Deformable Part-based Model

MOT17-01 MOT17-03 MOT17-06 MOT17-07 MOT17-08 MOT17-12 MOT17-14

Short name:

DPM

Benchmark:

Description:

At a high level DPM can be characterized by the combination of

* Strong low-level features based on histograms of oriented gradients (HOG)
* Efficient matching algorithms for deformable part-based models (pictorial structures)
* Discriminative learning with latent variables (latent SVM)

Hardware:

3GHz

Detector:

Public

Last submitted:

February 14, 2017 (1 year ago)

Published:

February 14, 2017 at 06:22:59 CET

Submissions:

3

Open source:

Yes

Project page / code:

Reference:

P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object Detection with Discriminatively Trained Part Based Models. In TPAMI, 2010.

Benchmark performance:

APSpecifications
0.613GHz

Detailed performance:

Sequence AP
MOT17-010.4304
MOT17-030.6929
MOT17-060.6197
MOT17-070.6646
MOT17-080.7906
MOT17-120.6216
MOT17-140.3418

Raw data:


DPM
ACF