Papers › UniVS: Unified and Universal Video Segmentation with Prompts as Queries

UniVS: Unified and Universal Video Segmentation with Prompts as Queries

28 Feb 2024CVPR 2024 1arXiv:2402.18115archive 2025-07-28

Minghan Li, Shuai Li, Xindong Zhang, Lei Zhang

Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts throughout the entire video, making it hard to handle the different tasks with the same architecture. We make an attempt to address these issues and present a novel unified VS architecture, namely UniVS, by using prompts as queries. UniVS averages the prompt features of the target from previous frames as its initial query to explicitly decode masks, and introduces a target-wise prompt cross-attention layer in the mask decoder to integrate prompt features in the memory pool. By taking the predicted masks of entities from previous frames as their visual prompts, UniVS converts different VS tasks into prompt-guided target segmentation, eliminating the heuristic inter-frame matching process. Our framework not only unifies the different VS tasks but also naturally achieves universal training and testing, ensuring robust performance across different scenarios. UniVS shows a commendable balance between performance and universality on 10 challenging VS benchmarks, covering video instance, semantic, panoptic, object, and referring segmentation tasks. Code can be found at https://github.com/MinghanLi/UniVS.

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 14 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 12 ran (9 with no instrument failure; 3 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

minghanli/univs officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 12 ran (3 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

14 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 3 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
3ran · our draft was wrong
8ran
2unverified

Licence: 14 of the 14 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 minghanli/univs. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

minghanli/univs official repository 14 samples, 12 ran (3 instrument-failed) · 2 unverified
batch_dice_coefficient_loss univs/modeling/video_matcher.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b4a2ff2dcc61c4d4 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float · returned Tensor · level recorded 2026-09-24
batch_dice_loss in 60 papers univs/modeling/video_matcher.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a03c334f626ed752 · report fixture: signature inputs:Tensor/4/float, targets:Tensor/4/float · returned Tensor · level recorded 2026-09-24
contrastive_aux_loss univs/univs_prompt_longvideo.py ran no licence file found · pointer only · 0c3ac5c5ab657973 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, pos_topk:int/0/int, topk:int/0/int · returned Tensor · level recorded 2026-09-24
contrastive_loss in 80 papers
census: 11 implementations from 18 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
univs/univs_prompt_longvideo.py ran no licence file found · pointer only · bb2f0ddf9840604b · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/bool, pos_topk:int/0/int, topk:int/0/int · returned Tensor · level recorded 2026-09-24
convert_box_to_mask univs/univs_prompt.py ran no licence file found · pointer only · e9937e82c9c52d3d · report fixture: signature outputs_box:Tensor/3/float, h:int/0/int, w:int/0/int · returned Tensor · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
univs/modeling/video_criterion.py ran fingerprinted no licence file found · pointer only · 63d3c6e9af5b08f8 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-24
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket
univs/modeling/video_criterion_prompt.py ran fingerprinted no licence file found · pointer only · 535792a3fc3afb99 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float, need_sigmoid:bool/0/bool · returned Tensor · level recorded 2026-09-24
is_semseg_dataset univs/prepare_targets.py ran · violated contract no licence file found · pointer only · 92c5b183ff2beae6 · report fixture: signature dataset_name:str/0/str · returned bool · level recorded 2026-09-24
sigmoid_ce_loss in 70 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
univs/modeling/video_criterion.py ran fingerprinted no licence file found · pointer only · 450b62615caa903a · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-24
sigmoid_ce_loss in 70 papers
census: 4 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
univs/modeling/video_criterion_prompt.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 46b849406325dd41 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-24
sigmoid_ce_with_weight_loss univs/modeling/video_criterion.py ran fingerprinted no licence file found · pointer only · db2f336362cda7c8 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, weights:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-24
sigmoid_ce_wo_logits_loss univs/modeling/video_criterion_prompt.py ran no licence file found · pointer only · 1a3d5d8a73ce293d · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_masks:float/0/float · returned Tensor · level recorded 2026-09-24
batch_sigmoid_ce_loss in 48 papers univs/modeling/video_matcher.py unverified no licence file found · pointer only · 1edd24985036b0bf · report
copy_TeacherNet_weights univs/utils/copy_TeacherNet_weights.py unverified no licence file found · pointer only · 770dbf8ac853d862 · report

Tasks

DecoderReferring Expression SegmentationReferring Video Object SegmentationVideo Instance SegmentationVideo Object SegmentationVideo Object TrackingVideo Panoptic SegmentationVideo SegmentationVideo Semantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation DAVIS 2017 (val) UniVS(Swin-L) J&F 1st frame 59.4? #17 of 18 Archive leaderboard report
Referring Expression Segmentation DAVIS 2017 (val) UniVS(Swin-L) J&F Full video 59.4 #17 of 18 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniVS(Swin-L) F 59.5 #24 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniVS(Swin-L) J 56.8 #24 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) UniVS(Swin-L) J&F 58.0 #24 of 33 Archive leaderboard report
Video Instance Segmentation OVIS validation UniVS(Swin-L) mask AP 41.7 #18 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 UniVS(Swin-L) AP50 79.4 #12 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 UniVS(Swin-L) AP75 63.3 #12 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 UniVS(Swin-L) AR1 46.2 #12 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 UniVS(Swin-L) AR10 63.1 #12 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS 2021 UniVS(Swin-L) mask AP 57.9 #12 of 26 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation UniVS(Swin-L) AP50 82.1 #7 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation UniVS(Swin-L) AP75 65.3 #7 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation UniVS(Swin-L) AR1 54.7 #7 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation UniVS(Swin-L) AR10 66.8 #7 of 44 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation UniVS(Swin-L) mask AP 60.0 #7 of 44 Archive leaderboard report
Video Object Segmentation DAVIS 2017 (val) UniVS(Swin-L) F-measure 79.5 #14 of 17 Archive leaderboard report
Video Object Segmentation DAVIS 2017 (val) UniVS(Swin-L) Jaccard 72.8 #14 of 17 Archive leaderboard report
Video Object Segmentation DAVIS 2017 (val) UniVS(Swin-L) Mean Jaccard & F-Measure 76.2 #14 of 17 Archive leaderboard report
Video Object Segmentation YouTube-VOS 2018 UniVS(Swin-L) Mean Jaccard & F-Measure 71.5 #13 of 17 Archive leaderboard report
Video Panoptic Segmentation VIPSeg UniVS(Swin-L) STQ 58.2 #8 of 12 Archive leaderboard report
Video Panoptic Segmentation VIPSeg UniVS(Swin-L) VPQ 49.3 #8 of 12 Archive leaderboard report
Video Semantic Segmentation VSPW UniVS(Swin-L) mIoU 59.8 #2 of 5 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