Visual Tracker Benchmark ver 1.1 (submitted to PAMI)

Test sequences

The full benchmark contains 100 sequences from recent literatures.

  • The sequence names are in CamelCase without any blanks or underscores (_).
  • When there exist multiple targets each target is identified as dot+id_number (e.g. Jogging.1 and Jogging.2).
  • Each row in the ground-truth files represents the bounding box of the target in that frame, (x, y, box-width, box-height).
  • In most sequences the first row corresponds to the first frame and the last row to the last frame, except the following sequences
        David(300:770), Football1(1:74), Freeman3(1:460), Freeman4(1:283).
TB-50 Sequences.
Basketball
Basketball [zip]
IV, OCC, DEF, OPR, BC
Biker
Biker [zip]
SV, OCC, MB, FM, OPR, OV, LR
Bird1
Bird1 [zip]
DEF, FM, OV
BlurBody
BlurBody [zip]
SV, DEF, MB, FM, IPR
BlurCar2
BlurCar2 [zip]
SV, MB, FM
BlurFace
BlurFace [zip]
MB, FM, IPR
BlurOwl
BlurOwl [zip]
SV, MB, FM, IPR
Bolt
Bolt [zip]
OCC, DEF, IPR, OPR
Box
Box [zip]
IV, SV, OCC, MB, IPR, OPR, OV, BC, LR
Car1
Car1 [zip]
IV, SV, MB, FM, BC, LR
Car4
Car4 [zip]
IV, SV
CarDark
CarDark [zip]
IV, BC
CarScale
CarScale [zip]
SV, OCC, FM, IPR, OPR
ClifBar
ClifBar [zip]
SV, OCC, MB, FM, IPR, OV, BC
Couple
Couple [zip]
SV, DEF, FM, OPR, BC
Crowds
Crowds [zip]
IV, DEF, BC
David
David [zip]
IV, SV, OCC, DEF, MB, IPR, OPR
Deer
Deer [zip]
MB, FM, IPR, BC, LR
Diving
Diving [zip]
SV, DEF, IPR
DragonBaby
DragonBaby [zip]
SV, OCC, MB, FM, IPR, OPR, OV
Dudek
Dudek [zip]
SV, OCC, DEF, FM, IPR, OPR, OV, BC
Football
Football [zip]
OCC, IPR, OPR, BC
Freeman4
Freeman4 [zip]
SV, OCC, IPR, OPR
Girl
Girl [zip]
SV, OCC, IPR, OPR
Human3
Human3 [zip]
SV, OCC, DEF, OPR, BC
Human4
Human4 [2]
[zip] IV, SV, OCC, DEF
Human6
Human6 [zip]
SV, OCC, DEF, FM, OPR, OV
Human9
Human9 [zip]
IV, SV, DEF, MB, FM
Ironman
Ironman [zip]
IV, SV, OCC, MB, FM, IPR, OPR, OV, BC, LR
Jump
Jump [zip]
SV, OCC, DEF, MB, FM, IPR, OPR
Jumping
Jumping [zip]
MB, FM
Liquor
Liquor [zip]
IV, SV, OCC, MB, FM, OPR, OV, BC
Matrix
Matrix [zip]
IV, SV, OCC, FM, IPR, OPR, BC
MotorRolling
MotorRolling
[zip] IV, SV, MB, FM, IPR, BC, LR
Panda
Panda [zip]
SV, OCC, DEF, IPR, OPR, OV, LR
RedTeam
RedTeam [zip]
SV, OCC, IPR, OPR, LR
Shaking
Shaking [zip]
IV, SV, IPR, OPR, BC
Singer2
Singer2 [zip]
IV, DEF, IPR, OPR, BC
Skating1
Skating1 [zip]
IV, SV, OCC, DEF, OPR, BC
