I3D-50 + LSTM

Reported on 6 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Computer Vision6 results

VideoonCATER
L1· 2017-05-22
1.2
SOTA
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750
VideoonCATER
Top 1 Accuracy· 2017-05-22
60.2
best: 90.7 (Loci)
SOTA
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750
VideoonCATER
Top 5 Accuracy· 2017-05-22
81.8
best: 98.5 (Loci)
SOTA
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750
Object TrackingonCATER
L1· 2017-05-22
1.2
SOTA
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750
Object TrackingonCATER
Top 1 Accuracy· 2017-05-22
60.2
best: 90.7 (Loci)
SOTA
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750
Object TrackingonCATER
Top 5 Accuracy· 2017-05-22
81.8
best: 98.5 (Loci)
SOTA
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset arXiv:1705.07750