Referring Video Object Segmentation on Ref-Youtube-VOS standard (val)
74.1J&F ScoreVideoSEG-O3-4B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VideoSEG-O3-4BMethod Category=MLLM-based Methods, Model Scale=4B2026.06 | 74.1 | 71.5 | 76.6 | |
| UniPixel-7BMethod Category=MLLM-based Methods, Model Scale=7B2026.06 | 71 | 69.5 | 72.4 | |
| VideoSEG-O3-2BMethod Category=MLLM-based Methods, Model Scale=2B2026.06 | 70.5 | 68.3 | 72.7 | |
| Sa2VA-8BMethod Category=MLLM-based Methods, Model Scale=8B2026.06 | 70 | — | — | |
| ReferDINOMethod Category=Specialized Methods2026.06 | 69.3 | 67 | 71.5 | |
| SAMWISEMethod Category=Specialized Methods2026.06 | 69.2 | 67.8 | 70.6 | |
| InstructSeg-3BMethod Category=MLLM-based Methods, Model Scale=3B2026.06 | 67.5 | 65.4 | 69.5 | |
| GLUS-7BMethod Category=MLLM-based Methods, Model Scale=7B2026.06 | 67.3 | 65.5 | 69 | |
| VideoLISA-3.8BMethod Category=MLLM-based Methods, Model Scale=3.8B2026.06 | 63.7 | 61.7 | 65.7 | |
| VISA-7BMethod Category=MLLM-based Methods, Model Scale=7B2026.06 | 61.5 | 59.8 | 63.2 | |
| LISA-7BMethod Category=MLLM-based Methods, Model Scale=7B2026.06 | 53.9 | 53.4 | 54.3 |