Papers › Language as Queries for Referring Video Object Segmentation

Language as Queries for Referring Video Object Segmentation

3 Jan 2022CVPR 2022 1arXiv:2201.00487archive 2025-07-28

Jiannan Wu, Yi Jiang, Peize Sun, Zehuan Yuan, Ping Luo

Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames. In this work, we propose a simple and unified framework built upon Transformer, termed ReferFormer. It views the language as queries and directly attends to the most relevant regions in the video frames. Concretely, we introduce a small set of object queries conditioned on the language as the input to the Transformer. In this manner, all the queries are obligated to find the referred objects only. They are eventually transformed into dynamic kernels which capture the crucial object-level information, and play the role of convolution filters to generate the segmentation masks from feature maps. The object tracking is achieved naturally by linking the corresponding queries across frames. This mechanism greatly simplifies the pipeline and the end-to-end framework is significantly different from the previous methods. Extensive experiments on Ref-Youtube-VOS, Ref-DAVIS17, A2D-Sentences and JHMDB-Sentences show the effectiveness of ReferFormer. On Ref-Youtube-VOS, Refer-Former achieves 55.6J&F with a ResNet-50 backbone without bells and whistles, which exceeds the previous state-of-the-art performance by 8.4 points. In addition, with the strong Swin-Large backbone, ReferFormer achieves the best J&F of 64.2 among all existing methods. Moreover, we show the impressive results of 55.0 mAP and 43.7 mAP on A2D-Sentences andJHMDB-Sentences respectively, which significantly outperforms the previous methods by a large margin. Code is publicly available at https://github.com/wjn922/ReferFormer.

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 8 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 7 ran (3 with no instrument failure; 4 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

wjn922/referformer officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 8 samples, 7 ran (4 instrument-failed) · 1 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

8 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 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 · honoured contract
3ran · our draft was wrong
1ran; the contract check could not run
2ran
1unverified

Licence: 8 of the 8 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 wjn922/referformer. “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.

wjn922/referformer official repository 8 samples, 7 ran (4 instrument-failed) · 1 unverified
aligned_bilinear in 17 papers models/referformer.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 29dbbaafa4be18e1 · report fixture: signature tensor:Tensor/4/float, factor:int/0/int · returned Tensor · level recorded 2026-09-22
box_cxcywh_to_xyxy in 60 papers inference_davis.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · ef1a3e10a9dbf4a9 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_locations in 14 papers models/referformer.py ran · honoured contract Apache-2.0 recorded; this copy not marked cleared · pointer only · ed1a308adb65f645 · report fixture: signature h:int/0/int, w:int/0/int, device:device/0/?, stride:int/0/int · returned Tensor · level recorded, date not recorded
dice_coef in 18 papers models/matcher.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 6296ea80154ae7f9 · report fixture: signature inputs:Tensor/4/float, targets:Tensor/4/float · returned Tensor · level recorded 2026-09-24
parse_dynamic_params in 14 papers models/referformer.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · 46f34dc9f9a94b67 · report fixture: signature params:Tensor/2/float, channels:int/0/int, weight_nums:list/1/int, bias_nums:list/1/int · returned tuple · level recorded 2026-09-22
rescale_bboxes in 13 papers inference_davis.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 2626a807bce7587a · report fixture: signature out_bbox:Tensor/2/float, size:tuple/1/int · returned Tensor · level recorded 2026-09-24
sigmoid_focal_coef models/matcher.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 9502374fe12f11e4 · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, alpha:float/0/float, gamma:int/0/int · returned Tensor · level recorded 2026-09-24
vis_add_mask in 6 papers inference_davis.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · ccbe959ea69981ad · report

Tasks

ObjectObject TrackingReferring Expression SegmentationReferring Video Object SegmentationSemantic SegmentationVideo Instance SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) AP 0.550 #3 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) IoU mean 0.703 #3 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) IoU overall 0.786 #3 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) Precision@0.5 0.831 #3 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) Precision@0.6 0.804 #3 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) Precision@0.7 0.741 #3 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) Precision@0.8 0.579 #3 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences ReferFormer (Video-Swin-B) Precision@0.9 0.212 #3 of 27 Archive leaderboard report
Referring Expression Segmentation DAVIS 2017 (val) ReferFormer J&F 1st frame 61.1 #7 of 18 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) ReferFormer (ResNet-101) F 58.4 #25 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) ReferFormer (ResNet-101) J 56.1 #25 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) ReferFormer (ResNet-101) J&F 57.3 #25 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) ReferFormer (ResNet-50) F 56.6 #27 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) ReferFormer (ResNet-50) J 54.8 #27 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) ReferFormer (ResNet-50) J&F 55.6 #27 of 33 Archive leaderboard report
Referring Video Object Segmentation MeViS ReferFormer F 32.2 #13 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS ReferFormer J 29.8 #13 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS ReferFormer J&F 31.0 #13 of 16 Archive leaderboard report
Referring Video Object Segmentation ReVOS ReferFormer (Video-Swin-B) F 29.9 #7 of 9 Archive leaderboard report
Referring Video Object Segmentation ReVOS ReferFormer (Video-Swin-B) J 26.2 #7 of 9 Archive leaderboard report
Referring Video Object Segmentation ReVOS ReferFormer (Video-Swin-B) J&F 28.1 #7 of 9 Archive leaderboard report
Referring Video Object Segmentation ReVOS ReferFormer (Video-Swin-B) R 8.8 #7 of 9 Archive leaderboard report
Referring Video Object Segmentation Ref-DAVIS17 ReferFormer F 64.1 #9 of 11 Archive leaderboard report
Referring Video Object Segmentation Ref-DAVIS17 ReferFormer J 58.1 #9 of 11 Archive leaderboard report
Referring Video Object Segmentation Ref-DAVIS17 ReferFormer J&F 61.1 #9 of 11 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS ReferFormer (Large) F 64.6 #12 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS ReferFormer (Large) J 61.3 #12 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS ReferFormer (Large) J&F 62.9 #12 of 18 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.

Methods

Absolute Position EncodingsAdamAttentionBPEConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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