Datasets › DAVIS

DAVIS (Densely Annotated VIdeo Segmentation)

Introduced by Federico Perazzi et al. in A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation1 Jan 2016 archive 2025-07-28

The Densely Annotation Video Segmentation dataset (DAVIS) is a high quality and high resolution densely annotated video segmentation dataset under two resolutions, 480p and 1080p. There are 50 video sequences with 3455 densely annotated frames in pixel level. 30 videos with 2079 frames are for training and 20 videos with 1376 frames are for validation.

Source: TENet: Triple Excitation Network for Video Salient Object Detection

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.

Papers archive 2025-07-28

30 shown of 58 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 734. 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
MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation 1 1 9 Jan 2024 not harvested
Deficiency-Aware Masked Transformer for Video Inpainting 1 1 17 Jul 2023 not harvested
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement 3 2 14 Jun 2023 ran 0 of 1 samples (1 unverified)
CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation 1 1 9 Mar 2023 ran 1 of 1 samples (0 unverified; 1 pointer-only for licence)
Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting 2 2 24 Jan 2023 not harvested
Deep Bayesian Video Frame Interpolation 1 1 23 Oct 2022 not harvested
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers 2 2 20 Oct 2022 ran 2 of 3 samples (1 unverified; 1 pointer-only for licence)
Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising 0 5 25 Aug 2022 not harvested
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization 1 1 22 Aug 2022 not harvested
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model 2 1 14 Jul 2022 ran 1 of 3 samples (2 unverified; 2 pointer-only for licence)
Tackling Background Distraction in Video Object Segmentation 1 1 14 Jul 2022 ran 1 of 3 samples (2 unverified)
Real-time Streaming Video Denoising with Bidirectional Buffers 1 2 14 Jul 2022 ran 3 of 3 samples (0 unverified)
Recurrent Video Restoration Transformer with Guided Deformable Attention 4 5 5 Jun 2022 ran 7 of 14 samples (7 unverified; 5 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)
FocalClick: Towards Practical Interactive Image Segmentation 1 1 6 Apr 2022 ran 12 of 21 samples (9 unverified; 1 pointer-only for licence)
Cascaded Sparse Feature Propagation Network for Interactive Segmentation 1 1 10 Mar 2022 not harvested
VRT: A Video Restoration Transformer 1 5 28 Jan 2022 ran 4 of 5 samples (1 unverified; 5 pointer-only for licence)
ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation 3 1 30 Nov 2021 not harvested
Pixel-Level Bijective Matching for Video Object Segmentation 1 1 4 Oct 2021 not harvested
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)
EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flow 3 1 20 Sep 2021 ran 2 of 5 samples (3 unverified)
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)
Joint Inductive and Transductive Learning for Video Object Segmentation 1 1 8 Aug 2021 ran 0 of 1 samples (1 unverified; 1 pointer-only for licence)
Associating Objects with Transformers for Video Object Segmentation 2 1 4 Jun 2021 not harvested
Learning Position and Target Consistency for Memory-based Video Object Segmentation 0 1 9 Apr 2021 not harvested
Patch Craft: Video Denoising by Deep Modeling and Patch Matching 1 5 25 Mar 2021 ran 4 of 8 samples (4 unverified; 8 pointer-only for licence)
Efficient Regional Memory Network for Video Object Segmentation 1 1 24 Mar 2021 ran 5 of 10 samples (5 unverified)
Reviving Iterative Training with Mask Guidance for Interactive Segmentation 5 2 12 Feb 2021 ran 1 of 1 samples (0 unverified)
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation 1 1 21 Jan 2021 ran 5 of 7 samples (2 unverified; 7 pointer-only for licence)
Spatiotemporal Graph Neural Network based Mask Reconstruction for Video Object Segmentation 0 1 10 Dec 2020 not harvested

The full list of 58 is in the JSON twin.

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • DAVIS (no YouTube-VOS training)
  • DAVIS sigma50
  • DAVIS sigma40
  • DAVIS sigma30
  • DAVIS sigma20
  • DAVIS sigma10
  • DAVIS 2017
  • DAVIS

8 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