Methods › Computer Vision › Video Object Segmentation Models › VOS
VOS
Introduced by Andreas Robinson et al. in Learning Fast and Robust Target Models for Video Object Segmentation
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
VOS is a type of video object segmentation model consisting of two network components. The target appearance model consists of a light-weight module, which is learned during the inference stage using fast optimization techniques to predict a coarse but robust target segmentation. The segmentation model is exclusively trained offline, designed to process the coarse scores into high quality segmentation masks.
In Syntology about another paper, arXiv:2202.01197: harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2202.01197'). Repositories: 2 listed of 2 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2202.01197, not a method entry. About another paper: this answer is about arXiv:2202.01197, while the archive credits arXiv:2003.00908.
Origin paper of this answer, arXiv:2202.01197 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 3 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 117 · with a code link: 59 · where Syntology ran a sample: 20 (18 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (20 of 117 tagged: 18 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 117, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
VideoMolmo: Spatio-Temporal Grounding Meets Pointing 5 Jun 2025 · 1 repository · arXiv:2506.05336
-
Foundations of Unknown-aware Machine Learning 20 May 2025 · 0 repositories · arXiv:2505.14933
-
RGB-D Video Object Segmentation via Enhanced Multi-store Feature Memory 23 Apr 2025 · 0 repositories · arXiv:2504.16471
-
FVOS for MOSE Track of 4th PVUW Challenge: 3rd Place Solution 13 Apr 2025 · 0 repositories · arXiv:2504.09507
-
GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation 10 Apr 2025 · 1 repository · arXiv:2504.07962Syntology 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result (of 12 harvested samples) · 12 pointer-only (licence)
-
Zero-Shot 4D Lidar Panoptic Segmentation 1 Apr 2025 · 0 repositories · arXiv:2504.00848
-
An Analysis of Data Transformation Effects on Segment Anything 2 25 Feb 2025 · 0 repositories · arXiv:2503.00042
-
Efficient Track Anything 28 Nov 2024 · 1 repository · arXiv:2411.18933Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Addressing Issues with Working Memory in Video Object Segmentation 29 Oct 2024 · 0 repositories · arXiv:2410.22451
-
X-Prompt: Multi-modal Visual Prompt for Video Object Segmentation 28 Sep 2024 · 1 repository · arXiv:2409.19342Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation 9 Sep 2024 · 0 repositories · arXiv:2409.05847
-
Discriminative Spatial-Semantic VOS Solution: 1st Place Solution for 6th LSVOS 29 Aug 2024 · 0 repositories · arXiv:2408.16431
-
CSS-Segment: 2nd Place Report of LSVOS Challenge VOS Track 24 Aug 2024 · 0 repositories · arXiv:2408.13582
-
LSVOS Challenge 3rd Place Report: SAM2 and Cutie based VOS 20 Aug 2024 · 0 repositories · arXiv:2408.10469
-
UNINEXT-Cutie: The 1st Solution for LSVOS Challenge RVOS Track 19 Aug 2024 · 0 repositories · arXiv:2408.10129
-
Video Object Segmentation via SAM 2: The 4th Solution for LSVOS Challenge VOS Track 19 Aug 2024 · 0 repositories · arXiv:2408.10125
-
Improving Unsupervised Video Object Segmentation via Fake Flow Generation 16 Jul 2024 · 0 repositories · arXiv:2407.11714
-
RMem: Restricted Memory Banks Improve Video Object Segmentation 12 Jun 2024 · 0 repositories · arXiv:2406.08476
-
Training-Free Robust Interactive Video Object Segmentation 8 Jun 2024 · 0 repositories · arXiv:2406.05485
-
A Semi-Self-Supervised Approach for Dense-Pattern Video Object Segmentation 7 Jun 2024 · 0 repositories · arXiv:2406.05131
-
3rd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation 6 Jun 2024 · 0 repositories · arXiv:2406.03668
-
One-shot Training for Video Object Segmentation 22 May 2024 · 0 repositories · arXiv:2405.14010
-
Global Motion Understanding in Large-Scale Video Object Segmentation 11 May 2024 · 0 repositories · arXiv:2405.07031
-
Space-time Reinforcement Network for Video Object Segmentation 7 May 2024 · 0 repositories · arXiv:2405.04042
-
LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation 30 Apr 2024 · 1 repository · arXiv:2404.19326
-
PM-VIS: High-Performance Box-Supervised Video Instance Segmentation 22 Apr 2024 · 0 repositories · arXiv:2404.13863
-
Dynamic in Static: Hybrid Visual Correspondence for Self-Supervised Video Object Segmentation 21 Apr 2024 · 1 repository · arXiv:2404.13505