Skating2
Skating2 [1,2]
[zip] SV, OCC, DEF, FM, OPR
Skiing
Skiing [zip]
IV, SV, DEF, IPR, OPR
Soccer
Soccer [zip]
IV, SV, OCC, MB, FM, IPR, OPR, BC
Surfer
Surfer [zip]
SV, FM, IPR, OPR, LR
Sylvester
Sylvester [zip]
IV, IPR, OPR
Tiger2
Tiger2 [zip]
IV, OCC, DEF, MB, FM, IPR, OPR, OV
Trellis
Trellis [zip]
IV, SV, IPR, OPR, BC
Walking
Walking [zip]
SV, OCC, DEF
Walking2
Walking2 [zip]
SV, OCC, LR
Woman
Woman [zip]
IV, SV, OCC, DEF, MB, FM, OPR
The rest of TB-100 Sequences.
Bird2
Bird2 [zip]
OCC, DEF, FM, IPR, OPR
BlurCar1
BlurCar1 [zip]
MB, FM
BlurCar3
BlurCar3 [zip]
MB, FM
BlurCar4
BlurCar4 [zip]
MB, FM
Board
Board [zip]
SV, MB, FM, OPR, OV, BC
Bolt2
Bolt2 [zip]
DEF, BC
Boy
Boy [zip]
SV, MB, FM, IPR, OPR
Car2
Car2 [zip]
IV, SV, MB, FM, BC
Car24
Car24 [zip]
IV, SV, BC
Coke
Coke [zip]
IV, OCC, FM, IPR, OPR, BC
Coupon
Coupon [zip]
OCC, BC
Crossing
Crossing [zip]
SV, DEF, FM, OPR, BC
Dancer
Dancer [zip]
SV, DEF, IPR, OPR
Dancer2
Dancer2 [zip]
DEF
David2
David2 [zip]
IPR, OPR
David3
David3 [zip]
OCC, DEF, OPR, BC
Dog
Dog [zip]
SV, DEF, OPR
Dog1
Dog1 [zip]
SV, IPR, OPR
Doll
Doll [zip]
IV, SV, OCC, IPR, OPR
FaceOcc1
FaceOcc1 [zip]
OCC
FaceOcc2
FaceOcc2 [zip]
IV, OCC, IPR, OPR
Fish
Fish [zip]
IV
FleetFace
FleetFace [zip]
SV, DEF, MB, FM, IPR, OPR
Football1
Football1 [zip]
IPR, OPR, BC
Freeman1
Freeman1 [zip]
SV, IPR, OPR
Freeman3
Freeman3 [zip]
SV, IPR, OPR
Girl2
Girl2 [zip]
SV, OCC, DEF, MB, OPR
Gym
Gym [zip]
SV, DEF, IPR, OPR
Human2
Human2 [zip]
IV, SV, MB, OPR
Human5
Human5 [zip]
SV, OCC, DEF
Human7
Human7 [zip]
IV, SV, OCC, DEF, MB, FM
Human8
Human8 [zip]
IV, SV, DEF
Jogging
Jogging [1,2]
[zip] OCC, DEF, OPR
KiteSurf
KiteSurf [zip]
IV, OCC, IPR, OPR
Lemming
Lemming [zip]
IV, SV, OCC, FM, OPR, OV
Man
Man [zip]
IV
Mhyang
Mhyang [zip]
IV, DEF, OPR, BC
MountainBike
MountainBike
[zip] IPR, OPR, BC
Rubik
Rubik [zip]
SV, OCC, IPR, OPR
Singer1
Singer1 [zip]
IV, SV, OCC, OPR
Skater
Skater [zip]
SV, DEF, IPR, OPR
Skater2
Skater2 [zip]
SV, DEF, FM, IPR, OPR
Subway
Subway [zip]
OCC, DEF, BC
Suv
Suv [zip]
OCC, IPR, OV
Tiger1
Tiger1 [zip]
IV, OCC, DEF, MB, FM, IPR, OPR
Toy
Toy [zip]
SV, FM, IPR, OPR
Trans
Trans [zip]
IV, SV, OCC, DEF
Twinnings
Twinnings [zip]
SV, OPR
Vase
Vase [zip]
SV, FM, IPR

Attributes

We have manually tagged the test sequences with 9 attributes, which represents the challenging aspects in visual tracking.

