Deep-Manta

Reported on 3 benchmarks across 3 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision1 result

Pose EstimationonKITTI Cars Hard
Average Orientation Similarity· uses extra data· 2017-03-22
80.39
best: 80.96 (Ego-Net (Monocular RGB only))
SOTA
Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image arXiv:1703.07570

Methodology1 result

3DonKITTI Cars Hard
Average Orientation Similarity· uses extra data· 2017-03-22
80.39
best: 80.96 (Ego-Net (Monocular RGB only))
SOTA
Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image arXiv:1703.07570

Audio1 result

1 Image, 2*2 StitchionKITTI Cars Hard
Average Orientation Similarity· uses extra data· 2017-03-22
80.39
best: 80.96 (Ego-Net (Monocular RGB only))
SOTA
Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image arXiv:1703.07570