RefVOS + SynthRef-YouTube-VIS

Reported on 4 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 Vision4 results

Instance SegmentationonDAVIS 2017 (val)
J&F 1st frame· uses extra data· 2021-06-08
45.3
best: 72.5 (UNINEXT-H)
SOTA
SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation arXiv:2106.04403
Referring Expression SegmentationonDAVIS 2017 (val)
J&F 1st frame· uses extra data· 2021-06-08
45.3
best: 72.5 (UNINEXT-H)
SOTA
SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation arXiv:2106.04403
Instance SegmentationonDAVIS 2017 (val)
J&F Full video· uses extra data· 2021-06-08
44.8
best: 59.4 (UniVS(Swin-L))
SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation arXiv:2106.04403
Referring Expression SegmentationonDAVIS 2017 (val)
J&F Full video· uses extra data· 2021-06-08
44.8
best: 59.4 (UniVS(Swin-L))
SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation arXiv:2106.04403