NAME DESCRIPTION
IV Illumination Variation - the illumination in the target region is significantly changed.
Basketball, Box, Car1, Car2, Car24, Car4, CarDark, Coke, Crowds, David, Doll, FaceOcc2, Fish, Human2, Human4.2, Human7, Human8, Human9, Ironman, KiteSurf, Lemming, Liquor, Man, Matrix, Mhyang, MotorRolling, Shaking, Singer1, Singer2, Skating1, Skiing, Soccer, Sylvester, Tiger1, Tiger2, Trans, Trellis, Woman
SV Scale Variation – the ratio of the bounding boxes of the first frame and the current frame is out of the range [1/ts, ts], ts > 1 (ts=2).
Biker, BlurBody, BlurCar2, BlurOwl, Board, Box, Boy, Car1, Car24, Car4, CarScale, ClifBar, Couple, Crossing, Dancer, David, Diving, Dog, Dog1, Doll, DragonBaby, Dudek, FleetFace, Freeman1, Freeman3, Freeman4, Girl, Girl2, Gym, Human2, Human3, Human4.2, Human5, Human6, Human7, Human8, Human9, Ironman, Jump, Lemming, Liquor, Matrix, MotorRolling, Panda, RedTeam, Rubik, Shaking, Singer1, Skater, Skater2, Skating1, Skating2.1, Skating2.2, Skiing, Soccer, Surfer, Toy, Trans, Trellis, Twinnings, Vase, Walking, Walking2, Woman
OCC Occlusion – the target is partially or fully occluded.
Basketball, Biker, Bird2, Bolt, Box, CarScale, ClifBar, Coke, Coupon, David, David3, Doll, DragonBaby, Dudek, FaceOcc1, FaceOcc2, Football, Freeman4, Girl, Girl2, Human3, Human4.2, Human5, Human6, Human7, Ironman, Jogging.1, Jogging.2, Jump, KiteSurf, Lemming, Liquor, Matrix, Panda, RedTeam, Rubik, Singer1, Skating1, Skating2.1, Skating2.2, Soccer, Subway, Suv, Tiger1, Tiger2, Trans, Walking, Walking2, Woman
DEF Deformation – non-rigid object deformation.
Basketball, Bird1, Bird2, BlurBody, Bolt, Bolt2, Couple, Crossing, Crowds, Dancer, Dancer2, David, David3, Diving, Dog, Dudek, FleetFace, Girl2, Gym, Human3, Human4.2, Human5, Human6, Human7, Human8, Human9, Jogging.1, Jogging.2, Jump, Mhyang, Panda, Singer2, Skater, Skater2, Skating1, Skating2.1, Skating2.2, Skiing, Subway, Tiger1, Tiger2, Trans, Walking, Woman
MB Motion Blur – the target region is blurred due to the motion of target or camera.
Biker, BlurBody, BlurCar1, BlurCar2, BlurCar3, BlurCar4, BlurFace, BlurOwl, Board, Box, Boy, ClifBar, David, Deer, DragonBaby, FleetFace, Girl2, Human2, Human7, Human9, Ironman, Jump, Jumping, Liquor, MotorRolling, Soccer, Tiger1, Tiger2, Woman
