AI Paper Atlas

Research map / Benchmarks / MeViS

MeViS leaderboard

38 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MeViS. Best J&F: 63.3 (Molmo2-4B, CVPR 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.

MeViS · J&F

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

#J&F ↑MethodPaperTopic
163.3Molmo2-4B
Qwen3-4B
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
CVPR 2026 · Table 4
Video-language understanding
260.3REM (Wan-14B)ReferEverything: Towards Segmenting Everything We Can Speak of in Videos
ICCV 2025 · Table 2
Video segmentation and tracking
360.1Ours (EVOG)
Qwen2.5-VL-7B
Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation
NeurIPS 2026 · Table 2
Video segmentation and tracking
460VideoSEG-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
555.5CMT + CME
SAM2 Hiera-B + CLIP-B
SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation
CVPR 2025 · Table 2
Video-language understanding
655.3VideoSeg-R1
Qwen2.5-VL-7B
VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning
AAAI 2026 · Table 1
Video-language understanding
754.7Refer-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
853.7SAMA-8B
Sa2VA-8B
SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
NeurIPS 2025 · Table 2
Video-language understanding
951.7VideoLoom-8B
InternVL3-8B
VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
ICML 2026 · Table 2
Video-language understanding
1051.3GLUSA
LISA-7B-v1
GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation
CVPR 2025 · Table 2
Video-language understanding
12 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

MeViS · J&F (val)

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

#J&F ↑MethodPaperTopic
162.9VIRSTVIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation
CVPR 2026 · Table 2
Video segmentation and tracking
257.1MomentSeg-7BMomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation
ECCV 2026 · Table 3
Video segmentation and tracking
355.8UniPixel 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
455.1UFVideoUFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models
CVPR 2026 · Table 4
Video-language understanding
554.4UniPixel + SPARROW
UniPixel
SPARROW: Learning Spatial Precision and Temporal Referential Consistency in Pixel-Grounded Video MLLMs
CVPR 2026 · Table 1
Video-language understanding
653.7MPG-SAM 2MPG-SAM 2: Adapting SAM 2 with Mask Priors and Global Context for Referring Video Object Segmentation
ICCV 2025 · Table 2
Video segmentation and tracking
751.8DeRVOS
DVIS++ + BEiT3-B
DeRVOS: Decoupling Consistent Trajectory Generation and Multimodal Understanding for Referring Video Object Segmentation
CVPR 2026 · Table 1
Video segmentation and tracking
851.2Sa2VA* (motion-centric LoRA)
InternVL2.5-8B
PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?
NeurIPS 2026 · Table 2
Video-language understanding
951.1FlowRVS
Wan2.1 1.3B
Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
ICLR 2026 · Table 1
Video segmentation and tracking
1050.9VRS-HQ
Chat-UniVi-13B
The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
CVPR 2025 · Table 2
Video-language understanding
7 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.