Aloe

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

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

Computer Vision6 results

VideoonCATER
Top 5 Accuracy· 2020-12-15
94
best: 98.5 (Loci)
SOTA
Attention over learned object embeddings enables complex visual reasoning arXiv:2012.08508
Object TrackingonCATER
Top 5 Accuracy· 2020-12-15
94
best: 98.5 (Loci)
SOTA
Attention over learned object embeddings enables complex visual reasoning arXiv:2012.08508
VideoonCATER
L1· 2020-12-15
0.44
best: 1.2 (I3D-50 + LSTM)
Attention over learned object embeddings enables complex visual reasoning arXiv:2012.08508
VideoonCATER
Top 1 Accuracy· 2020-12-15
74
best: 90.7 (Loci)
Attention over learned object embeddings enables complex visual reasoning arXiv:2012.08508
Object TrackingonCATER
L1· 2020-12-15
0.44
best: 1.2 (I3D-50 + LSTM)
Attention over learned object embeddings enables complex visual reasoning arXiv:2012.08508
Object TrackingonCATER
Top 1 Accuracy· 2020-12-15
74
best: 90.7 (Loci)
Attention over learned object embeddings enables complex visual reasoning arXiv:2012.08508