FM Fast Motion – the motion of the ground truth is larger than tm pixels (tm=20).
Biker, Bird1, Bird2, BlurBody, BlurCar1, BlurCar2, BlurCar3, BlurCar4, BlurFace, BlurOwl, Board, Boy, CarScale, ClifBar, Coke, Couple, Deer, DragonBaby, Dudek, FleetFace, Human6, Human7, Human9, Ironman, Jumping, Lemming, Liquor, Matrix, MotorRolling, Skater2, Skating2.1, Skating2.2, Soccer, Surfer, Tiger1, Tiger2, Toy, Vase, Woman
IPR In-Plane Rotation – the target rotates in the image plane.
Bird2, BlurBody, BlurFace, BlurOwl, Bolt, Box, Boy, CarScale, ClifBar, Coke, Dancer, David, David2, Deer, Diving, Dog1, Doll, DragonBaby, Dudek, FaceOcc2, FleetFace, Football, Football1, Freeman1, Freeman3, Freeman4, Girl, Gym, Ironman, Jump, KiteSurf, Matrix, MotorRolling, MountainBike, Panda, RedTeam, Rubik, Shaking, Singer2, Skater, Skater2, Skiing, Soccer, Surfer, Suv, Sylvester, Tiger1, Tiger2, Toy, Trellis, Vase
OPR Out-of-Plane Rotation – the target rotates out of the image plane.
Basketball, Biker, Bird2, Board, Bolt, Box, Boy, CarScale, Coke, Couple, Dancer, David, David2, David3, Dog, Dog1, Doll, DragonBaby, Dudek, FaceOcc2, FleetFace, Football, Football1, Freeman1, Freeman3, Freeman4, Girl, Girl2, Gym, Human2, Human3, Human6, Ironman, Jogging.1, Jogging.2, Jump, KiteSurf, Lemming, Liquor, Matrix, Mhyang, MountainBike, Panda, RedTeam, Rubik, Shaking, Singer1, Singer2, Skater, Skater2, Skating1, Skating2.1, Skating2.2, Skiing, Soccer, Surfer, Sylvester, Tiger1, Tiger2, Toy, Trellis, Twinnings, Woman
OV Out-of-View – some portion of the target leaves the view.
Biker, Bird1, Board, Box, ClifBar, DragonBaby, Dudek, Human6, Ironman, Lemming, Liquor, Panda, Suv, Tiger2
BC Background Clutters – the background near the target has the similar color or texture as the target.
Basketball, Board, Bolt2, Box, Car1, Car2, Car24, CarDark, ClifBar, Couple, Coupon, Crossing, Crowds, David3, Deer, Dudek, Football, Football1, Human3, Ironman, Liquor, Matrix, Mhyang, MotorRolling, MountainBike, Shaking, Singer2, Skating1, Soccer, Subway, Trellis
LR Low Resolution – the number of pixels inside the ground-truth bounding box is less than tr (tr =400).
Biker, Car1, Freeman3, Freeman4, Panda, RedTeam, Skiing, Surfer, Walking