-
Event-assisted Low-Light Video Object Segmentation 2 Apr 2024 · 1 repository · arXiv:2404.01945
-
Motion-Boundary-Driven Unsupervised Surgical Instrument Segmentation in Low-Quality Optical Flow 15 Mar 2024 · 1 repository · arXiv:2403.10039
-
OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework 13 Mar 2024 · 0 repositories · arXiv:2403.08682
-
The Ebb and Flow of Brand Loyalty: A 28-Year Bibliometric and Content Analysis 20 Feb 2024 · 0 repositories · arXiv:2402.13177
-
Point-VOS: Pointing Up Video Object Segmentation 8 Feb 2024 · 0 repositories · arXiv:2402.05917
-
UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces 25 Dec 2023 · 2 repositories · arXiv:2312.15715Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples) · 2 pointer-only (licence)
-
TAM-VT: Transformation-Aware Multi-scale Video Transformer for Segmentation and Tracking 13 Dec 2023 · 0 repositories · arXiv:2312.08514
-
Flexible visual prompts for in-context learning in computer vision 11 Dec 2023 · 1 repository · arXiv:2312.06592
-
Swap distance minimization in SOV languages. Cognitive and mathematical foundations 7 Dec 2023 · 0 repositories · arXiv:2312.04219
-
Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation 29 Nov 2023 · 1 repository · arXiv:2311.17893Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 12 harvested samples) · 12 pointer-only (licence)
-
Sketch-based Video Object Segmentation: Benchmark and Analysis 13 Nov 2023 · 0 repositories · arXiv:2311.07261
-
Learning the What and How of Annotation in Video Object Segmentation 8 Nov 2023 · 0 repositories · arXiv:2311.04414
-
SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution 23 Oct 2023 · 0 repositories · arXiv:2310.15115
-
Putting the Object Back into Video Object Segmentation 19 Oct 2023 · 1 repository · arXiv:2310.12982Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)
-
CoralVOS: Dataset and Benchmark for Coral Video Segmentation 3 Oct 2023 · 0 repositories · arXiv:2310.01946
-
Segmenting the motion components of a video: A long-term unsupervised model 2 Oct 2023 · 0 repositories · arXiv:2310.01040
-
Memory-Efficient Continual Learning Object Segmentation for Long Video 26 Sep 2023 · 0 repositories · arXiv:2309.15274
-
Adversarial Attacks on Video Object Segmentation with Hard Region Discovery 25 Sep 2023 · 0 repositories · arXiv:2309.13857
-
Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation 21 Sep 2023 · 0 repositories · arXiv:2309.11707
-
PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation 21 Sep 2023 · 1 repository · arXiv:2309.12303
-
Test-time Training for Matching-based Video Object Segmentation 21 Sep 2023 · 0 repositories
-
Robust Visual Tracking by Motion Analyzing 6 Sep 2023 · 0 repositories · arXiv:2309.03247
-
Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation 25 Aug 2023 · 1 repository · arXiv:2308.13266
-
Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation 25 Aug 2023 · 0 repositories · arXiv:2308.13505
-
Scalable Video Object Segmentation with Simplified Framework 19 Aug 2023 · 0 repositories · arXiv:2308.09903
-
Hierarchical Spatiotemporal Transformers for Video Object Segmentation 17 Jul 2023 · 0 repositories · arXiv:2307.08263
-
FODVid: Flow-guided Object Discovery in Videos 10 Jul 2023 · 0 repositories · arXiv:2307.04392
-
Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation 25 May 2023 · 1 repository · arXiv:2305.16318
-
Video Object Segmentation in Panoptic Wild Scenes 8 May 2023 · 2 repositories · arXiv:2305.04470Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Robust and Efficient Memory Network for Video Object Segmentation 24 Apr 2023 · 0 repositories · arXiv:2304.11840
-
Boosting Video Object Segmentation via Space-time Correspondence Learning 13 Apr 2023 · 1 repository · arXiv:2304.06211
-
CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning 9 Apr 2023 · 1 repository · arXiv:2304.04259
-
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks 2 Apr 2023 · 1 repository · arXiv:2304.00571
-
Reliability-Hierarchical Memory Network for Scribble-Supervised Video Object Segmentation 25 Mar 2023 · 1 repository · arXiv:2303.14384
-
Two-shot Video Object Segmentation 21 Mar 2023 · 1 repository · arXiv:2303.12078
-
Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation 17 Mar 2023 · 1 repository · arXiv:2303.10100
-
MOSE: A New Dataset for Video Object Segmentation in Complex Scenes 3 Feb 2023 · 1 repository · arXiv:2302.01872Syntology official (archive's flag): 6 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 12 harvested samples) · 6 pointer-only (licence)
