Referring Video Segmentation on JHMDB Sentences (test)
45.8mAP (0.5:0.95)DsHmp
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| DsHmpBackbone=Video-Swin-Base2024.04 | 45.8 | — | — | — | — | — | 73.9 | 73 | |
| SgMgBackbone=Video-Swin-Base2024.04 | 45 | — | — | — | — | — | 73.7 | 72.5 | |
| DsHmpBackbone=Video-Swin-Tiny2024.04 | 44.9 | — | — | — | — | — | 73.1 | 72.1 | |
| CCMAVenue=ACMMM212022.07 | 44.7 | 86.9 | 80.5 | 61.4 | 16.7 | 0 | 70.2 | 64.9 | |
| SOCBackbone=Video-Swin-Base2024.04 | 44.6 | — | — | — | — | — | 73.6 | 72.3 | |
| SgMgBackbone=Video-Swin-Tiny2024.04 | 44.4 | — | — | — | — | — | 72.8 | 71.7 | |
| MANetVenue=This Paper2022.07 | 44.3 | 91.8 | 83.4 | 55.2 | 13.8 | 0 | 68.7 | 68.1 | |
| HTMLBackbone=Video-Swin-Base2024.04 | 44.2 | — | — | — | — | — | — | — | |
| ReferFormerBackbone=Video-Swin-Base2024.04 | 43.7 | — | — | — | — | — | 73 | 71.8 | |
| HTMLBackbone=Video-Swin-Tiny2024.04 | 42.7 | — | — | — | — | — | — | — | |
| SOCBackbone=Video-Swin-Tiny2024.04 | 42.7 | — | — | — | — | — | 72.7 | 71.6 | |
| ReferFormerBackbone=Video-Swin-Tiny2024.04 | 42.2 | — | — | — | — | — | 71.9 | 71 | |
| MTTRBackbone=Video-Swin-Tiny2024.04 | 39.2 | — | — | — | — | — | 70.1 | 69.8 | |
| MTTRVenue=CVPR222022.07 | 36.6 | 91 | 81.5 | 57 | 14.4 | 0.1 | 67.4 | 67.9 | |
| CMPC-VInput Modality=RGB, Evaluation Protocol=without finetuning2021.05 | 34.2 | 81.3 | 65.7 | 37.1 | 7 | 0 | 61.6 | 61.7 | |
| CMPC-VVenue=T-PAMI212022.07 | 34.2 | 81.3 | 65.7 | 37.1 | 7 | 0 | 61.6 | 61.7 | |
| CSTMVenue=CVPR212022.07 | 33.5 | 78.3 | 63.9 | 37.8 | 7.6 | 0 | 59.8 | 60.4 | |
| AAMNInput=RGB+Flow2020.11 | 32 | 78.5 | 63.4 | 34.6 | 3.8 | 0 | 59.3 | 59 | |
| CMDyInput=RGB+Flow2020.11 | 30.8 | 76.6 | 60 | 32.9 | 5 | 0 | 56.2 | 58 | |
| CMDyVenue=AAAI202022.07 | 30.1 | 74.2 | 58.7 | 31.6 | 4.7 | 0 | 55.4 | 57.6 | |
| CMDyInput=RGB2020.11 | 30.1 | 74.2 | 58.7 | 31.6 | 4.7 | 0 | 55.4 | 57.6 | |
| ACGAInput=RGB+Flow2020.11 | 29.5 | — | — | — | — | — | 57.9 | 59.1 | |
| PRPEEvaluation Protocol=without finetuning2021.05 | 29.4 | 69 | 57.2 | 31.9 | 6 | 0.1 | — | — | |
| PolarRPEVenue=IJCAI202022.07 | 29.4 | 69.1 | 57.2 | 31.9 | 6 | 0.1 | — | — | |
| ACGANetInput Modality=RGB, Evaluation Protocol=without finetuning2021.05 | 28.9 | 75.6 | 56.4 | 28.7 | 3.4 | 0 | 57.6 | 58.4 | |
| ACGAVenue=ICCV192022.07 | 28.9 | 75.6 | 56.4 | 28.7 | 3.4 | 0 | 57.6 | 58.4 | |
| ACGAInput=RGB2020.11 | 28.9 | 75.6 | 56.4 | 28.7 | 3.4 | 0 | 57.6 | 58.4 | |
| AAMNInput=RGB2020.11 | 27.8 | 74.6 | 57.3 | 25.6 | 1.5 | 0 | 55.6 | 56.3 | |
| VT-CapsuleVenue=CVPR202022.07 | 26.1 | 67.7 | 51.3 | 28.3 | 5.1 | 0 | 53.5 | 55 | |
| VT-CapsuleInput=RGB2020.11 | 26.1 | 67.7 | 51.3 | 28.3 | 5.1 | 0 | 53.5 | 55 | |
| Gavrilyuk et al.Input Modality=RGB+Flow, Evaluation Protocol=without finetuning2021.05 | 23.3 | 69.9 | 46 | 17.3 | 1.4 | 0 | 54.1 | 54.2 | |
| A2DSVenue=CVPR182022.07 | 23.3 | 69.9 | 46 | 17.3 | 1.4 | 0 | 54.1 | 54.2 | |
| Gavrilyuk et al.Input=RGB+Flow2020.11 | 23.3 | 69.9 | 46 | 17.3 | 1.4 | 0 | 54.1 | 54.2 | |
| Hu et al.Input=RGB2020.11 | 17.8 | 63.3 | 35 | 8.5 | 0.2 | 0 | 54.6 | 52.8 | |
| Li et al.Input=RGB2020.11 | 17.3 | 57.8 | 33.5 | 10.3 | 0.6 | 0 | 52.9 | 49.1 | |
| CMSA+CFSAVenue=T-PAMI212022.07 | — | 76.4 | 62.5 | 38.9 | 9 | 0.1 | 62.8 | 58.1 | |
| OnlineReferBackbone=Video-Swin-Base2024.04 | — | — | — | — | — | — | 73.5 | 71.9 |