Visual trackers

We have tested 29 publicly available visual trackers. The trackers are listed in chronological order.

NAME CODE REFERENCE
CPF CPF P. Pe ́rez, C. Hue, J. Vermaak, and M. Gangnet. Color-Based Probabilistic Tracking. In ECCV, 2002.
KMS KMS D. Comaniciu, V. Ramesh, and P. Meer. Kernel-Based Object Tracking. PAMI, 25(5):564–577, 2003.
SMS SMS R. Collins. Mean-shift Blob Tracking through Scale Space. In CVPR, 2003.
VR-V VIVID/VR R. T. Collins, Y. Liu, and M. Leordeanu. Online Selection of Discriminative Tracking Features. PAMI, 27(10):1631–1643, 2005. [www]
* We also evaluated four other trackers included in the VIVID tracker suite. (PD-VRS-VMS-V, and TM-V).
Frag Frag A. Adam, E. Rivlin, and I. Shimshoni. Robust Fragments-based Tracking using the Integral Histogram. In CVPR, 2006. [www]
OAB OAB H. Grabner, M. Grabner, and H. Bischof. Real-Time Tracking via On-line Boosting. In BMVC, 2006. [www]
IVT IVT D. Ross, J. Lim, R.-S. Lin, and M.-H. Yang. Incremental Learning for Robust Visual Tracking. IJCV, 77(1):125–141, 2008. [www]
SemiT SBT H. Grabner, C. Leistner, and H. Bischof. Semi-supervised On-Line Boosting for Robust Tracking. In ECCV, 2008. [www]
MIL MIL B. Babenko, M.-H. Yang, and S. Belongie. Visual Tracking with Online Multiple Instance Learning. In CVPR, 2009. [www]
BSBT BSBT S. Stalder, H. Grabner, and L. van Gool. Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, but not Simpler than Recognition. In ICCV Workshop, 2009. [www]
TLD TLD Z. Kalal, J. Matas, and K. Mikolajczyk. P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints. In CVPR, 2010. [www]
VTD -- J. Kwon and K. M. Lee. Visual Tracking Decomposition. In CVPR, 2010. [www]
CXT CXT T. B. Dinh, N. Vo, and G. Medioni. Context Tracker: Exploring supporters and distracters in unconstrained environments. In CVPR, 2011. [www]
LSK LSK B. Liu, J. Huang, L. Yang, and C. Kulikowsk. Robust Tracking using Local Sparse Appearance Model and K-Selection. In CVPR, 2011. [www]
Struck Struck S. Hare, A. Saffari, and P. H. S. Torr. Struck: Structured Output Tracking with Kernels. In ICCV, 2011. [www]
VTS -- J. Kwon and K. M. Lee. Tracking by Sampling Trackers. In ICCV, 2011. [www]
ASLA ASLA X. Jia, H. Lu, and M.-H. Yang. Visual Tracking via Adaptive Structural Local Sparse Appearance Model. In CVPR, 2012. [www]
DFT DFT L. Sevilla-Lara and E. Learned-Miller. Distribution Fields for Tracking. In CVPR, 2012. [www]
L1APG L1APG C. Bao, Y. Wu, H. Ling, and H. Ji. Real Time Robust L1 Tracker Using Accelerated Proximal Gradient Approach. In CVPR, 2012. L1_Tracker">[www]
LOT LOT S. Oron, A. Bar-Hillel, D. Levi, and S. Avidan. Locally Orderless Tracking. In CVPR, 2012. [www]
MTT MTT T.Zhang, B. Ghanem,S. Liu,and N. Ahuja. Robust Visual Tracking via Multi-task Sparse Learning. In CVPR, 2012. [www]
ORIA ORIA Y. Wu, B. Shen, and H. Ling. Online Robust Image Alignment via Iterative Convex Optimization. In CVPR, 2012. [www]
SCM SCM W. Zhong, H. Lu, and M.-H. Yang. Robust Object Tracking via Sparsity-based Collaborative Model. In CVPR, 2012. [www]
CSK CSK F. Henriques, R. Caseiro, P. Martins, and J. Batista. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels. In ECCV, 2012. [www]
CT CT K. Zhang, L. Zhang, and M.-H. Yang. Real-time Compressive Tracking. In ECCV, 2012. [www]
LSHT LSHT S. He, Q. Yang, R. W. H. Lau, J. Wang, and M.-H. Yang. Visual Tracking via Locality Sensitive Histograms. In CVPR, 2013. [www]
LSS LSS D. Wang, H. Lu, and M.-H. Yang. Least Soft-thresold Squares Tracking. In CVPR, 2013.

Benchmark results

SRER evaluation results on the TB-50 dataset.
Each entry contains the average overlap in percent and the average number of failures in 1000 frames at the overlap threshold 0.5. The trackers are ordered by the average overlap scores, and the top 5 methods in each attribute are denoted by different colors: red, green, blue, cyan, and magenta.

