AI Paper Atlas

Research map / Benchmarks / ReVOS overall

ReVOS overall leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ReVOS overall. Best J&F: 68.4 (VIRST, 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.

ReVOS overall · J&F

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

#J&F ↑MethodPaperTopic
168.4VIRSTVIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation
CVPR 2026 · Table 1
Video segmentation and tracking
267.7VideoSEG-O3-4B
Qwen3-VL-4B
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
ICML 2026 · Table 2
Video-language understanding
366.2Ours (EVOG)
Qwen2.5-VL-7B
Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation
NeurIPS 2026 · Table 1
Video segmentation and tracking
465.1MomentSeg-7BMomentSeg: Moment-Centric Sampling for Enhanced Referring Video Object Segmentation
ECCV 2026 · Table 4
Video segmentation and tracking
561.3Refer-Agent
Ovis2.5-9B
Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation
CVPR 2026 · Table 2
Video-language understanding
660VRS-HQ
Chat-UniVi-13B
The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
CVPR 2025 · Table 1
Video-language understanding
758.9Omni-R1-11B + Sa2VA
Omni-R1-7B
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
NeurIPS 2025 · ReVOS performance table
Video-language understanding
858RGA3-7B
Qwen2.5-VL-7B
Object-centric Video Question Answering with Visual Grounding and Referring
ICCV 2025 · Table 4
Video-language understanding
955.7HyperSeg-3B
Phi-1.5-1.3B
HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver
CVPR 2025 · Table 2
Multimodal LLMs
1054.8SPOT-13BSPOT: Spatiotemporal Prompt Optimization for Motion-Stabilized MLLM-Guided Video Segmentation
CVPR 2026 · Table 4
Video-language understanding
3 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.