| Putting the Object Back into Video Object Segmentation | ✓ Link | 88.1 | 84.7 | | | 91.4 | | | 17.9 | Cutie+ (base, MEGA) | 2023-10-19 |
| Putting the Object Back into Video Object Segmentation | ✓ Link | 86.1 | 82.4 | | | 89.9 | | | 36.4 | Cutie (base, MEGA) | 2023-10-19 |
| Putting the Object Back into Video Object Segmentation | ✓ Link | 85.9 | 82.6 | | | 89.2 | | | 17.9 | Cutie+ (base) | 2023-10-19 |
| Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 84.7 | 80.9 | | | 88.5 | | | 1.3 | SwinB-AOST (L'=3, MS) | 2022-03-22 |
| Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 84.5 | 81.0 | | | 87.9 | | | 1.3 | SwinB-AOTv2-L | 2022-03-22 |
| Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation | | 83.9 | 80.3 | | | 87.4 | | | | JIMD-R50 | 2024-09-22 |
| XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 83.7 | 80.5 | | | 87.0 | | | | XMem (BL30K, MS) | 2022-07-14 |
| Tracking Anything with Decoupled Video Segmentation | ✓ Link | 83.2 | 79.6 | | | 86.8 | | | 25.3 | DEVA | 2023-09-07 |
| XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 83.1 | 79.7 | | | 86.4 | | | | XMem (MS) | 2022-07-14 |
| Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 82.8 | 78.9 | | | 86.7 | | | 15.4 | SwinB-DeAOT-L | 2022-10-18 |
| Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 82.7 | 78.8 | | | 86.6 | | | 12.0 | SwinB-AOST (L'=3) | 2022-03-22 |
| XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 82.5 | 79.1 | | | 85.8 | | | | XMem (BL30K, 600p) | 2022-07-14 |
| Learning Quality-aware Dynamic Memory for Video Object Segmentation | ✓ Link | 81.9 | 78.1 | | | 85.4 | | | | QDMN | 2022-07-16 |
| XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 81.2 | 77.6 | | | 84.7 | | | | XMem (BL30K) | 2022-07-14 |
| Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 81.2 | 77.3 | | | 85.1 | | | 12.1 | SwinB-AOT-L | 2021-06-04 |
| Reliable Propagation-Correction Modulation for Video Object Segmentation | ✓ Link | 81 | 77.6 | | | 84.3 | | | | RPCMVOS-Full-Res | 2021-12-06 |
| XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 81.0 | 77.4 | | | 84.5 | | | | XMem | 2022-07-14 |
| Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 80.7 | 76.9 | | | 84.5 | | | 27.0 | R50-DeAOT-L | 2022-10-18 |
| Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation | ✓ Link | 79.9 | 76.3 | 85.5 | 10.5 | 83.5 | 89.7 | 10.3 | | STCN | 2021-06-09 |
| Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 79.9 | 76.2 | | | 83.6 | | | 17.5 | R50-AOST (L'=3) | 2022-03-22 |
| XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model | ✓ Link | 79.8 | 76.3 | | | 83.4 | | | | XMem (DAVIS and YouTubeVOS only) | 2022-07-14 |
| Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 79.6 | 75.9 | | | 83.3 | | | 18.0 | R50-AOT-L | 2021-06-04 |
| Reliable Propagation-Correction Modulation for Video Object Segmentation | ✓ Link | 79.2 | 75.8 | | | 82.6 | | | | RPCMVOS | 2021-12-06 |
| Hierarchical Memory Matching Network for Video Object Segmentation | ✓ Link | 78.6 | 74.7 | | | 82.5 | | | | HMMN | 2021-09-23 |
| Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 78.3 | 74.3 | | | 82.3 | | | 18.7 | AOT-L | 2021-06-04 |
| Scalable Video Object Segmentation with Identification Mechanism | ✓ Link | 78.1 | 74.5 | | | 81.7 | | | 24.3 | R50-AOST (L'=2) | 2022-03-22 |
| Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration | ✓ Link | 78.0 | 74.4 | | | 81.6 | | | | CFBI+ | 2020-10-13 |
| Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 77.9 | 74.1 | | | 81.7 | | | 28.5 | DeAOT-L | 2022-10-18 |
| Kernelized Memory Network for Video Object Segmentation | ✓ Link | 77.2 | 74.1 | | | 80.3 | | | | KMN | 2020-07-16 |
| Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion | ✓ Link | 76.5 | 72.7 | 81.2 | 14.9 | 80.2 | 87.6 | 14.5 | | MiVOS | 2021-03-14 |
| Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 76.2 | 72.5 | | | 79.9 | | | 40.9 | DeAOT-B | 2022-10-18 |
| Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 75.5 | 71.6 | | | 79.3 | | | 29.6 | AOT-B | 2021-06-04 |
| Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 75.4 | 71.9 | | | 79.0 | | | 49.2 | DeAOT-S | 2022-10-18 |
| Efficient Regional Memory Network for Video Object Segmentation | ✓ Link | 75.0 | 71.9 | | | 78.1 | | | | RMNet | 2021-03-24 |
| Collaborative Video Object Segmentation by Foreground-Background Integration | ✓ Link | 74.8 | 71.1 | | | 78.5 | | | | CFBI | 2020-03-18 |
| Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 73.9 | 70.3 | | | 77.5 | | | 40.0 | AOT-S | 2021-06-04 |
| Decoupling Features in Hierarchical Propagation for Video Object Segmentation | ✓ Link | 73.7 | 70.0 | | | 77.3 | | | 63.5 | DeAOT-T | 2022-10-18 |
| Video Object Segmentation using Space-Time Memory Networks | ✓ Link | 72.2 | 69.3 | 78.0 | 16.9 | 75.2 | 83.0 | 17.5 | | STM | 2019-04-01 |
| Associating Objects with Transformers for Video Object Segmentation | ✓ Link | 72.0 | 68.3 | | | 75.7 | | | 51.4 | AOT-T | 2021-06-04 |
| PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation | ✓ Link | 71.6 | 67.5 | 76.8 | 21.7 | 75.8 | 84.3 | 20.6 | | PReMVOS | 2018-07-24 |
| MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation | ✓ Link | 69.5 | 66.4 | 76.0 | 18.0 | 72.7 | 82.3 | 19.1 | | MHP-VOS | 2019-04-17 |
| CNN in MRF: Video Object Segmentation via Inference in A CNN-Based Higher-Order Spatio-Temporal MRF | | 67.5 | 64.5 | 73.8 | 20.0 | 70.5 | 79.6 | 20.0 | | CINM | 2018-03-26 |
| LSMVOS: Long-Short-Term Similarity Matching for Video Object | ✓ Link | 67.4 | 63.7 | 72.7 | 16.9 | 71.2 | 81.4 | 16.5 | | LSMVOS | 2020-09-02 |
| Lucid Data Dreaming for Video Object Segmentation | ✓ Link | 66.6 | 63.4 | 74.0 | 19.5 | 69.9 | 80.1 | 19.5 | | Lucid | 2017-03-28 |
| Make One-Shot Video Object Segmentation Efficient Again | ✓ Link | 64.8 | 60.9 | | 22.1 | 68.6 | | | | e-OSVOS | 2020-12-03 |
| Separable Structure Modeling for Semi-supervised Video Object Segmentation | ✓ Link | 62.0 | 60.2 | | 23.5 | 63.8 | | 25.3 | | SSM-VOS | 2021-02-18 |
| FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation | ✓ Link | 57.8 | 55.1 | 62.6 | 29.8 | 60.9 | 68.5 | 33.5 | | FEELVOS | 2019-02-25 |
| Video Object Segmentation Without Temporal Information | | 57.5 | 52.9 | 60.2 | 24.1 | 62.1 | 70.5 | 21.9 | | OSVOS-S | 2017-09-18 |
| RANet: Ranking Attention Network for Fast Video Object Segmentation | ✓ Link | 55.4 | 53.4 | 61.9 | 21.9 | 57.3 | 67.7 | 22.1 | | RANet | 2019-08-19 |
| Siam R-CNN: Visual Tracking by Re-Detection | ✓ Link | 53.3 | 48.0 | 53.9 | 21.8 | 58.6 | 62.3 | 20.2 | | Siam R-CNN | 2019-11-28 |
| Fast Video Object Segmentation by Reference-Guided Mask Propagation | ✓ Link | 52.8 | 51.3 | 59.0 | 34.3 | 54.4 | 61.9 | 37.2 | | RGMP | 2018-06-01 |
| Online Adaptation of Convolutional Neural Networks for Video Object Segmentation | | 52.8 | 49.9 | 54.3 | 23.0 | | 60.3 | 23.4 | | OnAVOS | 2017-06-28 |
| A Generative Appearance Model for End-to-end Video Object Segmentation | ✓ Link | 52.3 | 49.2 | 53.2 | 28.9 | 55.3 | 61.1 | 27.6 | | AGAME | 2018-11-28 |
| CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing | ✓ Link | 51.3 | 47.4 | 54.1 | | 55.2 | 64.6 | | | CapsuleVOS | 2019-09-30 |
| One-Shot Video Object Segmentation | ✓ Link | 50.9 | 47.0 | 52.1 | 19.2 | | 59.7 | 19.8 | | OSVOS | 2016-11-16 |
| RVOS: End-to-End Recurrent Network for Video Object Segmentation | ✓ Link | 50.3 | 47.9 | 54.4 | 35.7 | 52.6 | 61.7 | 36.7 | | RVOS | 2019-03-13 |
| Fast and Accurate Online Video Object Segmentation via Tracking Parts | ✓ Link | 43.6 | 42.9 | 48.1 | 18.1 | 44.2 | 51.1 | 19.8 | | FAVOS | 2018-06-06 |
| Fast Online Object Tracking and Segmentation: A Unifying Approach | ✓ Link | 43.2 | 40.6 | 44.5 | 21.9 | 45.8 | 45.3 | 22.4 | | SiamMask | 2018-12-12 |
| Efficient Video Object Segmentation via Network Modulation | ✓ Link | 41.3 | 37.7 | 38.9 | 19.0 | | 47.4 | 17.4 | | OSMN | 2018-02-04 |