  All BC DEF FM IPR IV LR MB OCC OPR OV SV
STRUCK   57.5/3.6   59.3/3.3   52.4/4.6   55.6/3.8   57.0/3.4   59.0/3.3   59.1/3.9   59.9/2.8   55.9/4.1   57.3/3.7   58.9/3.4   57.8/3.6
SCM   54.4/4.1   61.3/2.9   51.5/4.8   42.8/6.5   51.8/4.3   61.1/3.1   61.7/2.5   45.2/5.9   56.8/3.8   57.0/3.8   56.4/4.5   55.8/3.9
ASLA   53.2/4.1   59.2/3.0   50.5/4.5   42.0/6.5   52.1/4.1   59.6/3.0   59.3/2.3   44.6/5.9   56.0/3.8   56.3/3.7   55.3/4.3   54.0/3.9
CSK   52.4/4.9   55.9/4.2   48.1/5.7   45.8/5.8   52.4/4.7   56.2/4.3   55.0/4.8   50.6/5.1   52.7/5.1   53.3/4.9   53.2/4.9   52.0/5.0
L1APG   50.8/4.8   54.8/4.2   44.6/5.8   44.6/6.0   52.0/4.5   52.9/4.7   59.5/3.2   49.2/5.2   50.9/4.8   50.9/5.0   55.5/4.4   51.0/4.7
OAB   50.3/5.3   50.1/5.1   46.0/6.0   47.4/5.7   51.0/4.9   48.3/5.8   56.2/4.5   49.9/5.1   49.2/5.6   49.2/5.6   50.0/5.6   50.8/5.1
VTD   49.3/5.2   55.1/4.2   46.2/5.5   41.7/6.8   50.2/4.6   53.7/4.6   47.1/5.6   43.5/6.3   52.3/4.9   53.7/4.6   51.5/5.4   48.9/5.4
VTS   49.1/5.1   54.7/4.2   46.3/5.5   40.6/6.8   50.0/4.5   53.7/4.4   47.1/5.6   42.6/6.2   52.2/4.8   53.4/4.5   51.2/5.3   48.8/5.3
DFT   49.0/5.6   53.2/4.7   48.1/5.5   41.7/6.3   50.7/5.1   53.0/4.7   47.7/6.3   46.7/5.4   52.7/5.1   53.2/5.0   55.2/4.4   47.9/5.9
LSK   48.6/5.0   53.4/4.1   45.1/5.5   38.9/6.7   48.1/4.8   50.2/4.8   58.5/3.2   39.8/6.5   50.6/4.8   50.0/4.8   47.5/5.5   49.8/4.8
RS   48.4/5.6   48.6/5.1   50.5/5.3   46.7/6.3   47.0/5.8   47.6/5.4   44.5/5.8   46.4/6.0   52.2/5.0   51.9/4.9   53.2/5.0   47.9/5.7
MTT   48.3/5.2   50.7/4.9   40.1/6.6   40.6/6.8   51.5/4.4   50.2/5.0   57.8/3.6   45.5/6.2   47.3/5.5   48.2/5.3   50.4/5.6   48.2/5.3
LSHT   48.3/5.3   52.8/4.4   46.3/5.6   40.6/6.4   48.0/4.9   52.3/4.5   49.0/5.6   42.9/5.6   52.1/4.9   53.7/4.5   53.4/4.2   48.6/5.4
CXT   48.2/5.4   49.4/5.5   37.0/7.2   46.2/5.7   52.1/4.4   48.5/5.4   53.7/5.0   52.0/4.7   45.7/6.0   47.2/5.7   51.0/5.3   48.7/5.5
LSS   47.6/5.6   52.8/4.7   42.7/6.3   39.5/6.6   47.1/5.5   51.4/5.2   56.2/4.1   42.7/6.1   51.2/5.1   50.2/5.4   55.2/4.6   48.5/5.3
TLD   46.8/5.5   48.3/5.4   37.4/7.2   44.6/5.5   48.9/4.9   46.7/5.6   53.3/4.9   51.0/4.5   45.2/5.9   46.0/5.7   50.2/5.0   47.1/5.6
TM   46.7/6.0   49.4/5.4   40.2/6.6   44.8/6.2   47.2/5.7   45.7/6.2   55.6/4.8   48.1/5.5   46.8/5.8   46.3/6.1   52.6/5.1   47.6/5.8
PD   46.6/5.8   45.1/6.1   46.4/6.0   47.6/5.6   48.5/5.2   45.1/6.0   43.2/6.1   50.6/4.7   49.2/5.6   48.9/5.6   52.4/5.2   46.3/5.9
IVT   46.4/5.5   51.6/4.6   40.5/6.4   37.3/6.9   46.4/5.3   51.2/4.8   55.8/3.7   41.3/6.2   49.3/5.1   49.0/5.3   52.3/4.9   47.1/5.3
