Browse State-of-the-Art › Video Semantic Segmentation
Video Semantic Segmentation
418 papers with code · 5 benchmarks · 8 datasets archive 2025-07-28
The goal of video semantic segmentation is to assign a predefined class to each pixel in all frames of a video. This requires the model not only to predict accurate segmentation masks but also to ensure that these masks remain temporally consistent across frames. This task has broad applications in areas such as autonomous driving, medical video analysis, and AR/VR.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 5 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; 0 placed): VSPW (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Cityscapes val (9 rows) | TMANet-50 | Temporal Memory Attention for Video Semantic Segmentation | code | — | Compare |
| CamVid (6 rows) | TMANet-50 | Temporal Memory Attention for Video Semantic Segmentation | code | — | Compare |
| VSPW (5 rows) | DVIS++(VIT-L) | DVIS++: Improved Decoupled Framework for Universal Video Segmentation | code | — | Compare |
| LaRS (3 rows) | WaSR-T (ResNet-101) | LaRS: A Diverse Panoptic Maritime Obstacle Detection Dataset and Benchmark | code | — | Compare |
| Multispectral Video Semantic Segmentation (3 rows) | MVNet(DeepLabV3) | Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline | code | — | Compare |
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
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 895 · with a code link: 418 · where Syntology ran a sample: 116 (95 with a run with no instrument failure, 21 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (116 of 895 tagged: 95 with a run with no instrument failure, 21 where every run was a failure of Syntology's instrument)
Page 1 of 9: papers 1 to 100 of 895, 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.
-
4 Dec 2016 67 repositories listed Syntology community repositories only · 21 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified (of 29 harvested samples) · 5 pointer-only (licence)Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
-
20 May 2016 37 repositories listedConvolutional networks are powerful visual models that yield hierarchies of features.
-
1 Aug 2024 11 repositories listed Syntology official (archive's flag): 3 ran · 40 ran (of which 9 constructed an object rather than computing a result; 29 with no instrument failure: 2 honoured, 0 violated, 27 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified (of 49 harvested samples) · 8 pointer-only (licence)We present Segment Anything Model 2 (SAM 2), a foundation model towards solving promptable visual segmentation in images and videos.
-
20 Dec 2021 6 repositories listed Syntology community repositories only · 6 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; 6 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline.
-
31 Mar 2021 5 repositories listed Syntology 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)To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning.
-
14 Mar 2021 5 repositories listed Syntology official (archive's flag): 2 ran · 10 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified (of 18 harvested samples)We present Modular interactive VOS (MiVOS) framework which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance.
-
24 Jul 2018 5 repositories listed Syntology 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 15 harvested samples) · 3 pointer-only (licence)We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations.
-
20 Sep 2023 4 repositories listedThis paper studies the unsupervised domain adaption (UDA) for echocardiogram video segmentation, where the goal is to generalize the model trained on the source domain to other unlabelled target domains.
-
3 Dec 2020 4 repositories listedIn the semi-supervised setting, the first mask of each object is provided at test time.
-
16 Jul 2020 4 repositories listed Syntology official (archive's flag): 3 ran · 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 15 harvested samples)The global transfer module conveys the segmentation information in an annotated frame to a target frame, while the local transfer module propagates the segmentation information in a temporally adjacent frame to the…
-
28 Nov 2018 4 repositories listed Syntology official (archive's flag): 8 ran · 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 1 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified (of 14 harvested samples) · 3 pointer-only (licence)Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage.
-
3 Sep 2018 4 repositories listedEnd-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset…
-
28 Mar 2017 4 repositories listedOur approach is suitable for both single and multiple object segmentation.
-
29 Mar 2024 3 repositories listed Syntology community repositories only · 2 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; 1 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 3 pointer-only (licence)Modern video segmentation methods adopt object queries to perform inter-frame association and demonstrate satisfactory performance in tracking continuously appearing objects despite large-scale motion and transient…
-
13 Apr 2023 3 repositories listedIn SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs).
-
6 Apr 2023 3 repositories listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples) · 5 pointer-only (licence)We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images.
-
26 Sep 2022 3 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets.
-
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation9 Jun 2021 3 repositories listed Syntology official: harvested, nothing ran · 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 6 samples that ran constructed an object rather than computing a result (of 10 harvested samples) · 2 pointer-only (licence)This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation.
-
30 Apr 2020 3 repositories listedWe describe our development and show the use of our solver in a video segmentation task and meta-learning for few-shot learning.
-
1 Apr 2019 3 repositories listed Syntology 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)In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory.
-
25 Feb 2019 3 repositories listed Syntology community repositories only · 9 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; 1 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples) · 1 pointer-only (licence)Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use.
-
24 Oct 2018 3 repositories listedThere already exist several semantic segmentation datasets for comparison among semantic segmentation methods in complex urban scenes, such as the Cityscapes and CamVid datasets, where the side views of the objects are…
-
1 Aug 2017 3 repositories listedSpecifically, our Video Object Segmentation with Re-identification (VS-ReID) model includes a mask propagation module and a ReID module.
-
23 Nov 2016 3 repositories 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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable.
-
3 May 2025 2 repositories listedManual annotation of volumetric medical images, such as magnetic resonance imaging (MRI) and computed tomography (CT), is a labor-intensive and time-consuming process.
-
10 Dec 2024 2 repositories listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 4 unverified (of 6 harvested samples)In this work, we focus on semi-supervised learning for video action detection.
-
25 Sep 2024 2 repositories listedTo bridge this gap, we take a step forward by proposing the first large-scale multi-modal underwater camouflaged object tracking dataset, namely UW-COT220.
-
16 Jul 2024 2 repositories listed Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)In this paper, we introduce a new task, Reasoning Video Object Segmentation (ReasonVOS).
-
24 Jun 2024 2 repositories listedMoreover, we provide a new motion expression guided video segmentation dataset MeViS to study the natural language-guided video understanding in complex environments.
-
25 Dec 2023 2 repositories listed Syntology 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)We evaluate our unified models on various benchmarks.
-
30 Nov 2023 2 repositories listed
-
18 Aug 2023 2 repositories listed
-
29 Jul 2023 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
17 Jul 2023 2 repositories listed
-
21 Jun 2023 2 repositories listed
-
8 May 2023 2 repositories listed Syntology 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)
-
28 Apr 2023 2 repositories listed
-
23 Mar 2023 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
22 Feb 2023 2 repositories listed
-
18 Oct 2022 2 repositories listed
-
9 Sep 2022 2 repositories listed
-
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)
-
21 Jul 2022 2 repositories listed Syntology community repositories only · 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) · 2 unverified (of 5 harvested samples)
-
14 Jul 2022 2 repositories listed Syntology official: harvested, nothing 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) · 2 unverified (of 3 harvested samples) · 2 pointer-only (licence)
-
22 Mar 2022 2 repositories listed
-
21 Mar 2022 2 repositories listed
-
8 Mar 2022 2 repositories listed Syntology official (archive's flag): 3 ran · 9 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; 6 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples)
-
29 Nov 2021 2 repositories listed Syntology official (archive's flag): 9 ran · 9 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; 5 where Syntology's instrument failed) · 2 unverified (of 11 harvested samples) · 6 pointer-only (licence)
-
15 Nov 2021 2 repositories listed
-
24 Oct 2021 2 repositories listed
-
26 Jul 2021 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
4 Jun 2021 2 repositories listed
-
26 Jan 2021 2 repositories listed
-
12 Oct 2020 2 repositories listed Syntology official (archive's flag): 3 ran · 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 3 pointer-only (licence)
-
11 Jul 2020 2 repositories listed
-
1 Jun 2020 2 repositories listed
-
25 Mar 2020 2 repositories listed
-
18 Mar 2020 2 repositories listed
-
27 Feb 2020 2 repositories listed
-
18 Feb 2020 2 repositories listed
-
19 Aug 2019 2 repositories listed Syntology official (archive's flag): 8 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 12 harvested samples) · 1 pointer-only (licence)
-
2 Apr 2019 2 repositories listed Syntology 4 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; 4 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
19 Nov 2018 2 repositories listed
-
6 Jun 2018 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
1 Jun 2018 2 repositories listed
-
8 Dec 2016 2 repositories listed Syntology 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 3 pointer-only (licence)
-
28 Jun 2025 1 repository listed
-
15 Jun 2025 1 repository listed
-
5 Jun 2025 1 repository listed
-
2 Jun 2025 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
26 May 2025 1 repository listed
-
26 May 2025 1 repository listed
-
24 May 2025 1 repository listed
-
20 May 2025 1 repository listed Syntology official (archive's flag): 1 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
2 May 2025 1 repository listed
-
18 Apr 2025 1 repository listed
-
16 Apr 2025 1 repository listed
-
14 Apr 2025 1 repository listed
-
10 Apr 2025 1 repository listed Syntology 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)
-
7 Apr 2025 1 repository listed
-
4 Apr 2025 1 repository listed
-
1 Apr 2025 1 repository listed
-
30 Mar 2025 1 repository listed
-
26 Mar 2025 1 repository listed
-
25 Mar 2025 1 repository listed
-
19 Mar 2025 1 repository listed Syntology official (archive's flag): 25 ran · 25 ran (of which 15 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified (of 39 harvested samples) · 39 pointer-only (licence)
-
19 Mar 2025 1 repository listed
-
19 Mar 2025 1 repository listed
-
18 Mar 2025 1 repository listed
-
5 Mar 2025 1 repository listed
-
28 Feb 2025 1 repository listed
-
12 Feb 2025 1 repository listed
-
10 Feb 2025 1 repository listed
-
23 Jan 2025 1 repository listed Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified (of 16 harvested samples) · 1 pointer-only (licence)
-
19 Jan 2025 1 repository listed
-
17 Jan 2025 1 repository listed
-
14 Jan 2025 1 repository listed
-
13 Jan 2025 1 repository listed Syntology official: no sample here; runs from other or unrecorded repositories · 7 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)
-
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning12 Jan 2025 1 repository listed
Syntology lines on 39 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