-
Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation 29 Jan 2023 · 0 repositories · arXiv:2301.12352
-
Segment Every Reference Object in Spatial and Temporal Spaces 1 Jan 2023 · 0 repositories
-
Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions 1 Jan 2023 · 1 repository
-
Video Object Segmentation-aware Video Frame Interpolation 1 Jan 2023 · 1 repository
-
Video State-Changing Object Segmentation 1 Jan 2023 · 1 repository
-
Look Before You Match: Instance Understanding Matters in Video Object Segmentation 13 Dec 2022 · 0 repositories · arXiv:2212.06826
-
Breaking the "Object" in Video Object Segmentation 12 Dec 2022 · 0 repositories · arXiv:2212.06200
-
Dual Prototype Attention for Unsupervised Video Object Segmentation 22 Nov 2022 · 1 repository · arXiv:2211.12036
-
LVOS: A Benchmark for Long-term Video Object Segmentation 18 Nov 2022 · 1 repository · arXiv:2211.10181
-
Decoupling Features in Hierarchical Propagation for Video Object Segmentation 18 Oct 2022 · 2 repositories · arXiv:2210.09782
-
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation 4 Sep 2022 · 2 repositories · arXiv:2209.03138Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximization 22 Aug 2022 · 1 repository · arXiv:2208.10128
-
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation 1 Aug 2022 · 0 repositories · arXiv:2208.01159
-
Region Aware Video Object Segmentation with Deep Motion Modeling 21 Jul 2022 · 0 repositories · arXiv:2207.10258
-
Tackling Background Distraction in Video Object Segmentation 14 Jul 2022 · 1 repository · arXiv:2207.06953Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)
-
Towards Grand Unification of Object Tracking 14 Jul 2022 · 1 repository · arXiv:2207.07078Syntology official (archive's flag): 5 ran · 6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
Towards Robust Video Object Segmentation with Adaptive Object Calibration 2 Jul 2022 · 1 repository · arXiv:2207.00887Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
5th Place Solution for YouTube-VOS Challenge 2022: Video Object Segmentation 20 Jun 2022 · 0 repositories · arXiv:2206.09585
-
Differentiable Soft-Masked Attention 1 Jun 2022 · 1 repository · arXiv:2206.00182
-
Boosting Video Object Segmentation based on Scale Inconsistency 2 May 2022 · 1 repository · arXiv:2205.01197
-
Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging 22 Apr 2022 · 0 repositories · arXiv:2204.10846
-
Learning Video Salient Object Detection Progressively from Unlabeled Videos 5 Apr 2022 · 1 repository · arXiv:2204.02008
-
Scalable Video Object Segmentation with Identification Mechanism 22 Mar 2022 · 2 repositories · arXiv:2203.11442
-
VOS: Learning What You Don't Know by Virtual Outlier Synthesis 2 Feb 2022 · 2 repositories · arXiv:2202.01197Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 3 pointer-only (licence)
-
Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easier 23 Dec 2021 · 0 repositories · arXiv:2112.12402
-
HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images 16 Dec 2021 · 1 repository · arXiv:2112.09131
-
MUNet: Motion Uncertainty-aware Semi-supervised Video Object Segmentation 29 Nov 2021 · 0 repositories · arXiv:2111.14646
-
FAMINet: Learning Real-time Semi-supervised Video Object Segmentation with Steepest Optimized Optical Flow 20 Nov 2021 · 1 repository · arXiv:2111.10531
-
FlowVOS: Weakly-Supervised Visual Warping for Detail-Preserving and Temporally Consistent Single-Shot Video Object Segmentation 20 Nov 2021 · 0 repositories · arXiv:2111.10621
-
Dense Unsupervised Learning for Video Segmentation 11 Nov 2021 · 1 repository · arXiv:2111.06265Syntology official (archive's flag): 6 ran · 6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
-
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic Perspective 2 Nov 2021 · 1 repository · arXiv:2111.01323
-
Pixel-Level Bijective Matching for Video Object Segmentation 4 Oct 2021 · 1 repository · arXiv:2110.01644
-
Towards Unknown-aware Learning with Virtual Outlier Synthesis 29 Sep 2021 · 0 repositories
-
Space Time Recurrent Memory Network 14 Sep 2021 · 0 repositories · arXiv:2109.06474
-
Full-Duplex Strategy for Video Object Segmentation 6 Aug 2021 · 1 repository · arXiv:2108.03151Syntology official (archive's flag): 7 ran · 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)
-
Video Object Segmentation Using Global and Instance Embedding Learning 19 Jun 2021 · 0 repositories
Tasks archive 2025-07-28
20 shown of 76 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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