| SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction | ✓ Link | 69.5 | | | | SetCon | 2026-05-19 |
| VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation | ✓ Link | 68.4 | 66.3 | 70.6 | | VIRST | 2026-03-28 |
| Think Visually Across Space and Time: Grounded Reasoning for Video Segmentation | ✓ Link | 68.3 | | | | TCoVP-M-4B (extra data) | 2026-10-18 |
| VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation | ✓ Link | 67.7 | 65.0 | 70.4 | | VideoSEG-O3-4B | 2026-06-05 |
| MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding | ✓ Link | 65.1 | 62.3 | 67.8 | | MomentSeg-7B | 2025-10-10 |
| MomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation | | 65.1 | | | | MomentSeg-7B | 2026-09-08 |
| VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation | ✓ Link | 64.8 | 62.0 | 67.5 | | VideoSEG-O3-2B | 2026-06-05 |
| UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning | | 63.7 | 61.7 | 65.7 | | UniPixel (7B) | 2025-09-22 |
| VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding | ✓ Link | 63.1 | | | | VideoLoom-8B (extra data) | 2026-01-12 |
| MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding | ✓ Link | 62.6 | 60.0 | 65.2 | | MomentSeg-3B | 2025-10-10 |
| UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning | | 62.1 | 59.7 | 64.4 | | UniPixel (3B) | 2025-09-22 |
| ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning | | 62.1 | 59.3 | 65.0 | | ReVSeg-7B | 2025-12-02 |
| UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception | | 61.9 | 59.3 | 64.4 | | UniRAP | 2026-10-21 |
| Reinforcing Video Reasoning Segmentation to Think Before It Segments | ✓ Link | 61.3 | 58.2 | 64.4 | | Veason-R1-7B | 2025-08-15 |
| RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation | ✓ Link | 61.2 | 58.2 | 64.3 | | RCoT-Seg-3B | 2026-05-08 |
| Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos | ✓ Link | 60.8 | | | | Sa2VA-InternVL3-8B (extra data) | 2025-01-07 |
| FeVOS: Foresight Expression Video Object Segmentation | ✓ Link | 60.3 | | | | FeVOS-R1 | 2026-06-24 |
| The Devil is in Temporal Token: High Quality Video Reasoning Segmentation | ✓ Link | 60 | 57.6 | 62.5 | 18.9 | VRS-HQ (Chat-UniVi-13B) | 2025-01-15 |
| Reinforcing Video Reasoning Segmentation to Think Before It Segments | ✓ Link | 59.9 | 56.9 | 62.8 | | Veason-R1-3B | 2025-08-15 |
| SVAC: Scaling Is All You Need For Referring Video Object Segmentation | ✓ Link | 59.2 | 58.2 | 60.2 | | SVAC-8B | 2025-09-28 |
| The Devil is in Temporal Token: High Quality Video Reasoning Segmentation | ✓ Link | 59.1 | 56.6 | 61.6 | 19.7 | VRS-HQ (Chat-UniVi-7B) | 2025-01-15 |
| Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration | ✓ Link | 58.9 | | | | Omni-R1-11B (Sa2VA-4B + SAM2 Hiera-L) (extra data) | 2025-05-26 |
| Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory | | 58.0 | 55.4 | 60.7 | | SDAM | 2026-03-02 |
| PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Images and Videos | | 57.4 | | | | PhysMLLMs | 2026-08-25 |
| ViLLa: Video Reasoning Segmentation with Large Language Model | ✓ Link | 57.0 | | | | ViLLa (InternVideo2-6B) (extra data) | 2024-07-18 |
| HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver | ✓ Link | 55.7 | | | | HyperSeg-3B | 2025-06-11 |
| SVAC: Scaling Is All You Need For Referring Video Object Segmentation | ✓ Link | 55.6 | 55.1 | 56.1 | | SVAC-4B | 2025-09-28 |
| SPOT: Spatiotemporal Prompt Optimization for Motion-Stabilized MLLM-Guided Video Segmentation | | 54.8 | | | | SPOT-13B | 2026-06-03 |
| InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models | ✓ Link | 54.5 | | | | InstructSeg (Mipha-3B) (extra data) | 2024-12-18 |
| Online Reasoning Video Object Segmentation | | 54.3 | | | | ORVOS (Ours) (extra data) | 2026-04-13 |
| GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation | ✓ Link | 51.4 | | | | GLUS-A (Additional-SFT) (extra data) | 2025-04-10 |
| VISA: Reasoning Video Object Segmentation via Large Language Models | ✓ Link | 50.9 | 48.8 | 52.9 | 14.5 | VISA (Chat-UniVi-13B) | 2024-07-16 |
| Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation | ✓ Link | 50.3 | | | | DecAF (training-free, Qwen2.5-VL-7B + SAM2) (extra data) | 2025-10-22 |
| SVAC: Scaling Is All You Need For Referring Video Object Segmentation | ✓ Link | 49.4 | 48.1 | 50.7 | | SVAC-1B | 2025-09-28 |
| STAC: Selective Spatiotemporal Aggregation and Compression for Video Reasoning Segmentation | ✓ Link | 48.4 | | | | STAC | 2026-07-03 |
| VISA: Reasoning Video Object Segmentation via Large Language Models | ✓ Link | 46.9 | 44.9 | 49.0 | 15.5 | VISA (Chat-UniVi-7B) | 2024-07-16 |
| Tracking with Human-Intent Reasoning | ✓ Link | 45.0 | 43.2 | 46.8 | 12.8 | TrackGPT (LLaVA-13B) | 2023-12-29 |
| LISA: Reasoning Segmentation via Large Language Model | ✓ Link | 41.6 | 39.8 | 43.5 | 8.6 | LISA (LLaVA-13B) | 2023-08-01 |
| Language as Queries for Referring Video Object Segmentation | ✓ Link | 28.1 | 26.2 | 29.9 | 8.8 | ReferFormer (Video-Swin-B) | 2022-01-03 |
| MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions | ✓ Link | 26.4 | 21.2 | 31.7 | 3.2 | LMPM (Swin-T) | 2023-08-16 |
| End-to-End Referring Video Object Segmentation with Multimodal Transformers | ✓ Link | 25.5 | 25.1 | 25.9 | 5.6 | MTTR (Video-Swin-T) | 2021-11-29 |