AI Paper Atlas

Research map / Benchmarks / VIP

VIP leaderboard

15 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on VIP. Best mIoU: 45.9 (SiamMAE, NeurIPS 2023).

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.

VIP · mIoU

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

#mIoU ↑MethodPaperTopic
145.9SiamMAE
ViT-S/8
Siamese Masked Autoencoders
NeurIPS 2023 · Comparison with prior work tab
Video segmentation and tracking
244.2TED
I2VGen-XL + ADM
Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
NeurIPS 2025 · Table: Results on JHMDB and VI
Tracking
343.6VideoMAC (RN50)
RN50
VideoMAC: Video Masked Autoencoders Meet ConvNets
CVPR 2024 · Table 1
Video segmentation and tracking
442.9OursUnified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation
CVPR 2023 · Appendix Table (VIP test)
Video segmentation and tracking
540.8iBOT + Ours
iBOT ViT-B/16
From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learning
CVPR 2026 · Table 1
Video segmentation and tracking
640.8Ours
ResNet-18
Contrastive Learning for Space-Time Correspondence via Self-Cycle Consistency
CVPR 2022 · Table 3
Self-supervised and contrastive
739.7T-CoRe
ViT-S/16
When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning
CVPR 2025 · Table 1
Video segmentation and tracking
839.6VideoHiGraph
ResNet-18
Exposing the Self-Supervised Space-Time Correspondence Learning via Graph Kernels
AAAI 2023 · Table 3
Video segmentation and tracking
938.8SMTC
ResNet-50
Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos
ICCV 2023 · Table 4
Video segmentation and tracking
1038.4SFCSemantic-Aware Fine-Grained Correspondence
ECCV 2022 · Table 1
Open-set and few-shot detection
5 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.