AI Paper Atlas

Research map / Benchmarks / OVIS

OVIS leaderboard

32 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on OVIS. Best AP (val): 53.2 (CAVIS, ICCV 2025).

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.

OVIS · AP (val)

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

14 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

OVIS · AP

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

#AP ↑MethodPaperTopic
149.1MiNQVIS
Swin-L
MiNQVIS: Mitigating Noisy Queries for Robust Online Video Instance Segmentation
ECCV 2026 · Table 1
Video segmentation and tracking
246.9CTVIS
Swin-L
CTVIS: Consistent Training for Online Video Instance Segmentation
ICCV 2023 · Table 1
Video segmentation and tracking
346.5ViLLaViLLa: Video Reasoning Segmentation with Large Language Model
ICCV 2025 · Appendix Table
Video-language understanding
439.4MinVIS
Swin-L
MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training
NeurIPS 2022 · Table 3
Video segmentation and tracking
532.2Ach (team)Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge
NeurIPS 2021 · Table 2
Video segmentation and tracking
621EntitySAM
SAM 2.1
EntitySAM: Segment Everything in Video
CVPR 2025 · Table 4
Open-set and few-shot detection
720InstanceFormer with prior, memory, and TCL
ResNet-50
InstanceFormer: An Online Video Instance Segmentation Framework
AAAI 2023 · Prior and memory ablation tabl
Video segmentation and tracking
819.7SWBridge
SwinB
Sliced Wasserstein Bridge for Open-Vocabulary Video Instance Segmentation
ICCV 2025 · Table 2
Video segmentation and tracking
915.7VITA + MaskFreeVIS (video mask-free)
VITA, ResNet-50
Mask-Free Video Instance Segmentation
CVPR 2023 · Table: State-of-the-art compar
Video segmentation and tracking
1014.1SegFS
MOBIUS MNv4-CM slow model
Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing
ECCV 2026 · Table 1
Video segmentation and tracking

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