AI Paper Atlas

Research map / Benchmarks / DAVIS 2017

DAVIS 2017 leaderboard

70 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on DAVIS 2017. Best J&F (val): 91.3 (SeC, ICLR 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.

DAVIS 2017 · J&F (val)

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

38 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

DAVIS 2017 · J&F

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

4 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

DAVIS 2017 · FPS (val)

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

#FPS ↑MethodPaperTopic
190.6MobileVOS ResNet18†*
ResNet18
MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation
CVPR 2023 · DAVIS 2017 results table
Video segmentation and tracking
270SwiftNet (ResNet-18)
ResNet-18
SwiftNet: Real-Time Video Object Segmentation
CVPR 2021 · Table: Quantitative results on
Video segmentation and tracking
360SAT-FastState-Aware Tracker for Real-Time Video Object Segmentation
CVPR 2020 · Table: Quantitative results on
Video segmentation and tracking
441.3Ours-fast
ResNet-18
Learning Fast and Robust Target Models for Video Object Segmentation
CVPR 2020 · Table 3
Open-set and few-shot detection
536SWEM
ResNet-50
SWEM: Towards Real-Time Video Object Segmentation With Sequential Weighted Expectation-Maximization
CVPR 2022 · Comparisons with previous appr
Video segmentation and tracking
627RDE-VOSRecurrent Dynamic Embedding for Video Object Segmentation
CVPR 2022 · Table 1
Video segmentation and tracking
722.6XMemXMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
ECCV 2022 · Table 2
Video segmentation and tracking
820.2STCNRethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
NeurIPS 2021 · Table 3
Video segmentation and tracking
911.8SITVOS
ResNet50
Siamese Network with Interactive Transformer for Video Object Segmentation
AAAI 2022 · Table 1
Video segmentation and tracking
1010.7Full version
ConvViTb
Spatial-Temporal Multi-level Association for Video Object Segmentation
ECCV 2024 · 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

DAVIS 2017 · J&F (test-dev)

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

1 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

DAVIS 2017 · J mean (val)

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

DAVIS 2017 · F mean (val)

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

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