paper
-with-
me
Papers
Browse State-of-the-Art
Datasets
Methods
AI Agents
Trends
Digest
🌙
Video Object Segmentation
벤치마크
Video Object Segmentation on
M$^3$-VOS
8개 결과 ·
⬇ CSV
·
JSON
Average IOU
69.5
71.03
72.55
74.07
75.6
2022-07
2026-09
XMem — 70.4 (2022-07-14)
XMem — 70.4 (2022-07-14)
Cutie-base — 74.6 (2023-10-19)
Cutie-base — 74.6 (2023-10-19)
SAM 2 — 69.5 (2024-08-01)
SAM 2 — 69.5 (2024-08-01)
ReVOS — 75.6 (2025-06-15)
ReVOS — 75.6 (2025-06-15)
XMem — 70.4 (2022-07-14)
Cutie-base — 74.6 (2023-10-19)
ReVOS — 75.6 (2025-06-15)
2022-07-14 — XMem: Average IOU 70.4
2023-10-19 — Cutie-base: Average IOU 74.6
2025-06-15 — ReVOS: Average IOU 75.6
Rank
Model
Average IOU
Paper
Code
Year
1
ReVOS
75.6
M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation
zixuan-chen/M3VOS_Experiment
2025
2
Cutie-base
74.6
Putting the Object Back into Video Object Segmentation
hkchengrex/Cutie
2023
3
XMem
70.4
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
hkchengrex/XMem
·
tianyuan168326/videosemanticcompression-pytorch
2022
4
SAM 2
69.5
SAM 2: Segment Anything in Images and Videos
facebookresearch/segment-anything
·
facebookresearch/sam2
·
yangchris11/samurai
·
+8
2024
5
ReVOS
75.6
M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation
zixuan-chen/M3VOS_Experiment
2025
6
Cutie-base
74.6
Putting the Object Back into Video Object Segmentation
hkchengrex/Cutie
2023
7
XMem
70.4
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
hkchengrex/XMem
·
tianyuan168326/videosemanticcompression-pytorch
2022
8
SAM 2
69.5
SAM 2: Segment Anything in Images and Videos
facebookresearch/segment-anything
·
facebookresearch/sam2
·
yangchris11/samurai
·
+8
2024
1–8 / 8
페이지당
10
20
50
100