STEP-ICCV21 Results

Click on a measure to sort the table accordingly. See below for a more detailed description.



Benchmark Statistics

TrackerSTQAQSQ (IoU)Hz
IPL_ETRI
1.
48.6 43.3 54.5 9.5
EffPS_MM
2. online method
42.8 26.4 69.2 1.9
R. Mohan, A. Valada. Efficientps: Efficient panoptic segmentation. In International Journal of Computer Vision, 2021.
EffPS_MM
3. online method
42.8 26.4 69.2 1.9
R. Mohan, A. Valada. Efficientps: Efficient panoptic segmentation. In International Journal of Computer Vision, 2021.
siain
4. online method
31.8 15.4 65.7 3.2
SequencesFrames
2950

Difficulty Analysis

Sequence difficulty (from easiest to hardest, measured by average STQ)

STEP-ICCV21-01

STEP-ICCV21-01

(49.4 STQ)

STEP-ICCV21-07

STEP-ICCV21-07

(34.6 STQ)


Evaluation Measures

Lower is better. Higher is better.
Measure Better Perfect Description
STQ higher 100%Segmentation and Tracking Quality [1]. The geometric mean of Association Quality and Segmentation Quality.
AQ higher 100%Association Quality [1]. The class-agnostic Association Quality.
SQ (IoU) higher 100%Segmentation Quality [1]. The mean IoU of the semantic segmentation.
Hz higher Inf.Processing speed (in frames per second excluding the detector) on the benchmark. The frequency is provided by the authors and not officially evaluated by the MOTChallenge.

Legend

Symbol Description
online method 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.
using public detections This method used the provided detection set as input.
using private detections This method used a private detection set as input.
new This entry has been submitted or updated less than a week ago.

References:


[1] Weber, M., Xie, J., Collins, M., Zhu, Y., Voigtlaender, P., Adam, H., Green, B., Geiger, A., Leibe, B., Cremers, D., Osep, A., Leal-Taixe, L. & Chen, L.C. STEP: Segmenting and Tracking Every Pixel. arXiv:2102.11859, 2021.