AGT: Adapted Graph Tracking


Video not available.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Rendering of new sequences is currently deactivated due to heavy load.

Benchmark:

MOT17 | MOT16 |

Short name:

AGT

Detector:

Public

Description:

graph tracking with self adapted weights.

Reference:

Alibaba DAMO Academy city-brain team

Last submitted:

August 17, 2020 (3 years ago)

Published:

August 13, 2020 at 21:08:56 CET

Submissions:

4

Project page / code:

n/a

Open source:

No

Hardware:

Tesla-V100 32 G, 2 Core

Runtime:

6.8 Hz

Benchmark performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT1774.666.557.11,029 (43.7)363 (15.4)30,300108,98480.793.853.161.757.578.567.278.183.61.74,005 (49.6)8,382 (103.9)

Detailed performance:

Sequence MOTA IDF1 HOTA MT ML FP FN Rcll Prcn AssA DetA AssRe AssPr DetRe DetPr LocA FAF ID Sw. Frag
MOT17-01-DPM58.049.143.91053832,28964.591.639.349.341.482.653.876.483.50.939108
MOT17-01-FRCNN58.049.143.91053832,28964.591.639.349.341.482.653.876.483.50.939108
MOT17-01-SDP58.049.143.91053832,28964.591.639.349.341.482.653.876.483.50.939108
MOT17-03-DPM89.377.466.613104,0286,94493.496.060.773.365.280.878.981.184.62.7246668
MOT17-03-FRCNN89.377.466.613104,0286,94493.496.060.773.365.280.878.981.184.62.7246668
MOT17-03-SDP89.377.466.613104,0286,94493.496.060.773.365.280.878.981.184.62.7246668
MOT17-06-DPM63.960.949.488415263,53370.094.045.953.455.566.657.677.382.90.4195273
MOT17-06-FRCNN63.960.949.488415263,53370.094.045.953.455.566.657.677.382.90.4195273
MOT17-06-SDP63.960.949.488415263,53370.094.045.953.455.566.657.677.382.90.4195273
MOT17-07-DPM64.251.243.82331,0544,83671.492.036.253.438.875.058.675.582.72.1151421
MOT17-07-FRCNN64.251.243.82331,0544,83671.492.036.253.438.875.058.675.582.72.1151421
MOT17-07-SDP64.251.243.82331,0544,83671.492.036.253.438.875.058.675.582.72.1151421
MOT17-08-DPM50.438.636.22171,7118,36460.488.229.845.232.474.050.073.082.22.7400575
MOT17-08-FRCNN50.438.636.22171,7118,36460.488.229.845.232.474.050.073.082.22.7400575
MOT17-08-SDP50.438.636.22171,7118,36460.488.229.845.232.474.050.073.082.22.7400575
MOT17-12-DPM56.463.350.427205953,13663.890.353.448.057.879.752.574.382.70.746179
MOT17-12-FRCNN56.463.350.427205953,13663.890.353.448.057.879.752.574.382.70.746179
MOT17-12-SDP56.463.350.427205953,13663.890.353.448.057.879.752.574.382.70.746179
MOT17-14-DPM49.852.639.643451,8037,22660.986.238.541.441.871.046.866.278.52.4258570
MOT17-14-FRCNN49.852.639.643451,8037,22660.986.238.541.441.871.046.866.278.52.4258570
MOT17-14-SDP49.852.639.643451,8037,22660.986.238.541.441.871.046.866.278.52.4258570

Raw data: