| 1 | SAM2 | 90.7 | Yes | SAM 2: Segment Anything in Images and Videos | 2024-08-01 | Code |
| 2 | Cutie+ (base) | 90.5 | Yes | Putting the Object Back into Video Object Segmen... | 2023-10-19 | Code |
| 3 | ISVOS (BL30K, MS) | 89.8 | Yes | Look Before You Match: Instance Understanding Ma... | 2022-12-13 | - |
| 4 | XMem (BL30K, MS) | 89.5 | Yes | XMem: Long-Term Video Object Segmentation with a... | 2022-07-14 | Code |
| 5 | ISVOS (MS) | 88.6 | Yes | Look Before You Match: Instance Understanding Ma... | 2022-12-13 | - |
| 6 | XMem (MS) | 88.2 | Yes | XMem: Long-Term Video Object Segmentation with a... | 2022-07-14 | Code |
| 7 | ISVOS (BL30K) | 88.2 | Yes | Look Before You Match: Instance Understanding Ma... | 2022-12-13 | - |
| 8 | Cutie+ (base, MEGA) | 88.1 | Yes | Putting the Object Back into Video Object Segmen... | 2023-10-19 | Code |
| 9 | JIMD | 88.1 | No | Memory Matching is not Enough: Jointly Improving... | 2024-09-22 | - |
| 10 | Cutie (base) | 87.9 | No | Putting the Object Back into Video Object Segmen... | 2023-10-19 | Code |
| 11 | XMem (BL30K) | 87.7 | Yes | XMem: Long-Term Video Object Segmentation with a... | 2022-07-14 | Code |
| 12 | DEVA | 87.6 | Yes | Tracking Anything with Decoupled Video Segmentat... | 2023-09-07 | Code |
| 13 | SwinB-AOTv2-L (MS) | 87 | No | Scalable Video Object Segmentation with Identifi... | 2022-03-22 | Code |
| 14 | SwinB-AOST (L'=3, MS) | 86.7 | No | Scalable Video Object Segmentation with Identifi... | 2022-03-22 | Code |
| 15 | SwinB-AOTv2-L | 86.3 | No | Scalable Video Object Segmentation with Identifi... | 2022-03-22 | Code |
| 16 | SwinB-DeAOT-L | 86.2 | No | Decoupling Features in Hierarchical Propagation ... | 2022-10-18 | Code |
| 17 | XMem | 86.2 | Yes | XMem: Long-Term Video Object Segmentation with a... | 2022-07-14 | Code |
| 18 | RAVOS | 86.1 | Yes | Region Aware Video Object Segmentation with Deep... | 2022-07-21 | - |
| 19 | R50-AOST (L'=3) | 85.6 | No | Scalable Video Object Segmentation with Identifi... | 2022-03-22 | Code |
| 20 | QDMN | 85.6 | Yes | Learning Quality-aware Dynamic Memory for Video ... | 2022-07-16 | Code |
| 21 | SwinB-AOT-L | 85.4 | No | Associating Objects with Transformers for Video ... | 2021-06-04 | Code |
| 22 | R50-AOST (L'=2) | 85.3 | No | Scalable Video Object Segmentation with Identifi... | 2022-03-22 | Code |
| 23 | STCN | 85.3 | Yes | Rethinking Space-Time Networks with Improved Mem... | 2021-06-09 | Code |
| 24 | TarViS | 85.3 | Yes | TarViS: A Unified Approach for Target-based Vide... | 2023-01-06 | Code |
| 25 | R50-DeAOT-L | 85.2 | No | Decoupling Features in Hierarchical Propagation ... | 2022-10-18 | Code |
| 26 | R50-AOT-L | 84.9 | No | Associating Objects with Transformers for Video ... | 2021-06-04 | Code |
| 27 | HMMN | 84.7 | Yes | Hierarchical Memory Matching Network for Video O... | 2021-09-23 | Code |
| 28 | MiVOS | 84.5 | Yes | Modular Interactive Video Object Segmentation: I... | 2021-03-14 | Code |
