Putting the Object Back into Video Object Segmentation | ✓ Link | 87.5 | 86.6 | 82.2 | 91.0 | 90.1 | | | 17.9 | Cutie+ (base, MEGA) | 2023-10-19 |
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 86.9 | 85.6 | 81.7 | 90.3 | 90.2 | | | | XMem (BL30K, MS) | 2022-07-14 |
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 86.7 | 85.3 | 81.7 | 89.9 | 89.9 | | | | XMem (MS) | 2022-07-14 |
Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 86.5 | 85.6 | 80.7 | 90.7 | 88.9 | | 65.6 | 0.7 | SwinB-AOTv2-L (all frames, MS) | 2022-03-22 |
Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 86.2 | 85.6 | 80.0 | 90.6 | 88.4 | | 70.3 | 11.9 | SwinB-DeAOT-L | 2022-10-18 |
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 86.1 | 85.1 | 80.3 | 89.8 | 89.2 | 22.6 | | | XMem (BL30K) | 2022-07-14 |
Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 86.0 | 84.9 | 80.4 | 89.9 | 88.7 | | 19.8 | 22.4 | R50-DeAOT-L | 2022-10-18 |
Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 85.8 | | 79.6 | 90.1 | 88.2 | | | 5.1 | SwinB-AOTv2-L (all frames) | 2022-03-22 |
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 85.7 | 84.6 | 80.2 | 89.3 | 88.7 | 22.6 | | | XMem | 2022-07-14 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 85.5 | 84.5 | 79.6 | 89.5 | 88.2 | 6.4 | 14.9 | | R50-AOT-L (all frames) | 2021-06-04 |
Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 85.4 | 85.1 | 78.9 | 90.2 | 87.3 | | 15.1 | 6.3 | R50-AOTv2-L (all frames) | 2022-03-22 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 85.1 | 85.1 | 78.4 | 90.1 | 86.9 | 5.2 | 65.4 | | SwinB-AOT-L (all frames) | 2021-06-04 |
Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 85.0 | 83.8 | 79.3 | 88.8 | 87.9 | | 15.4 | 14.9 | R50-AOST (L'=3) | 2022-03-22 |
Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 84.8 | 84.2 | 78.6 | 89.4 | | | | 24.7 | DeAOT-L | 2022-10-18 |
Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 84.6 | 83.9 | 78.5 | 88.9 | 87.0 | | 13.2 | 30.4 | DeAOT-B | 2022-10-18 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 84.5 | 84.3 | 77.9 | 89.3 | 86.4 | 9.3 | 65.4 | | SwinB-AOT-L | 2021-06-04 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 84.5 | 83.7 | 78.4 | 88.8 | 87.1 | 6.5 | 8.3 | | AOT-L (all frames) | 2021-06-04 |
Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 84.5 | 83.5 | 78.8 | 88.5 | 87.2 | | 13.9 | 20.2 | R50-AOST (L'=2) | 2022-03-22 |
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 84.4 | 83.7 | 78.2 | 88.5 | 87.2 | 22.6 | | | XMem (YouTubeVOS only) | 2022-07-14 |
Region Aware Video Object Segmentation with Deep Motion Modeling | | 84.4 | 83.1 | 79.1 | 87.8 | 87.4 | 23 | | | RAVOS | 2022-07-21 |
Reliable Propagation-Correction Modulation for Video Object Segmentation | ✓ Link | 84.3 | 83.3 | 78.9 | 87.9 | 86.9 | | | | RPCMVOS-MS | 2021-12-06 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 84.1 | 83.7 | 78.1 | 88.5 | 86.1 | 14.9 | 14.9 | | R50-AOT-L | 2021-06-04 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 84.1 | 83.6 | 78.0 | 88.5 | 86.5 | 20.5 | 8.3 | | AOT-B (all frames) | 2021-06-04 |
Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 84.0 | 83.3 | 77.9 | 88.3 | 86.6 | | 10.2 | 38.7 | DeAOT-S | 2022-10-18 |
Reliable Propagation-Correction Modulation for Video Object Segmentation | ✓ Link | 84 | 83.1 | | 87.7 | 86.7 | | | 78.5 | RPCMVOS | 2021-12-06 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 83.8 | 82.9 | 77.7 | 87.9 | 86.5 | 16.0 | 8.3 | | AOT-L | 2021-06-04 |
