GOT-10k: Generic Object Tracking Benchmark

Up-to-Date Leaderboard

Instructions:

Leaderboard will be updated immediately once new public submissions are evaluated and validated.
Click the name of an entry to see its descriptions and detailed performance, or download its tracking results.
AO: the average of overlap rates between tracking results and groundtruths over all frames.
SR: success rate, the percentage of successfully tracked frames where overlap rates are above a threshold.

Rank_↓	Method	AO	SR_0.50	SR_0.75	Hz	Hardware	Language	Date	Author
1	DCFST	0.597 ²	0.708 ¹	0.452 ²	51.46	TITAN X(Pascal), E5-2630	Pytorch	Jul 24, 2019	noUmbrella
2	ATOM2	0.602 ¹	0.701 ²	0.479 ¹	45.91	1080ti	python	Jun 14, 2019	wangxianhai
3	siamrpn_tp	0.517 ³	0.615 ³	0.329 ³	3.18	1070	python	Jun 09, 2019	triplepool
4	SiamFCv2	0.374	0.404	0.144	25.81	1 GeForce GTX Titan X	MATLAB	Dec 10, 2018	Official
5	litttletrack	0.355	0.395	0.106	30.42	1080ti	python	Jun 03, 2019	tianlang
6	SiamFC	0.348	0.353	0.098	44.15	1 GeForce GTX Titan X	MATLAB	Dec 10, 2018	Official
7	GOTURN	0.347	0.375	0.124	108.55 ²	1 GeForce GTX Titan X	Python	Dec 10, 2018	Official
8	CCOT	0.325	0.328	0.107	0.68	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
9	ECO	0.316	0.309	0.111	2.62	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
10	CF2	0.315	0.297	0.088	5.57	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
11	MDNet	0.299	0.303	0.099	1.52	1 GeForce GTX Titan X	Python	Dec 10, 2018	Official
12	CFNetc2	0.293	0.265	0.087	35.62	1 GeForce GTX Titan X	MATLAB	Dec 10, 2018	Official
13	ECOhc	0.286	0.276	0.096	44.55	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
14	CFNetc5	0.270	0.225	0.072	24.88	1 GeForce GTX Titan X	MATLAB	Dec 10, 2018	Official
15	CFNetc1	0.261	0.243	0.084	38.48	1 GeForce GTX Titan X	MATLAB	Dec 10, 2018	Official
16	BACF	0.260	0.262	0.101	14.44	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
17	MEEM	0.253	0.235	0.068	20.59	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
18	DAT	0.251	0.242	0.048	45.52	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
19	DSST	0.247	0.223	0.081	18.25	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
20	SAMF	0.246	0.241	0.084	7.43	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
21	Staple	0.246	0.239	0.089	28.87	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
22	SRDCFdecon	0.237	0.220	0.094	2.89	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
23	SRDCF	0.236	0.227	0.094	5.58	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
24	fDSST	0.206	0.187	0.075	30.43	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
25	CSK	0.205	0.174	0.056	133.46 ¹	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
26	KCF	0.203	0.177	0.065	94.66 ³	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
27	CSK_r1	0.202	0.169	0.056	17.96	CPU	Python	Dec 29, 2018	Chris
28	L1APG	0.181	0.174	0.068	13.06	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
29	LK	0.177	0.144	0.048	10.15	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
30	IVT	0.128	0.084	0.023	71.29	16 cores 2.0 GHz CPU	MATLAB	Dec 10, 2018	Official
31	kcf_tp	0.074	0.031	0.002	63.43	1070	python	Jun 09, 2019	triplepool

