ResNet101-RNN

Reported on 4 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Computer Vision3 results

Scene ParsingonSUN-RGBD
Accuracy (%)· 2020-04-26
60.7
best: 67.2 (OMNIVORE (Swin-B))
SOTA
When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition arXiv:2004.12349
AnimationonSUN-RGBD
Accuracy (%)· 2020-04-26
60.7
best: 67.2 (OMNIVORE (Swin-B))
SOTA
When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition arXiv:2004.12349
3D Character Animation From A Single PhotoonSUN-RGBD
Accuracy (%)· 2020-04-26
60.7
best: 67.2 (OMNIVORE (Swin-B))
SOTA
When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition arXiv:2004.12349

Audio1 result

2D Semantic SegmentationonSUN-RGBD
Accuracy (%)· 2020-04-26
60.7
best: 67.2 (OMNIVORE (Swin-B))
SOTA
When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition arXiv:2004.12349