| 29 | XMem (DAVIS and YouTubeVOS only) | 84.5 | Yes | XMem: Long-Term Video Object Segmentation with a... | 2022-07-14 | Code |
| 30 | DeAOT-L | 84.1 | No | Decoupling Features in Hierarchical Propagation ... | 2022-10-18 | Code |
| 31 | AOT-L | 83.8 | No | Associating Objects with Transformers for Video ... | 2021-06-04 | Code |
| 32 | RPCMVOS | 83.7 | No | Reliable Propagation-Correction Modulation for V... | 2021-12-06 | Code |
| 33 | R50-AOST (L'=1) | 83.7 | No | Scalable Video Object Segmentation with Identifi... | 2022-03-22 | Code |
| 34 | RMNet | 83.5 | No | Efficient Regional Memory Network for Video Obje... | 2021-03-24 | Code |
| 35 | CFBI+ | 82.9 | No | Collaborative Video Object Segmentation by Multi... | 2020-10-13 | Code |
| 36 | KMN | 82.8 | No | Kernelized Memory Network for Video Object Segme... | 2020-07-16 | Code |
| 37 | AOT-B | 82.5 | No | Associating Objects with Transformers for Video ... | 2021-06-04 | Code |
| 38 | MobileVOS (BL30K) | 82.3 | Yes | MobileVOS: Real-Time Video Object Segmentation C... | 2023-03-14 | - |
| 39 | DeAOT-B | 82.2 | No | Decoupling Features in Hierarchical Propagation ... | 2022-10-18 | Code |
| 40 | CFBI | 81.9 | No | Collaborative Video Object Segmentation by Foreg... | 2020-03-18 | Code |
| 41 | STM | 81.75 | Yes | Video Object Segmentation using Space-Time Memor... | 2019-04-01 | Code |
| 42 | AOT-S | 81.3 | No | Associating Objects with Transformers for Video ... | 2021-06-04 | Code |
| 43 | DeAOT-S | 80.8 | No | Decoupling Features in Hierarchical Propagation ... | 2022-10-18 | Code |
| 44 | DeAOT-T | 80.5 | No | Decoupling Features in Hierarchical Propagation ... | 2022-10-18 | Code |
| 45 | MobileVOS | 80.2 | No | MobileVOS: Real-Time Video Object Segmentation C... | 2023-03-14 | - |
| 46 | AOT-T | 79.9 | No | Associating Objects with Transformers for Video ... | 2021-06-04 | Code |
| 47 | JOINT | 78.6 | No | Joint Inductive and Transductive Learning for Vi... | 2021-08-08 | Code |
| 48 | PReMVOS | 77.85 | No | PReMVOS: Proposal-generation, Refinement and Mer... | 2018-07-24 | Code |
| 49 | SSM-VOS | 77.6 | No | - | - | Code |
| 50 | LSMVOS | 77.4 | No | LSMVOS: Long-Short-Term Similarity Matching for ... | 2020-09-02 | Code |
| 51 | SWEM | 77.2 | No | SWEM: Towards Real-Time Video Object Segmentatio... | 2022-08-22 | Code |
| 52 | e-OSVOS | 77.2 | Yes | Make One-Shot Video Object Segmentation Efficien... | 2020-12-03 | Code |
| 53 | XMem (DAVIS only) | 76.7 | No | XMem: Long-Term Video Object Segmentation with a... | 2022-07-14 | Code |
| 54 | MHP-VOS | 76.15 | No | MHP-VOS: Multiple Hypotheses Propagation for Vid... | 2019-04-17 | Code |
| 55 | PTSNet | 74.65 | No | Proposal, Tracking and Segmentation (PTS): A Cas... | 2019-07-02 | Code |
| 56 | AFB-URR | 74.6 | No | Video Object Segmentation with Adaptive Feature ... | 2020-10-15 | Code |
| 57 | DEVA (EntitySeg) | 73.4 | Yes | Tracking Anything with Decoupled Video Segmentat... | 2023-09-07 | Code |
| 58 | TVOS | 72.3 | No | A Transductive Approach for Video Object Segment... | 2020-04-15 | Code |
