| SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction | ✓ Link | 80.8 | | | SetCon | 2026-05-19 |
| ReVEAL: Eliciting Role-Aware Latent Visual Evidence from MLLMs for Reasoning Video Object Segmentation | ✓ Link | 80.7 | | | ReVEAL (Qwen3VL-8B) | 2026-10-30 |
| VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation | ✓ Link | 80.0 | | | VideoSEG-O3-2B | 2026-06-05 |
| VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation | ✓ Link | 79.5 | | | VIRST | 2026-03-28 |
| Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos | ✓ Link | 79.4 | | | Sa2VA-Qwen2.5VL-7B (extra data) | 2025-01-07 |
| VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation | ✓ Link | 79.4 | | | VideoSEG-O3-4B | 2026-06-05 |
| Unlocking Motion in Expressions: Temporal Calibration for Referring Video Object Segmentation | ✓ Link | 77.7 | 74.5 | 80.8 | EMC | 2026-08-17 |
| ReVEAL: Eliciting Role-Aware Latent Visual Evidence from MLLMs for Reasoning Video Object Segmentation | ✓ Link | 77.7 | | | ReVEAL (Qwen2.5VL-7B) | 2026-10-30 |
| Towards Streaming Referring Video Segmentation via Large Language Model | ✓ Link | 76.6 | | | StreamingRVOS-4B | 2026-06-03 |
| Video Generation Models are General-Purpose Vision Learners | | 76.4 | | | GenCeption Specialist-L | 2026-07-10 |
| Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory | | 76.0 | 73.2 | 78.8 | SDAM | 2026-03-02 |
| PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos | | 76.0 | | | PhysMLLMs | 2026-08-25 |
| Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation | ✓ Link | 75.2 | | | DecAF (training-free, Qwen2.5-VL-7B + SAM2) (extra data) | 2025-10-22 |
| ReferEverything: Towards Segmenting Everything We Can Speak of in Videos | | 75.0 | | | REM Wan-14B | 2024-10-30 |
| DTOS: Dynamic Time Object Sensing with Large Multimodal Model | ✓ Link | 74.88 | | | DTOS-9B | 2025-06-11 |
| ViLLa: Video Reasoning Segmentation with Large Language Model | ✓ Link | 74.3 | | | ViLLa (InternVideo2-6B) (extra data) | 2024-07-18 |
| Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation | ✓ Link | 74.2 | 69.9 | 78.5 | FindTrack | 2025-03-05 |
| STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation | ✓ Link | 73.6 | 70.1 | 77.2 | STAC | 2026-07-03 |
| Deforming Videos to Masks: Flow Matching for Referring Video Segmentation | ✓ Link | 73.3 | | | FlowRVS (Wan 2.1 T2V 1.3B DiT, zero-shot) (extra data) | 2025-10-07 |
| Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation | ✓ Link | 72.5 | | | GeoLaV | 2026-06-23 |
| G$^2$TAM: Geometry Grounded Track Anything Model | | 71.7 | 68.2 | 75.1 | G2TAM | 2026-07-04 |
| InterRVOS: Interaction-aware Referring Video Object Segmentation | ✓ Link | 71.6 | | | ReVIOSa-4B (standard RVOS, AML-only) (extra data) | 2025-06-03 |
| HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver | ✓ Link | 71.2 | | | HyperSeg-3B | 2025-06-11 |
| Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model | | 71.2 | 67.5 | 75.0 | HCD | 2025-08-19 |
| InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models | ✓ Link | 71.1 | | | InstructSeg (Mipha-3B) (extra data) | 2024-12-18 |
| SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation | ✓ Link | 70.6 | | | SAMWISE (Hiera-B + RoBERTa) (extra data) | 2024-11-26 |
| VISA: Reasoning Video Object Segmentation via Large Language Models | ✓ Link | 70.4 | | | VISA Chat-UniVi-13B (extra data) | 2024-07-16 |
| VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos | ✓ Link | 69.5 | | | VideoGLaMM (Phi-3 Mini 3.8B, RVOS fine-tuned) (extra data) | 2024-11-07 |
| Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation | ✓ Link | 69.4 | 66.2 | 72.6 | VD-IT | 2024-03-18 |
| One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos | ✓ Link | 68.8 | | | VideoLISA-3.8B (Post-optimization) (extra data) | 2024-09-29 |
| Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation | ✓ Link | 68.0 | 64.8 | 71.3 | MUTR | 2023-05-25 |
| UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces | ✓ Link | 67.2 | | | UniRef++-L (joint multi-task, language-only) (extra data) | 2023-12-25 |
| Tracking Anything with Decoupled Video Segmentation | ✓ Link | 66.3 | | | DEVA + ReferFormer Swin-L (offline) (extra data) | 2023-09-07 |
| SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation | ✓ Link | 65.8 | 62.5 | 69.1 | SOC | 2023-05-26 |
| MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation | | 65.0 | 61.9 | 68.1 | LMPM++ | 2025-12-11 |
| Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation | ✓ Link | 64.9 | 61.7 | 68.1 | DsHmp | 2024-04-04 |
| OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation | ✓ Link | 64.8 | | | OnlineRefer Swin-L (online) (extra data) | 2023-07-18 |
| LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation | ✓ Link | 64.3 | 61.8 | 66.8 | LoSh | 2023-06-14 |
| Spectrum-guided Multi-granularity Referring Video Object Segmentation | ✓ Link | 63.3 | 60.6 | 66.0 | SgMg | 2023-07-25 |
| HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation | | 62.1 | 59.2 | 65.1 | HTML | 2023-01-01 |
| Language as Queries for Referring Video Object Segmentation | ✓ Link | 61.1 | 58.1 | 64.1 | ReferFormer | 2022-01-03 |
| Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus | ✓ Link | 59.7 | | | R²-VOS (ResNet-50, zero-shot) (extra data) | 2022-07-04 |
| Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation | ✓ Link | 54.5 | | | LBDT | 2022-06-08 |
| URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark | ✓ Link | 51.6 | 47.3 | 56.0 | URVOS | |