Browse State-of-the-Art › Unsupervised Video Object Segmentation
Unsupervised Video Object Segmentation
52 papers with code · 6 benchmarks · 8 datasets archive 2025-07-28
The unsupervised scenario assumes that the user does not interact with the algorithm to obtain the segmentation masks. Methods should provide a set of object candidates with no overlapping pixels that span through the whole video sequence. This set of objects should contain at least the objects that capture human attention when watching the whole video sequence i.e objects that are more likely to be followed by human gaze.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
6 leaderboard tables shown for this task, 6 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 1 placed): DAVIS 2016 val (1 judged, 1 placed), YouTube-Objects (1 judged, 0 placed), FBMS test (1 judged, 1 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “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. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is 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. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
8 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 89 · with a code link: 52 · where Syntology ran a sample: 13 (13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (13 of 89 tagged: 13 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 89 of 89, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “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 figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
29 Sep 2019 3 repositories listedTo handle the nonrigid background like a sea, we also propose a robust fusion mechanism between motion and appearance-based features.
-
21 Jun 2023 2 repositories listedOnline unsupervised video object segmentation (UVOS) uses the previous frames as its input to automatically separate the primary object(s) from a streaming video without using any further manual annotation.
-
4 Sep 2022 2 repositories listed Syntology 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)Unsupervised video object segmentation (VOS) aims to detect the most salient object in a video sequence at the pixel level.
-
15 Nov 2021 2 repositories listedWe further show that D2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
-
18 Feb 2020 2 repositories listedRecent interest in self-supervised dense tracking has yielded rapid progress, but performance still remains far from supervised methods.
-
26 Sep 2019 2 repositories listed Syntology official (archive's flag): 18 ran · 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 1 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified (of 23 harvested samples) · 2 pointer-only (licence)Our learning process integrates two highly related tasks: tracking large image regions and establishing fine-grained pixel-level associations between consecutive video frames.
-
19 Nov 2018 2 repositories listedWe investigate the problem of strictly unsupervised video object segmentation, i. e., the separation of a primary object from background in video without a user-provided object mask or any training on an annotated…
-
14 Jan 2025 1 repository listedIn this paper, we address the challenges in unsupervised video object segmentation (UVOS) by proposing an efficient algorithm, termed MTNet, which concurrently exploits motion and temporal cues.
-
26 Sep 2023 1 repository listedUnsupervised video object segmentation (VOS) is a task that aims to detect the most salient object in a video without external guidance about the object.
-
7 Sep 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 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) · 3 unverified (of 10 harvested samples) · 10 pointer-only (licence)To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic…
-
22 May 2023 1 repository listedExtensive experiments on the DAVIS2017-unsupervised and YoutubeVIS19&21 datasets demonstrate the superior performance of UVOSAM without mask supervision compared to existing mask-supervised methods, as well as its…
-
17 Apr 2023 1 repository listedThe Gestalt law of common fate, i. e., what move at the same speed belong together, has inspired unsupervised object discovery based on motion segmentation.
-
18 Mar 2023 1 repository listedIn the static object predictor, the RGB source is converted to depth and static saliency sources, simultaneously.
-
15 Mar 2023 1 repository listedUnsupervised video object segmentation aims to segment the most prominent object in a video sequence.
-
22 Nov 2022 1 repository listedUnsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos.
-
19 Sep 2022 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 2 pointer-only (licence)We propose a simple, yet powerful approach for unsupervised object segmentation in videos.
-
8 Sep 2022 1 repository listedThe proposed model effectively extracts the RGB and motion information by extracting superpixel-based component prototypes from the input RGB images and optical flow maps.
-
18 Jul 2022 1 repository listedOptical flow is an easily conceived and precious cue for advancing unsupervised video object segmentation (UVOS).
-
6 Apr 2022 1 repository listedUnsupervised video object segmentation (UVOS) aims at automatically separating the primary foreground object(s) from the background in a video sequence.
-
29 Mar 2022 1 repository listedBy contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual quality of training data and is not robust to object deformation.
-
15 Dec 2021 1 repository listedThe main novelty of the proposed model is that the autoencoder is also trained to predict the background noise, which allows to compute for each frame a pixel-dependent threshold to perform the foreground segmentation.
-
15 Nov 2021 1 repository listedWe further show that D^2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
-
11 Nov 2021 1 repository listed Syntology 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)On established VOS benchmarks, our approach exceeds the segmentation accuracy of previous work despite using significantly less training data and compute power.
-
11 Aug 2021 1 repository listedIn this paper, we propose a novel multi-source fusion network for zero-shot video object segmentation.
-
6 Aug 2021 1 repository listed Syntology 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)Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues.
