AI Paper Atlas

Research map / Benchmarks / MOVi-E

MOVi-E leaderboard

19 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MOVi-E. Best FG-ARI: 84.1 (SAVi++, NeurIPS 2022).

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.

MOVi-E · FG-ARI

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

#FG-ARI ↑MethodPaperTopic
184.1SAVi++SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos
NeurIPS 2022 · Table 1
Open-set and few-shot detection
284SSyncSelective Synergistic Learning for Video Object-Centric Learning
ECCV 2026 · Table 1
Video segmentation and tracking
383.7SlotCurriReconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning
CVPR 2026 · Table 2
Video segmentation and tracking
483.4BA (ours)
DINO ViT-S/8
Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation
ECCV 2024 · Table 1
Video segmentation and tracking
582.9SLOT CONTRASTTemporally Consistent Object-Centric Learning by Contrasting Slots
CVPR 2025 · Table 1
Video segmentation and tracking
682.2DIOD*
DIOD
DIOD: Self-Distillation Meets Object Discovery
CVPR 2024 · Table 2
Open-set and few-shot detection
781.9SRL (Ours)
DINO-v2-Base/14
From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning
ICLR 2026 · Table 1
Open-set and few-shot detection
878.33OursMulti-Object Discovery by Low-Dimensional Object Motion
ICCV 2023 · Table 1
Depth and stereo
975.7Grounded CorrespondenceRethinking Temporal Consistency in Video Object-Centric Learning: From Prediction to Correspondence
ICML 2026 · Table 4
Video segmentation and tracking
1073.9VideoSAURObject-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
NeurIPS 2023 · Table 1
Video segmentation and tracking
8 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

MOVi-E · mBO

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

#mBO ↑MethodPaperTopic
143.38SlotAdapt
Stable Diffusion v1.5
Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation
ICLR 2025 · Appendix, Comparative evaluati
Text-to-image diffusion
239.3Ours
DINOSAUR
Bootstrapping Top-down Information for Self-modulating Slot Attention
NeurIPS 2024 · Table: Comparison with DINOSAU
Open-set and few-shot detection
338.96LSD (Ours)Object-Centric Slot Diffusion
NeurIPS 2023 · Table 1
Autoregressive and latent generation
435.6VideoSAURObject-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities
NeurIPS 2023 · Table 1
Video segmentation and tracking
535.52DINOSAUR (ViT-B/8)
ViT-B/8
Bridging the Gap to Real-World Object-Centric Learning
ICLR 2023 · Appendix synthetic results tab
Open-set and few-shot detection
634.8SSyncSelective Synergistic Learning for Video Object-Centric Learning
ECCV 2026 · Table 1
Video segmentation and tracking
729.83AdaSlot
DINOSAUR
Adaptive Slot Attention: Object Discovery with Dynamic Slot Number
CVPR 2024 · Table 2
Open-set and few-shot detection
829.3SRL (Ours)
DINO-v2-Base/14
From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning
ICLR 2026 · Table 1
Open-set and few-shot detection
929.2SLOT CONTRASTTemporally Consistent Object-Centric Learning by Contrasting Slots
CVPR 2025 · Table 1
Video segmentation and tracking
1028.9SlotCurriReconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning
CVPR 2026 · Table 2
Video segmentation and tracking
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.