Legend

DCFST: None [Project Page]
ATOM2: None [Project Page]
siamrpn_tp: None [Project Page]
SiamFCv2: End-to-End Representation Learning for Correlation Filter based tracking. J. Valmadre, L. Bertinetto, J.F. Henriques, A. Vedaldi, P.H.S. Torr, CVPR 2017. [Paper] [Project Page] [Code]
litttletrack: None [Project Page]
SiamFC: Fully-Convolutional Siamese Networks for Object Tracking. L. Bertinetto, J. Valmedre, J.F. Henriques, A. Vedaldi, P.H.S. Torr, ECCV workshop 2016. [Paper] [Project Page] [Code]
GOTURN: Learning to Track at 100 FPS with Deep Regression Networks. D. Held, S. Thrun, S. Savarese, ECCV 2016. [Paper] [Project Page] [Code]
CCOT: Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking. M. Danelljan, A. Robinson, F. Khan, M. Felsberg, ECCV 2016. [Paper] [Project Page] [Code]
ECO: ECO: Efficient Convolution Operators for Tracking. M. Danelljan, G. Bhat, F.S. Khan, M. Felsberg, CVPR 2017. [Paper] [Project Page] [Code]
CF2: Hierachical Convolutional Features for Visual Tracking. C. Ma, J.B. Huang, X. Yang and M.H. Yang, ICCV 2015. [Paper] [Project Page] [Code]
MDNet: Learning Multi-Domain Convolutional Neural Networks for Visual Tracking. N. Hyeonseob and B. Han. CVPR 2016. [Paper] [Project Page] [Code]
CFNetc2: End-to-End Representation Learning for Correlation Filter based tracking. J. Valmadre, L. Bertinetto, J.F. Henriques, A. Vedaldi, P.H.S. Torr, CVPR 2017. [Paper] [Project Page] [Code]
ECOhc: ECO: Efficient Convolution Operators for Tracking. M. Danelljan, G. Bhat, F.S. Khan, M. Felsberg, CVPR 2017. [Paper] [Project Page] [Code]
CFNetc5: End-to-End Representation Learning for Correlation Filter based tracking. J. Valmadre, L. Bertinetto, J.F. Henriques, A. Vedaldi, P.H.S. Torr, CVPR 2017. [Paper] [Project Page] [Code]
CFNetc1: End-to-End Representation Learning for Correlation Filter based tracking. J. Valmadre, L. Bertinetto, J.F. Henriques, A. Vedaldi, P.H.S. Torr, CVPR 2017. [Paper] [Project Page] [Code]
BACF: Learning Background-Aware Correlation Filters for Visual Tracking. H.K. Galoogahi, A. Fagg, S. Lucey, ICCV 2017. [Paper] [Project Page] [Code]
MEEM: MEEM: Robust Tracking via Multiple Experts using Entropy Minimization. J. Zhang, S. Ma and S. Sclaroff, ECCV 2014. [Paper] [Project Page] [Code]
DAT: In Defense of Color-Based Model-Free Tracking. H. Possegger, T. Mauthner and H. Bischof, CVPR 2015. [Paper] [Project Page] [Code]
DSST: Accurate Scale Estimation for Robust Visual Tracking. M. Danelljan, G. Hager, F.S. Khan and M. Felsberg, BMVC 2014. [Paper] [Project Page] [Code]
SAMF: A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration. Y. Li and J. Zhu, ECCV workshop 2014. [Paper] [Code]
Staple: Staple: Complementary Learners for Real-Time Tracking. L. Bertinetto, J. Valmadre, S. Golodetz, O. Miksik, P.H.S. Torr, CVPR 2016. [Paper] [Project Page] [Code]
SRDCFdecon: Adaptively Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking. M. Danelljan, G. Hager, F. Khan, M. Felsberg, CVPR 2016. [Paper]
SRDCF: Learning Spatially Regularized Correlation Filters for Visual Tracking. M. Danelljan, G. Hager, F. Khan, M. Felsberg, ICCV 2015. [Paper] [Project Page] [Code]
fDSST: Discriminative Scale Space Tracking. M. Danelljan, G. Hager, F. Khan, M. Felsberg, PAMI 2017. [Paper] [Project Page] [Code]
CSK: Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. J.F. Henriques, R. Caseiro, P. Martins, J. Batista, ECCV 2012. [Paper] [Project Page] [Code]
KCF: High-Speed Tracking with Kernelized Correlation Filters. J.F. Henriques, R. Caseiro, P. Martins, J. Batista, PAMI 2015. [Paper] [Project Page] [Code]
CSK_r1: None [Project Page]
L1APG: Real-Time Robust L1 Tracker Using Accelerated Proximal Gradient Approach. C. Bao, Y. Wu, H. Ling and H. Ji, CVPR 2012. [Paper] [Code]
LK: Good Features to Track. J. Shi and C. Tomasi, CVPR 2002. [Paper]
IVT: Incremental Learning for Robust Visual Tracking. D. Ross, J. Lim, R.S. Lin and M.H. Yang, IJCV 2007. [Paper] [Project Page] [Code]
kcf_tp: None [Project Page]