Datasets › YouTube-VOS 2018

YouTube-VOS 2018 (Youtube Video Object Segmentation)

Introduced in YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark1 Jan 2018 archive 2025-07-28

Youtube-VOS is a Video Object Segmentation dataset that contains 4,453 videos - 3,471 for training, 474 for validation, and 508 for testing. The training and validation videos have pixel-level ground truth annotations for every 5th frame (6 fps). It also contains Instance Segmentation annotations. It has more than 7,800 unique objects, 190k high-quality manual annotations and more than 340 minutes in duration.

Source: CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing Image Source: https://youtube-vos.org/

Benchmarks archive 2025-07-28

All 10 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 Cutie+ (base, MEGA) Overall 87.5 Putting the Object Back into Video Object Segmentation hkchengrex/Cutie 53 Compare
Semi-Supervised Video Object Segmentation YouTube-VOS 2019 Cutie+ (base, MEGA) Overall 87.5 Putting the Object Back into Video Object Segmentation hkchengrex/Cutie 22 Compare
Video Object Segmentation YouTube-VOS 2018 XMem (BL30K, MS) Mean Jaccard & F-Measure 86.9 XMem: Long-Term Video Object Segmentation with an... hkchengrex/XMem +1 17 Compare
Video Inpainting YouTube-VOS 2018 ProPainter PSNR 34.43 ProPainter: Improving Propagation and Transformer for... sczhou/propainter +2 10 Compare
Video Object Segmentation YouTube-VOS 2019 XMem (BL30K,MS) Mean Jaccard & F-Measure 86.8 XMem: Long-Term Video Object Segmentation with an... hkchengrex/XMem +1 10 Compare
Visual Object Tracking YouTube-VOS 2018 OSVOS O (Average of Measures) 58.8 One-Shot Video Object Segmentation kmaninis/OSVOS-PyTorch +7 9 Compare
One-shot visual object segmentation YouTube-VOS 2018 OSVOS F-Measure (Seen) 60.5 One-Shot Video Object Segmentation kmaninis/OSVOS-PyTorch +7 2 Compare
Video Inpainting YouTube-VOS FGT++ LPIPS 0.025 Exploiting Optical Flow Guidance for Transformer-Based... hitachinsk/fgt +1 2 Compare
Visual Object Tracking YouTube-VOS AOC-MF F-Measure (Seen) 87.4 Towards Robust Video Object Segmentation with Adaptive... jerryx1110/robust-video-object-segmentation 2 Compare
One-shot visual object segmentation YouTube-VOS RVOS-Mask-ST+ F-Measure (Seen) 67.2 RVOS: End-to-End Recurrent Network for Video Object Segmentation imatge-upc/rvos 1 Compare

Papers archive 2025-07-28

30 shown of 48 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 203. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
UniVS: Unified and Universal Video Segmentation with Prompts as Queries 1 1 28 Feb 2024 ran 12 of 14 samples (2 unverified; 14 pointer-only for licence)
Putting the Object Back into Video Object Segmentation 1 2 19 Oct 2023 ran 3 of 5 samples (2 unverified)
ProPainter: Improving Propagation and Transformer for Video Inpainting 3 1 7 Sep 2023 ran 20 of 34 samples (14 unverified; 16 pointer-only for licence)
Tracking Anything in High Quality 1 1 26 Jul 2023 not harvested
Deficiency-Aware Masked Transformer for Video Inpainting 1 1 17 Jul 2023 not harvested
TrickVOS: A Bag of Tricks for Video Object Segmentation 0 2 27 Jun 2023 not harvested
MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillation 0 1 14 Mar 2023 not harvested
Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting 2 2 24 Jan 2023 not harvested
Decoupling Features in Hierarchical Propagation for Video Object Segmentation 2 12 18 Oct 2022 not harvested
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 0 19 1 Aug 2022 not harvested
Region Aware Video Object Segmentation with Deep Motion Modeling 0 1 21 Jul 2022 not harvested
Learning Quality-aware Dynamic Memory for Video Object Segmentation 1 1 16 Jul 2022 ran 0 of 1 samples (1 unverified; 1 pointer-only for licence)
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model 2 12 14 Jul 2022 ran 1 of 3 samples (2 unverified; 2 pointer-only for licence)
Towards Robust Video Object Segmentation with Adaptive Object Calibration 1 2 2 Jul 2022 ran 2 of 4 samples (2 unverified; 4 pointer-only for licence)
Towards An End-to-End Framework for Flow-Guided Video Inpainting 2 1 6 Apr 2022 ran 5 of 6 samples (1 unverified; 6 pointer-only for licence)
Scalable Video Object Segmentation with Identification Mechanism 2 11 22 Mar 2022 not harvested
Reliable Propagation-Correction Modulation for Video Object Segmentation 1 4 6 Dec 2021 ran 1 of 5 samples (4 unverified)
Hierarchical Memory Matching Network for Video Object Segmentation 1 1 23 Sep 2021 ran 5 of 8 samples (3 unverified; 8 pointer-only for licence)
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting 1 1 7 Sep 2021 ran 10 of 11 samples (1 unverified; 11 pointer-only for licence)
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation 1 1 27 Jul 2021 ran 0 of 6 samples (6 unverified)
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation 3 4 9 Jun 2021 ran 6 of 10 samples (4 unverified; 2 pointer-only for licence)
Associating Objects with Transformers for Video Object Segmentation 2 13 4 Jun 2021 not harvested
Efficient Regional Memory Network for Video Object Segmentation 1 1 24 Mar 2021 ran 5 of 10 samples (5 unverified)
Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion 5 1 14 Mar 2021 ran 9 of 18 samples (9 unverified)
Separable Structure Modeling for Semi-supervised Video Object Segmentation 1 1 18 Feb 2021 not harvested
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation 1 2 21 Jan 2021 ran 5 of 7 samples (2 unverified; 7 pointer-only for licence)
Make One-Shot Video Object Segmentation Efficient Again 4 1 3 Dec 2020 not harvested
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation 1 1 23 Oct 2020 not harvested
Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement 1 1 15 Oct 2020 not harvested
Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration 1 1 13 Oct 2020 ran 0 of 2 samples (2 unverified)

The full list of 48 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

License archive 2025-07-28

CC BY 4.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • YouTube-VOS 2018
  • YouTube-VOS
  • YouTube-VOS 2019

3 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections