CFBI (val)

Reported on 6 benchmarks across 2 tasks · 1 paper

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

Computer Vision6 results

VideoonDAVIS 2016
F-Score· 2022-08-01
90.5
best: 94.7 (AOC-MF (val))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2016
J&F· 2022-08-01
89.4
best: 93.4 (ISVOS (BL30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
VideoonDAVIS 2016
Jaccard (Mean)· 2022-08-01
88.3
best: 92.5 (ISVOS (BL30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2016
F-Score· 2022-08-01
90.5
best: 94.7 (AOC-MF (val))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2016
J&F· 2022-08-01
89.4
best: 93.4 (ISVOS (BL30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159
Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2022-08-01
88.3
best: 92.5 (ISVOS (BL30K, MS))
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation arXiv:2208.01159