Learning Quality-aware Dynamic Memory for Video Object Segmentation | ✓ Link | 83.8 | 82.7 | 78.4 | 87.5 | 86.4 | | | | QDMN | 2022-07-16 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 83.5 | 82.6 | 77.7 | 87.5 | 86.0 | 20.5 | 8.3 | | AOT-B | 2021-06-04 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 83.0 | 82.2 | 77.3 | 87.0 | 85.7 | 27.1 | 7.9 | | AOT-S (all frames) | 2021-06-04 |
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration | ✓ Link | 82.8 | 81.8 | 77.1 | 86.6 | 85.6 | 4.0 | | | CFBI+ | 2020-10-13 |
Hierarchical Memory Matching Network for Video Object Segmentation | ✓ Link | 82.6 | 82.1 | 76.8 | 87.0 | 84.6 | | | | HMMN | 2021-09-23 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 82.6 | 82.0 | 76.6 | 86.7 | 85.0 | 27.1 | 7.9 | | AOT-S | 2021-06-04 |
Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 82.0 | 81.6 | 75.8 | 86.3 | 84.2 | | 7.2 | 53.4 | DeAOT-T | 2022-10-18 |
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion | ✓ Link | 82.0 | 80.6 | 77.3 | 84.7 | 85.5 | | | | MiVOS | 2021-03-14 |
Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 81.6 | 81.4 | 75.5 | 86.1 | 83.5 | | 12.5 | 30.9 | R50-AOST (L'=1) | 2022-03-22 |
Efficient Regional Memory Network for Video Object Segmentation | ✓ Link | 81.5 | 82.1 | 75.7 | 85.7 | 82.4 | | | | RMNet | 2021-03-24 |
Kernelized Memory Network for Video Object Segmentation | ✓ Link | 81.4 | 81.4 | 75.3 | 85.6 | 83.3 | | | | KMN | 2020-07-16 |
Collaborative Video Object Segmentation by Foreground-Background Integration | ✓ Link | 81.4 | 81.1 | 75.3 | 85.8 | 83.4 | 3.4 | 66.3 | | CFBI | 2020-03-18 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 80.9 | 80.0 | 75.2 | 84.7 | 83.5 | 41.0 | 5.3 | | AOT-T (all frames) | 2021-06-04 |
Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 80.2 | 80.1 | 74.0 | 84.5 | 82.2 | 41.0 | 5.3 | | AOT-T | 2021-06-04 |
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement | ✓ Link | 79.6 | 78.8 | 74.1 | 83.1 | 82.6 | | | | AFB-URR | 2020-10-15 |
Learning Fast and Robust Target Models for Video Object Segmentation | ✓ Link | 72.1 | 72.3 | | 76.2 | 74.1 | 65.9 | | | FRTM | 2020-02-27 |
Make One-Shot Video Object Segmentation Efficient Again | ✓ Link | 71.4 | 71.7 | 74.3 | 66.0 | 73.8 | | | | e-OSVOS | 2020-12-03 |
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation | ✓ Link | 69.9 | 71.7 | | 75.8 | 70.4 | 61.4 | | | STM-cycle | 2020-10-23 |
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation | ✓ Link | 68.2 | 67.0 | 64.5 | 68.4 | 73.2 | | | | MAMP | 2021-07-27 |
Video Object Segmentation using Space-Time Memory Networks | ✓ Link | 68.2 | | | | | | | | STM | 2019-04-01 |
Separable Structure Modeling for Semi-supervised Video Object Segmentation | ✓ Link | 66.5 | 72.3 | 57.8 | 73.3 | 62.6 | 24.1 | | | SSM-VOS | 2021-02-18 |
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation | ✓ Link | 64.4 | 71.0 | | 70.0 | 61.2 | 55.5 | | | S2S | 2018-09-03 |
CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing | ✓ Link | 62.3 | 67.3 | 53.7 | 68.1 | 59.9 | 13.5 | | | CapsuleVOS | 2019-09-30 |
One-Shot Video Object Segmentation | ✓ Link | 58.8 | 59.8 | 54.2 | 60.5 | 60.7 | 0.10 | | | OSVOS | 2016-11-16 |
RVOS: End-to-End Recurrent Network for Video Object Segmentation | ✓ Link | 56.8 | 63.6 | | 67.2 | 51.0 | 45.5 | | | RVOS | 2019-03-13 |
Efficient Video Object Segmentation via Network Modulation | ✓ Link | 51.2 | 60.0 | 40.6 | 60.1 | 44.0 | 7.14 | | | OSMN | 2018-02-04 |
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation | ✓ Link | | 83.2 | 79.0 | 87.9 | 87.3 | | | | STCN | 2021-06-09 |