| Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation | ✓ Link | 65.2 | | | TCoVP-M-4B (extra data) | 2026-10-18 |
| VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation | ✓ Link | 62.9 | 60.4 | 65.4 | VIRST | 2026-03-28 |
| Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs | ✓ Link | 61.3 | | | Video-ORA-9B | 2026-08-20 |
| ReferEverything: Towards Segmenting Everything We Can Speak of in Videos | | 60.3 | | | REM Wan-14B | 2024-10-30 |
| ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning | | 59.8 | 56.1 | 63.4 | ReVSeg-7B | 2025-12-02 |
| MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation | | 57.1 | | | MomentSeg-7B | 2026-09-08 |
| DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentation | | 56.0 | | | DeRVOS | 2026-06-03 |
| UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning | | 55.8 | 53.2 | 58.3 | UniPixel (7B) | 2025-09-22 |
| Think, Compress, Answer: Reinforcement Learning for Multimodal Grounding via Reasoning Compression | | 55.8 | | | TCA | 2026-10-19 |
| PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos | | 55.1 | | | PhysMLLMs | 2026-08-25 |
| MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation | ✓ Link | 53.7 | 50.7 | 56.7 | MPG-SAM 2 | 2025-01-23 |
| RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation | ✓ Link | 53.7 | 50.7 | 56.7 | RCoT-Seg | 2026-05-08 |
| Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation | ✓ Link | 53.2 | 50.5 | 55.9 | FindTrack | 2025-03-05 |
| UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning | | 53.1 | 50.4 | 55.7 | UniPixel (3B) | 2025-09-22 |
| VoCap: Video Object Captioning and Segmentation from Any Prompt | | 53.0 | | | VoCap + FindTrack | 2025-08-29 |
| Mitigating Query Selection Bias in Referring Video Object Segmentation | | 52.8 | 49.4 | 56.1 | TQF-B | 2025-09-17 |
| OneThinker: All-in-one Reasoning Model for Image and Video | ✓ Link | 52.7 | | | OneThinker-8B | 2025-12-02 |
| Unleashing Hierarchical Reasoning: An LLM-Driven Framework for Training-Free Referring Video Object Segmentation | | 52.4 | 49.2 | 55.6 | PARSE-VOS | 2025-09-06 |
| Reinforcing Video Reasoning Segmentation to Think Before It Segments | ✓ Link | 52.2 | 48.4 | 56.0 | Veason-R1-7B | 2025-08-15 |
| VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding | ✓ Link | 51.7 | | | VideoLoom-8B (extra data) | 2026-01-12 |
| GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation | ✓ Link | 51.3 | 48.5 | 54.2 | GLUS | 2025-04-10 |
| Reinforcing Video Reasoning Segmentation to Think Before It Segments | ✓ Link | 51.2 | 48.2 | 54.2 | Veason-R1-3B | 2025-08-15 |
| SPOT: Spatiotemporal Prompt Optimization for Motion-Stabilized MLLM-Guided Video Segmentation | | 51.2 | | | SPOT-13B | 2026-06-03 |
| Deforming Videos to Masks: Flow Matching for Referring Video Segmentation | ✓ Link | 51.1 | | | FlowRVS (Wan 2.1 T2V 1.3B DiT, MeViS-only) (extra data) | 2025-10-07 |
| The Devil is in Temporal Token: High Quality Video Reasoning Segmentation | ✓ Link | 50.9 | 48 | 53.7 | VRS-HQ (Chat-UniVi-13B) | 2025-01-15 |
| Towards Streaming Referring Video Segmentation via Large Language Model | ✓ Link | 50.9 | | | StreamingRVOS-4B | 2026-06-03 |
| Mitigating Query Selection Bias in Referring Video Object Segmentation | | 50.1 | 46.8 | 53.3 | TQF-T | 2025-09-17 |
| Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation | ✓ Link | 50.0 | | | GeoLaV | 2026-06-23 |
| STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation | ✓ Link | 49.9 | | | STAC | 2026-07-03 |