VR   45.9/6.0   44.8/6.2   45.3/6.2   47.1/5.9   47.9/5.5   43.7/6.4   42.4/6.0   49.7/5.3   48.1/5.9   48.2/5.9   50.8/5.5   45.8/6.2
MIL   45.9/6.1   48.6/5.3   45.7/5.9   44.1/6.5   45.7/5.9   47.1/5.6   43.5/6.8   43.7/6.3   47.6/5.8   48.9/5.7   52.7/5.1   44.5/6.5
LOT   45.5/5.9   48.6/5.2   42.4/6.5   47.1/5.5   43.2/6.3   45.4/5.8   38.1/6.1   46.9/5.3   49.5/5.2   48.5/5.5   49.2/4.8   45.6/5.8
FRAG   44.2/6.6   46.1/5.9   41.8/6.8   44.8/6.4   43.3/6.7   42.6/6.6   42.6/7.3   46.1/6.1   46.6/6.2   46.1/6.4   50.1/5.5   44.2/6.8
KMS   43.8/6.6   44.1/6.2   44.8/6.4   44.6/6.3   42.7/6.8   41.5/6.8   39.4/7.3   43.9/6.1   46.6/6.2   45.8/6.5   45.8/6.2   44.0/6.6
CPF   43.5/6.6   42.8/6.4   44.2/6.8   42.9/6.9   43.1/6.4   41.0/6.9   43.6/5.3   39.8/7.1   47.9/5.8   47.6/5.9   46.4/6.0   44.1/6.6
ORIA   42.4/6.4   47.6/5.9   34.8/7.8   32.8/7.6   44.9/5.5   46.9/5.9   50.8/4.4   36.8/7.3   44.4/6.3   44.9/6.1   46.9/6.2   43.4/6.3
CT   40.4/6.6   43.2/5.9   39.4/6.8   35.7/7.5   42.8/6.0   42.5/6.2   40.0/6.8   37.1/7.2   43.7/6.4   44.9/6.1   47.3/5.9   40.2/6.8
SBT   37.3/7.4   37.3/7.4   28.0/8.5   36.7/7.3   35.5/7.5   34.7/7.7   48.0/6.3   38.3/6.8   36.8/7.4   35.8/7.7   41.0/7.2   38.7/7.2
MS   35.6/7.9   36.7/7.4   32.8/8.0   40.5/7.1   36.8/7.8   34.6/7.8   28.4/9.2   41.2/6.8   37.4/7.7   37.3/7.9   41.0/6.9   36.0/7.9
BSBT   31.4/7.8   30.8/7.8   20.6/8.7   30.8/7.6   31.2/7.6   28.9/8.0   42.4/6.8   32.3/7.4   32.0/7.7   30.4/7.9   36.3/7.2   32.5/7.7
SMS   29.0/8.2   24.2/8.4   29.7/8.5   31.6/7.7   30.4/8.1   26.7/8.3   31.7/8.0   33.0/7.2   33.3/7.9   31.5/8.2   31.0/8.2   29.9/8.3


SRER (TB-50) OPE (50/100) SRE (50/100) TRE (50/100)
Overall

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
IV: Illumination Variation

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
SV: Scale Variation

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
OCC: Occlusion

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
DEF: Deformation

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
MB: Motion Blur

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
FM: Fast Motion

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
IPR: In-Plane Rotation

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
OPR: Out-of-Plane Rotation

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
OV: Out-of-View

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
BC: Background Clutter

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
LR: Low Resolution

[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
[pdf]
Locations of visitors to this page