| 59 | AGAME | 71.05 | No | A Generative Appearance Model for End-to-end Vid... | 2018-11-28 | Code |
| 60 | CINM | 70.6 | No | CNN in MRF: Video Object Segmentation via Infere... | 2018-03-26 | - |
| 61 | Siam R-CNN | 70.55 | No | Siam R-CNN: Visual Tracking by Re-Detection | 2019-11-28 | Code |
| 62 | Propose-Reduce | 70.4 | Yes | Video Instance Segmentation with a Propose-Reduc... | 2021-03-25 | Code |
| 63 | MAMP | 69.7 | No | Self-Supervised Video Object Segmentation by Mot... | 2021-07-27 | Code |
| 64 | Araslanov et al. | 69.4 | No | Dense Unsupervised Learning for Video Segmentation | 2021-11-11 | Code |
| 65 | OSVOS-S | 68 | No | Video Object Segmentation Without Temporal Infor... | 2017-09-18 | - |
| 66 | UnOVOST | 67.9 | No | UnOVOST: Unsupervised Offline Video Object Segme... | 2020-01-15 | Code |
| 67 | RGMP | 66.7 | No | - | - | Code |
| 68 | AGSS-VOS | 66.6 | No | - | - | Code |
| 69 | RANet | 65.7 | No | RANet: Ranking Attention Network for Fast Video ... | 2019-08-19 | Code |
| 70 | MAST | 65.5 | No | MAST: A Memory-Augmented Self-supervised Tracker | 2020-02-18 | Code |
| 71 | MAST | 65.5 | Yes | MAST: A Memory-Augmented Self-supervised Tracker | 2020-02-18 | Code |
| 72 | OnAVOS | 65.35 | No | Online Adaptation of Convolutional Neural Networ... | 2017-06-28 | - |
| 73 | STEm-Seg | 64.7 | Yes | STEm-Seg: Spatio-temporal Embeddings for Instanc... | 2020-03-18 | Code |
| 74 | VideoMatch | 62.4 | No | VideoMatch: Matching based Video Object Segmenta... | 2018-09-04 | - |
| 75 | Spatiotemporal CNN | 61.65 | No | Spatiotemporal CNN for Video Object Segmentation | 2019-04-04 | Code |
| 76 | VOSwL (Language) | 60.8 | No | Video Object Segmentation with Language Referrin... | 2018-03-21 | - |
| 77 | RVOS | 60.55 | No | RVOS: End-to-End Recurrent Network for Video Obj... | 2019-03-13 | Code |
| 78 | OSVOS | 60.25 | No | One-Shot Video Object Segmentation | 2016-11-16 | Code |
| 79 | UVC | 59.5 | No | Joint-task Self-supervised Learning for Temporal... | 2019-09-26 | Code |
| 80 | MATNet | 58.6 | No | - | - | Code |
| 81 | ALBA | 58.4 | No | ALBA : Reinforcement Learning for Video Object S... | 2020-05-26 | Code |
| 82 | FAVOS | 58.2 | No | Fast and Accurate Online Video Object Segmentati... | 2018-06-06 | Code |
| 83 | AGS | 57.5 | Yes | - | - | Code |
| 84 | SiamMask | 56.4 | No | Fast Online Object Tracking and Segmentation: A ... | 2018-12-12 | Code |
| 85 | MuG-W | 56.05 | No | Learning Video Object Segmentation from Unlabele... | 2020-03-10 | Code |
| 86 | PDB | 55.1 | No | - | - | - |
| 87 | OSMN | 54.8 | No | Efficient Video Object Segmentation via Network ... | 2018-02-04 | Code |
| 88 | CorrFlow | 50.3 | No | Self-supervised Learning for Video Correspondenc... | 2019-05-02 | Code |
| 89 | CycleTime | 48.7 | No | Learning Correspondence from the Cycle-Consisten... | 2019-03-18 | Code |
| 90 | RVOS | 41.2 | No | RVOS: End-to-End Recurrent Network for Video Obj... | 2019-03-13 | Code |