HAF+BoW/FV halluc.

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 ParsingonYUP++
Accuracy (%)· uses extra data· 2019-06-13
92.6
best: 94.4 (DEEP-HAL with ODF+SDF (I3D))
SOTA
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs arXiv:1906.05910
AnimationonYUP++
Accuracy (%)· uses extra data· 2019-06-13
92.6
best: 94.4 (DEEP-HAL with ODF+SDF (I3D))
SOTA
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs arXiv:1906.05910
3D Character Animation From A Single PhotoonYUP++
Accuracy (%)· uses extra data· 2019-06-13
92.6
best: 94.4 (DEEP-HAL with ODF+SDF (I3D))
SOTA
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs arXiv:1906.05910

Audio1 result

2D Semantic SegmentationonYUP++
Accuracy (%)· uses extra data· 2019-06-13
92.6
best: 94.4 (DEEP-HAL with ODF+SDF (I3D))
SOTA
Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition with CNNs arXiv:1906.05910