TransportNet

Reported on 8 benchmarks across 2 tasks

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

Computer Vision8 results

VideoonDAVIS 2016 val
F
85
best: 90.2 (DEVA (DIS))
VideoonDAVIS 2016 val
G
84.8
best: 88.9 (GSANet)
VideoonDAVIS 2016 val
J
84.5
best: 88.3 (GSANet)
VideoonFBMS test
J
78.7
best: 84.7 (FakeFlow)
Video Object SegmentationonDAVIS 2016 val
F
85
best: 90.2 (DEVA (DIS))
Video Object SegmentationonDAVIS 2016 val
G
84.8
best: 88.9 (GSANet)
Video Object SegmentationonDAVIS 2016 val
J
84.5
best: 88.3 (GSANet)
Video Object SegmentationonFBMS test
J
78.7
best: 84.7 (FakeFlow)