convSTAR

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Robots1 result

Activity RecognitiononJester (Gesture Recognition)
Val· 2019-11-25
92.7
best: 98.15 (DirecFormer)
Gating Revisited: Deep Multi-layer RNNs That Can Be Trained arXiv:1911.11033

Time Series1 result

Action RecognitiononJester (Gesture Recognition)
Val· 2019-11-25
92.7
best: 98.15 (DirecFormer)
Gating Revisited: Deep Multi-layer RNNs That Can Be Trained arXiv:1911.11033

Computer Vision1 result

Action Recognition In VideosonJester (Gesture Recognition)
Val· 2019-11-25
92.7
best: 96.7 (CPNet Res34, 5 CP)
Gating Revisited: Deep Multi-layer RNNs That Can Be Trained arXiv:1911.11033