Cascaded-MTL

Reported on 5 benchmarks across 1 task · 1 paper · 4 SOTA

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

Computer Vision5 results

CrowdsonShanghaiTech B
MAE· 2017-07-30
20
best: 5.51 (EBC-ZIP-B)
SOTA
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting arXiv:1707.09605
CrowdsonShanghaiTech A
MAE· 2017-07-30
101.3
best: 47.81 (EBC-ZIP-B)
SOTA
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting arXiv:1707.09605
CrowdsonShanghaiTech A
MSE· 2017-07-30
152.4
best: 76.7 (APGCC)
SOTA
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting arXiv:1707.09605
CrowdsonUCF CC 50
MAE· 2017-07-30
322.8
best: 154.8 (APGCC)
SOTA
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting arXiv:1707.09605
CrowdsonUCF-QNRF
MAE· 2017-07-30
252
best: 69.46 (EBC-ZIP-B)
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting arXiv:1707.09605