FRCNN+FPN-Res50+refined feature map+Crowdhuman

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Robots2 results

Autonomous VehiclesonCaltech
Reasonable Miss Rate· uses extra data· 2018-04-30
3.46
best: 24.8 (LDCF)
CrowdHuman: A Benchmark for Detecting Human in a Crowd arXiv:1805.00123
Autonomous VehiclesonCityPersons
Reasonable MR^-2· uses extra data· 2018-04-30
10.67
best: 15.5 (TLL)
CrowdHuman: A Benchmark for Detecting Human in a Crowd arXiv:1805.00123

Computer Vision2 results

Pedestrian DetectiononCaltech
Reasonable Miss Rate· uses extra data· 2018-04-30
3.46
best: 24.8 (LDCF)
CrowdHuman: A Benchmark for Detecting Human in a Crowd arXiv:1805.00123
Pedestrian DetectiononCityPersons
Reasonable MR^-2· uses extra data· 2018-04-30
10.67
best: 15.5 (TLL)
CrowdHuman: A Benchmark for Detecting Human in a Crowd arXiv:1805.00123