Papers › TarViS: A Unified Approach for Target-based Video Segmentation

TarViS: A Unified Approach for Target-based Video Segmentation

6 Jan 2023CVPR 2023 1arXiv:2301.02657archive 2025-07-28

Ali Athar, Alexander Hermans, Jonathon Luiten, Deva Ramanan, Bastian Leibe

The general domain of video segmentation is currently fragmented into different tasks spanning multiple benchmarks. Despite rapid progress in the state-of-the-art, current methods are overwhelmingly task-specific and cannot conceptually generalize to other tasks. Inspired by recent approaches with multi-task capability, we propose TarViS: a novel, unified network architecture that can be applied to any task that requires segmenting a set of arbitrarily defined 'targets' in video. Our approach is flexible with respect to how tasks define these targets, since it models the latter as abstract 'queries' which are then used to predict pixel-precise target masks. A single TarViS model can be trained jointly on a collection of datasets spanning different tasks, and can hot-swap between tasks during inference without any task-specific retraining. To demonstrate its effectiveness, we apply TarViS to four different tasks, namely Video Instance Segmentation (VIS), Video Panoptic Segmentation (VPS), Video Object Segmentation (VOS) and Point Exemplar-guided Tracking (PET). Our unified, jointly trained model achieves state-of-the-art performance on 5/7 benchmarks spanning these four tasks, and competitive performance on the remaining two. Code and model weights are available at: https://github.com/Ali2500/TarViS

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 1 repository linked to this paper: 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) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 6 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Ali2500/TarViS officialmentioned in papermentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested: 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) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
2unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Ali2500/TarViS. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Ali2500/TarViS official repository 6 samples, 4 ran (0 instrument-failed) · 2 unverified
cat in 32 papers tarvis/modelling/point_sampling_utils.py ran MIT (permissive) · 723587c9b01223c1 · report fixture: signature tensors:list/1/Tensor, dim:int/0/int · returned Tensor · level recorded 2026-09-25
compute_padded_dims tarvis/modelling/utils.py ran MIT (permissive) · ca3f23e7a9f1011a · report fixture: signature height:int/0/int, width:int/0/int, multiple_of:int/0/int · returned tuple · level recorded 2026-09-25
compute_padding tarvis/modelling/utils.py ran MIT (permissive) · 3117cc9941298e0c · report fixture: signature height:int/0/int, width:int/0/int, pad_multiple_of:int/0/int · returned tuple · level recorded 2026-09-25
split_by_query_group tarvis/modelling/utils.py ran MIT (permissive) · 70f1b932a11d5437 · report fixture: signature x:Tensor/3/float, dim:int/0/int, query_group_names:list/1/str, query_group_counts:list/1/int · returned dict · level recorded 2026-09-25
point_sample in 12 papers tarvis/modelling/point_sampling_utils.py unverified MIT (permissive) · 35425cfa0d3f34a7 · report
point_sample_3d tarvis/modelling/point_sampling_utils.py unverified MIT (permissive) · a29da2f7b8a01b44 · report

Tasks

Instance SegmentationPanoptic SegmentationSegmentationSemantic SegmentationVideo Instance SegmentationVideo Object SegmentationVideo Panoptic SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) TarViS F-measure (Mean) 88.5 #24 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) TarViS J&F 85.3 #24 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) TarViS Jaccard (Mean) 81.7 #24 of 81 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-L) AP50 67.8 #14 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-L) AP75 44.6 #14 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-L) AR1 18.0 #14 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-L) AR10 50.4 #14 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-L) mask AP 43.2 #14 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-T) AP50 55.0 #27 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-T) AP75 34.4 #27 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-T) AR1 16.1 #27 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-T) AR10 40.9 #27 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (Swin-T) mask AP 34.0 #27 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (ResNet-50) AP50 52.5 #29 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (ResNet-50) AP75 30.4 #29 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (ResNet-50) AR1 15.9 #29 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (ResNet-50) AR10 39.9 #29 of 44 Archive leaderboard report
Video Instance Segmentation OVIS validation TarViS (ResNet-50) mask AP 31.1 #29 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-L) AP50 81.4 #7 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-L) AP75 67.6 #7 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-L) AR1 47.6 #7 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-L) AR10 64.8 #7 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-L) mask AP 60.2 #7 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-T) AP50 71.6 #20 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-T) AP75 56.6 #20 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-T) AR1 42.2 #20 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-T) AR10 57.2 #20 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (Swin-T) mask AP 50.9 #20 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (ResNet-50) AP50 69.6 #22 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (ResNet-50) AP75 53.2 #22 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (ResNet-50) AR1 40.5 #22 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (ResNet-50) AR10 55.9 #22 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 TarViS (ResNet-50) mask AP 48.3 #22 of 26 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (Swin-L) VPQ 58.9 #4 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (Swin-L) VPQ (stuff) 69.9 #4 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (Swin-L) VPQ (thing) 43.7 #4 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (Swin-T) VPQ 58.0 #5 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (Swin-T) VPQ (stuff) 69.0 #5 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (Swin-T) VPQ (thing) 42.9 #5 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (ResNet-50) VPQ 53.3 #8 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (ResNet-50) VPQ (stuff) 66.0 #8 of 8 Archive leaderboard report
Video Panoptic Segmentation Cityscapes-VPS TarViS (ResNet-50) VPQ (thing) 35.9 #8 of 8 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (Swin-L) AQ 72.0 #2 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (Swin-L) SQ 72.0 #2 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (Swin-L) STQ 73.0 #2 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (Swin-T) AQ 71.2 #3 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (Swin-T) SQ 69.9 #3 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (Swin-T) STQ 70.6 #3 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (ResNet-50) AQ 70.3 #4 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (ResNet-50) SQ 68.8 #4 of 6 Archive leaderboard report
Video Panoptic Segmentation KITTI-STEP TarViS (ResNet-50) STQ 69.6 #4 of 6 Archive leaderboard report
Video Panoptic Segmentation VIPSeg TarViS (Swin-L) STQ 52.9 #9 of 12 Archive leaderboard report
Video Panoptic Segmentation VIPSeg TarViS (Swin-L) VPQ 48.0 #9 of 12 Archive leaderboard report
Video Panoptic Segmentation VIPSeg TarViS (Swin-T) STQ 45.3 #11 of 12 Archive leaderboard report
Video Panoptic Segmentation VIPSeg TarViS (Swin-T) VPQ 35.8 #11 of 12 Archive leaderboard report
Video Panoptic Segmentation VIPSeg TarViS (ResNet-50) STQ 43.1 #12 of 12 Archive leaderboard report
Video Panoptic Segmentation VIPSeg TarViS (ResNet-50) VPQ 33.5 #12 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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