9 | 50.3 ±8.2 | 55.0 | 19.2% | 39.8% | 8,341 | 81,843 | 490 (8.9) | 754 (13.7) | 0.2 | Public |
Anonymous submission | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
CRF_TRACK 101. | 31.6 | 50.3 ±7.9 | 54.4 | 18.3% | 35.7% | 7,148 | 82,746 | 702 (12.9) | 1,387 (25.4) | 1.5 | Public |
Anonymous submission | |||||||||||
CRFTrack16 102. | 32.3 | 50.3 ±7.9 | 54.4 | 18.3% | 35.7% | 7,148 | 82,746 | 702 (12.9) | 1,387 (25.4) | 1.5 | Public |
Anonymous submission | |||||||||||
MOTHPCLEAN 103. | 32.2 | 50.4 ±9.4 | 47.0 | 19.1% | 39.5% | 5,332 | 84,505 | 657 (12.2) | 862 (16.1) | 11.8 | Public |
Anonymous submission | |||||||||||
TTL16 104. | 44.3 | 50.4 ±10.3 | 50.1 | 17.4% | 39.9% | 8,491 | 81,156 | 807 (14.5) | 1,251 (22.5) | 6.7 | Public |
Anonymous submission | |||||||||||
PV 105. | 46.3 | 50.4 ±10.1 | 50.8 | 14.9% | 38.9% | 2,600 | 86,780 | 1,061 (20.2) | 3,181 (60.7) | 7.3 | Public |
Anonymous submission | |||||||||||
MOTPP16 106. | 33.6 | 50.5 ±9.7 | 47.2 | 19.6% | 39.4% | 5,939 | 83,694 | 638 (11.8) | 823 (15.2) | 3.0 | Public |
Anonymous submission | |||||||||||
UTA 107. | 41.7 | 50.6 ±7.9 | 50.4 | 18.3% | 33.5% | 7,752 | 81,584 | 722 (13.1) | 2,196 (39.7) | 5.0 | Public |
Anonymous submission | |||||||||||
TPM 108. | 36.7 | 51.3 ±9.3 | 47.9 | 18.7% | 40.8% | 2,701 | 85,504 | 569 (10.7) | 707 (13.3) | 0.8 | Public |
Anonymous submission | |||||||||||
HDTR 109. | 26.4 | 53.6 ±8.7 | 46.6 | 21.2% | 37.0% | 4,714 | 79,353 | 618 (10.9) | 833 (14.7) | 3.6 | Public |
retrack 110. ![]() | 34.0 | 53.9 ±13.0 | 52.7 | 20.3% | 32.3% | 6,999 | 76,251 | 818 (14.1) | 2,613 (44.9) | 22.3 | Public |
Anonymous submission | |||||||||||
Tracker | Avg Rank | MOTA | IDF1 | MT | ML | FP | FN | ID Sw. | Frag | Hz | Detector |
Tracktor16 111. | 35.1 | 54.4 ±12.0 | 52.5 | 19.0% | 36.9% | 3,280 | 79,149 | 682 (12.1) | 1,480 (26.2) | 1.5 | Public |
P. Bergmann, T. Meinhardt, L. Leal-Taixé. Tracking without bells and whistles. In ICCV, 2019. | |||||||||||
MTT_TPR 112. | 36.1 | 54.9 ±11.7 | 53.1 | 18.7% | 34.8% | 4,130 | 76,673 | 1,447 (25.0) | 3,693 (63.7) | 6.7 | Public |
Anonymous submission | |||||||||||
MPNTrack16 113. | 20.8 | 55.9 ±11.7 | 59.9 | 26.0% | 35.6% | 7,086 | 72,902 | 431 (7.2) | 921 (15.3) | 11.9 | Public |
Anonymous submission | |||||||||||
MHT___ReID 114. | 40.8 | 56.4 ±11.6 | 54.2 | 39.7% | 17.4% | 23,791 | 54,169 | 1,478 (21.0) | 1,547 (22.0) | 0.5 | Public |
Anonymous submission | |||||||||||
ReTrack16 115. | 31.3 | 57.0 ±12.3 | 54.2 | 21.9% | 34.3% | 4,446 | 73,258 | 688 (11.5) | 1,543 (25.8) | 0.8 | Public |
Anonymous submission | |||||||||||
DpTrack 116. | 30.5 | 59.3 ±18.7 | 52.8 | 27.4% | 24.6% | 8,566 | 63,603 | 2,045 (31.4) | 1,555 (23.9) | 10.4 | Public |
Anonymous submission | |||||||||||
DS_v2 117. | 26.2 | 59.3 ±12.9 | 57.5 | 24.2% | 29.1% | 7,465 | 65,810 | 887 (13.9) | 2,738 (42.8) | 39.4 | Public |
Anonymous submission | |||||||||||
dpt_dpt 118. | 24.3 | 61.3 ±10.7 | 60.4 | 32.1% | 18.6% | 12,411 | 57,481 | 739 (10.8) | 1,960 (28.6) | 148.0 | Public |
Anonymous submission |
Due to a minor bug in the export script, all results were re-evaluated on April 11, 2016. Here is the old snapshot of the leaderboard.
Sequences | Frames | Trajectories | Boxes |
7 | 5919 | 759 | 182326 |
Sequence difficulty (from easiest to hardest, measured by average MOTA)
...
...
Measure | Better | Perfect | Description |
Avg Rank | lower | 1 | This is the rank of each tracker averaged over all present evaluation measures. |
MOTA | higher | 100 % | Multiple Object Tracking Accuracy [1]. This measure combines three error sources: false positives, missed targets and identity switches. |
MOTP | higher | 100 % | Multiple Object Tracking Precision [1]. The misalignment between the annotated and the predicted bounding boxes. |
IDF1 | higher | 100 % | ID F1 Score [2]. The ratio of correctly identified detections over the average number of ground-truth and computed detections. |
FAF | lower | 0 | The average number of false alarms per frame. |
MT | higher | 100 % | Mostly tracked targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at least 80% of their respective life span. |
ML | lower | 0 % | Mostly lost targets. The ratio of ground-truth trajectories that are covered by a track hypothesis for at most 20% of their respective life span. |
FP | lower | 0 | The total number of false positives. |
FN | lower | 0 | The total number of false negatives (missed targets). |
ID Sw. | lower | 0 | The total number of identity switches. Please note that we follow the stricter definition of identity switches as described in [3]. |
Frag | lower | 0 | The total number of times a trajectory is fragmented (i.e. interrupted during tracking). |
Hz | higher | Inf. | Processing speed (in frames per second excluding the detector) on the benchmark. |
Symbol | Description |
This is an online (causal) method, i.e. the solution is immediately available with each incoming frame and cannot be changed at any later time. | |
This method used the provided detection set as input. | |
![]() |
This entry has been submitted or updated less than a week ago. |
[1] | Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics. Image and Video Processing, 2008(1):1-10, 2008. |
[2] | Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking. In ECCV workshop on Benchmarking Multi-Target Tracking, 2016. |
[3] | Learning to associate: HybridBoosted multi-target tracker for crowded scene. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009. |