-
19 Jun 2021 1 repository listedAdditionally, to exclude the information of the moving background objects from motion features, our transformation module enables to reciprocally transform the appearance features to enhance the motion features, so as…
-
25 Mar 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 5 pointer-only (licence)Video instance segmentation (VIS) aims to segment and associate all instances of predefined classes for each frame in videos.
-
5 Jan 2021 1 repository listedWe efficiently handle problems present in existing methods such as drift while temporal propagation, tracking and addition of new objects.
-
1 Jan 2021 1 repository listedHow to make the appearance and motion information interact effectively to accommodate complex scenarios is a fundamental issue in flow-based zero-shot video object segmentation.
-
26 Aug 2020 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples)On the other hand, 3D convolutional networks have been successfully applied for video classification tasks, but have not been leveraged as effectively to problems involving dense per-pixel interpretation of videos…
-
20 Aug 2020 1 repository listed
-
26 May 2020 1 repository listed
-
18 Mar 2020 1 repository listed
-
10 Mar 2020 1 repository listed Syntology 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) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
9 Mar 2020 1 repository listed
-
19 Jan 2020 1 repository listed
-
19 Jan 2020 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
24 Oct 2019 1 repository listed
-
12 Aug 2019 1 repository listed
-
5 Jul 2019 1 repository listed Syntology 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) · 0 unverified (of 3 harvested samples)
-
1 Jun 2019 1 repository listed
-
2 May 2019 1 repository listed
-
18 Mar 2019 1 repository listed
-
13 Mar 2019 1 repository listed
-
17 Oct 2018 1 repository listed
-
9 Oct 2018 1 repository listed
-
1 Sep 2018 1 repository listed
-
20 May 2018 1 repository listed
-
20 Sep 2017 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
18 Apr 2017 1 repository listed
-
Saliency-Motion Guided Trunk-Collateral Network for Unsupervised Video Object Segmentation8 Apr 2025 0 repositories listed
-
16 Jul 2024 0 repositories listed
-
25 Jan 2024 0 repositories listed
-
SimulFlow: Simultaneously Extracting Feature and Identifying Target for Unsupervised Video Object Segmentation30 Nov 2023 0 repositories listed
-
Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation21 Sep 2023 0 repositories listed
-
Tsanet: Temporal and Scale Alignment for Unsupervised Video Object Segmentation8 Mar 2023 0 repositories listed
-
Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation29 Jan 2023 0 repositories listed
-
Flow-guided Semi-supervised Video Object Segmentation25 Jan 2023 0 repositories listed
-
Unsupervised Video Object Segmentation with Online Adversarial Self-Tuning1 Jan 2023 0 repositories listed
-
Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy17 Dec 2022 0 repositories listed
-
Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance10 Nov 2022 0 repositories listed
-
1 Sep 2022 0 repositories listed
-
23 Dec 2021 0 repositories listed
-
Learning To Segment Dominant Object Motion From Watching Videos28 Nov 2021 0 repositories listed
-
Video Salient Object Detection via Contrastive Features and Attention Modules3 Nov 2021 0 repositories listed
-
1 Jan 2021 0 repositories listed
-
4 Dec 2020 0 repositories listed
-
DyStaB: Unsupervised Object Segmentation via Dynamic-Static Bootstrapping16 Aug 2020 0 repositories listed
-
4 Aug 2020 0 repositories listed
-
1 Aug 2020 0 repositories listed
-
Global Optimality Guarantees for Nonconvex Unsupervised Video Segmentation9 Jul 2019 0 repositories listed
-
Key Instance Selection for Unsupervised Video Object Segmentation18 Jun 2019 0 repositories listed
-
Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation19 Dec 2018 0 repositories listed
-
Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation13 Dec 2018 0 repositories listed
-
4 Sep 2018 0 repositories listed
-
1 Sep 2018 0 repositories listed
-
1 Sep 2018 0 repositories listed
-
Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos24 Mar 2018 0 repositories listed
-
Instance Embedding Transfer to Unsupervised Video Object Segmentation3 Jan 2018 0 repositories listed
-
Learning to Segment Moving Objects1 Dec 2017 0 repositories listed
-
Primary Object Segmentation in Videos Based on Region Augmentation and Reduction1 Jul 2017 0 repositories listed
-
19 Apr 2017 0 repositories listed
-
FusionSeg: Learning to combine motion and appearance for fully automatic segmention of generic objects in videos19 Jan 2017 0 repositories listed
-
Learning Motion Patterns in Videos21 Dec 2016 0 repositories listed
-
Primary Object Segmentation in Videos via Alternate Convex Optimization of Foreground and Background Distributions1 Jun 2016 0 repositories listed
-
Motion Trajectory Segmentation via Minimum Cost Multicuts1 Dec 2015 0 repositories listed
-
Causal Video Object Segmentation From Persistence of Occlusions1 Jun 2015 0 repositories listed
Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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