| FeVOS: Foresight Expression Video Object Segmentation | ✓ Link | 49.5 | | | FeVOS-R1 | 2026-06-24 |
| ViLLa: Video Reasoning Segmentation with Large Language Model | ✓ Link | 49.4 | | | ViLLa (InternVideo2-6B) (extra data) | 2024-07-18 |
| ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations | | 49.3 | 44.7 | 53.9 | ReferDINO (Swin-B) | 2025-01-24 |
| InterRVOS: Interaction-aware Referring Video Object Segmentation | ✓ Link | 49.3 | | | ReVIOSa-4B (standard RVOS, AML-only) (extra data) | 2025-06-03 |
| Semantic and Sequential Alignment for Referring Video Object Segmentation | | 48.9 | | | SSA (extra data) | 2025-06-11 |
| DTOS: Dynamic Time Object Sensing with Large Multimodal Model | ✓ Link | 48.86 | | | DTOS-9B | 2025-06-11 |
| Decoupled Motion Expression Video Segmentation | | 48.6 | | | DMVS | 2025-06-11 |
| SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation | ✓ Link | 48.3 | 45.4 | 51.2 | SAMWISE | 2024-11-26 |
| Multi-Context Temporal Consistent Modeling for Referring Video Object Segmentation | ✓ Link | 47.6 | 44.1 | 51.1 | DsHmp + MTCM | 2025-01-09 |
| MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation | | 47.6 | 44.3 | 50.9 | LMPM++ | 2025-12-11 |
| Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos | ✓ Link | 46.9 | | | Sa2VA-8B (extra data) | 2025-01-07 |
| Event-Aware Instructed Assistant for Referring Video Segmentation | | 46.8 | 43.7 | 49.9 | EVIS-1B | 2026-06-25 |
| Event-Aware Instructed Assistant for Referring Video Segmentation | | 46.7 | 43.5 | 49.9 | EVIS | 2026-06-25 |
| Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation | ✓ Link | 46.4 | 43 | 49.8 | DsHmp | 2024-04-04 |
| LTCA: Long-range Temporal Context Attention for Referring Video Object Segmentation | ✓ Link | 45.3 | 41.7 | 48.9 | LTCA | 2025-10-09 |
| VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos | ✓ Link | 45.15 | | | VideoGLaMM (Phi-3 Mini 3.8B, RVOS fine-tuned) (extra data) | 2024-11-07 |
| GREx: Generalized Referring Expression Segmentation, Comprehension, and Generation | | 44.6 | 41.7 | 47.5 | ReLA | 2026-01-08 |
| VISA: Reasoning Video Object Segmentation via Large Language Models | ✓ Link | 44.5 | | | VISA Chat-UniVi-13B (extra data) | 2024-07-16 |
| One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos | ✓ Link | 44.4 | | | VideoLISA-3.8B (Post-optimization) (extra data) | 2024-09-29 |
| Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation | ✓ Link | 43.5 | | | DecAF (training-free, Qwen2.5-VL-7B + SAM2) (extra data) | 2025-10-22 |
| Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation | | 43.2 | | | OISA-1B | 2025-07-30 |
| Temporally Consistent Referring Video Object Segmentation with Hybrid Memory | ✓ Link | 42.7 | 39.9 | 45.5 | HTR | 2024-03-28 |
| MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions | ✓ Link | 37.2 | 34.2 | 40.2 | LMPM | 2023-08-16 |
| VLT: Vision-Language Transformer and Query Generation for Referring Segmentation | ✓ Link | 35.5 | 33.6 | 37.3 | VLT+TC | 2022-10-28 |
| InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling | ✓ Link | 32 | | | InternVideo2.5 | 2025-01-21 |
| Language as Queries for Referring Video Object Segmentation | ✓ Link | 31.0 | 29.8 | 32.2 | ReferFormer | 2022-01-03 |
| End-to-End Referring Video Object Segmentation with Multimodal Transformers | ✓ Link | 30.0 | 28.8 | 31.2 | MTTR | 2021-11-29 |
| Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation | ✓ Link | 29.3 | 27.8 | 30.8 | LBDT | 2022-06-08 |
| URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark | ✓ Link | 27.8 | 25.7 | 29.9 | URVOS | |