|
AOC-MF (val)
|
Towards Robust Video Object Segmentation with Ada…
|
94.70
|
2022-07-02
|
|
|
ISVOS (BL30K, MS)
|
Look Before You Match: Instance Understanding Mat…
|
93.40
|
2022-12-13
|
|
|
XMem (BL30K, MS)
|
XMem: Long-Term Video Object Segmentation with an…
|
93.30
|
2022-07-14
|
|
|
BATMAN (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
92.50
|
2022-08-01
|
|
|
STCN (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
91.60
|
2022-08-01
|
|
|
XMem
|
XMem: Long-Term Video Object Segmentation with an…
|
91.50
|
2022-07-14
|
|
|
MobileVOS (val)
|
MobileVOS: Real-Time Video Object Segmentation Co…
|
91.40
|
2023-03-14
|
|
|
AOT (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
91.10
|
2022-08-01
|
|
|
LCM (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
90.70
|
2022-08-01
|
|
|
RPCMVOS (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
90.60
|
2022-08-01
|
|
|
KMN (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
90.50
|
2022-08-01
|
|
|
TransVOS (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
90.50
|
2022-08-01
|
|
|
CFBI+ (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
89.90
|
2022-08-01
|
|
|
STM (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
89.90
|
2022-08-01
|
|
|
ViTAE-T-Stage
|
ViTAE: Vision Transformer Advanced by Exploring I…
|
89.80
|
2021-06-07
|
|
|
CFBI (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
89.40
|
2022-08-01
|
|
|
RMN (val)
|
BATMAN: Bilateral Attention Transformer in Motion…
|
88.80
|
2022-08-01
|
|
|
3DC-Seg
|
Making a Case for 3D Convolutions for Object Segm…
|
84.70
|
2020-08-26
|
|
|
VOSwL (Mask+Language)
|
Video Object Segmentation with Language Referring…
|
84.50
|
2018-03-21
|
|
|
Ours
|
Learning Discriminative Feature with CRF for Unsu…
|
83.40
|
2020-08-04
|
|
|
VOSwL (Language)
|
Video Object Segmentation with Language Referring…
|
82.80
|
2018-03-21
|
|
|
DFNet
|
Learning Discriminative Feature with CRF for Unsu…
|
81.80
|
2020-08-04
|
|
|
LOCATE
|
LOCATE: Self-supervised Object Discovery via Flow…
|
80.90
|
2023-08-22
|
|
|
FODVid
|
FODVid: Flow-guided Object Discovery in Videos
|
78.71
|
2023-07-10
|
|