AI Paper Atlas

Research map / Benchmarks / Ref-YouTube-VOS

Ref-YouTube-VOS leaderboard

40 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Ref-YouTube-VOS. Best J&F: 81.3 (VideoSeg-R1, AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Ref-YouTube-VOS · J&F

29 papers, each with its best reported number for its own method; higher is better.

#J&F ↑MethodPaperTopic
181.3VideoSeg-R1
Qwen2.5-VL-7B
VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning
AAAI 2026 · Table 1
Video-language understanding
278.8SetCon
Qwen3-VL-8B
SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
NeurIPS 2026 · Table 2
Open-set and few-shot detection
374.1VideoSEG-O3-4B
Qwen3-VL-4B
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
ICML 2026 · Table 1
Video-language understanding
472.3MomentSeg-7BMomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation
ECCV 2026 · Table 3
Video segmentation and tracking
572.2G2TAMG$^2$TAM: Geometry Grounded Track Anything Model
ICML 2026 · Table 5
3D generation
671.8SPOT-13BSPOT: Spatiotemporal Prompt Optimization for Motion-Stabilized MLLM-Guided Video Segmentation
CVPR 2026 · Table 1
Video-language understanding
771.3Refer-Agent
Ovis2.5-9B
Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation
CVPR 2026 · Table 1
Video-language understanding
870.5StreamingRVOS-4BTowards Streaming Referring Video Segmentation via Large Language Model
CVPR 2026 · Table 1
Video segmentation and tracking
970.5GeoLaVBoosting Text-Driven Video Segmentation via Geometry-Aware Distillation
ECCV 2026 · Table 1
Video segmentation and tracking
1070.1UNINEXT (ViT-H)
ViT-H
Universal Instance Perception As Object Discovery and Retrieval
CVPR 2023 · Table 10
Open-set and few-shot detection
19 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Ref-YouTube-VOS · J&F (val)

12 papers, each with its best reported number for its own method; higher is better.

#J&F ↑MethodPaperTopic
173.9MPG-SAM 2MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation
ICCV 2025 · Table 1
Video segmentation and tracking
273.4UFVideoUFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
CVPR 2026 · Table 4
Video-language understanding
371VRS-HQ
Chat-UniVi-13B
The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
CVPR 2025 · Table 2
Video-language understanding
471UniPixel 7B
Qwen2.5-VL 7B
UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning
NeurIPS 2025 · Table: MeViS, Ref-YouTube-VOS,
Multimodal LLMs
567.9AL-Ref-SAM 2
SAM 2
Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation
AAAI 2025 · Table 1
Video-language understanding
667.5InstructSeg
Mipha-3B
InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models
ICCV 2025 · Table 4
Video-language understanding
765.3SDAMTraining-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory
AAAI 2026 · Table 1
Video segmentation and tracking
864.9UniLSeg-100Universal Segmentation at Arbitrary Granularity with Language Instruction
CVPR 2024 · Table 3
Open-set and few-shot detection
964.8VD-IT (Video Diffusion)
ModelScopeT2V
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
ECCV 2024 · Table 1
Video segmentation and tracking
1064.2ReferFormer*
Swin-L
Language As Queries for Referring Video Object Segmentation
CVPR 2022 · Table 1
CNN features
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.