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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2301.02657")

Code

Syntology Ran 0 of 6 code samples harvested from 1 repository linked to this paper; 6 have no recorded run.

By repository: official repository: 6 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Ali2500/TarViS officialmentioned in papermentioned on GitHubpytorchMIT 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; 0 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6unverified

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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

cat Ali2500/TarViS/tarvis/modelling/point_sampling_utils.py official repository unverified MIT (permissive) · 723587c9b01223c1 · report
compute_padded_dims Ali2500/TarViS/tarvis/modelling/utils.py official repository unverified MIT (permissive) · ca3f23e7a9f1011a · report
compute_padding Ali2500/TarViS/tarvis/modelling/utils.py official repository unverified MIT (permissive) · 3117cc9941298e0c · report
point_sample Ali2500/TarViS/tarvis/modelling/point_sampling_utils.py official repository unverified MIT (permissive) · 35425cfa0d3f34a7 · report
point_sample_3d Ali2500/TarViS/tarvis/modelling/point_sampling_utils.py official repository unverified MIT (permissive) · a29da2f7b8a01b44 · report
split_by_query_group Ali2500/TarViS/tarvis/modelling/utils.py official repository unverified MIT (permissive) · 70f1b932a11d5437 · 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