Papers › Temporally Consistent Referring Video Object Segmentation with Hybrid Memory

Temporally Consistent Referring Video Object Segmentation with Hybrid Memory

28 Mar 2024arXiv:2403.19407archive 2025-07-28

Bo Miao, Mohammed Bennamoun, Yongsheng Gao, Mubarak Shah, Ajmal Mian

Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS paradigm that explicitly models temporal instance consistency alongside the referring segmentation. Specifically, we introduce a novel hybrid memory that facilitates inter-frame collaboration for robust spatio-temporal matching and propagation. Features of frames with automatically generated high-quality reference masks are propagated to segment the remaining frames based on multi-granularity association to achieve temporally consistent R-VOS. Furthermore, we propose a new Mask Consistency Score (MCS) metric to evaluate the temporal consistency of video segmentation. Extensive experiments demonstrate that our approach enhances temporal consistency by a significant margin, leading to top-ranked performance on popular R-VOS benchmarks, i.e., Ref-YouTube-VOS (67.1%) and Ref-DAVIS17 (65.6%). The code is available at https://github.com/bo-miao/HTR.

PaperPDFCodeCode 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 15 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (4 with no instrument failure; 10 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. 2 of the 14 samples that ran have no recorded date.

bo-miao/HTR officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 14 ran (10 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

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 10 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 · violated contract
8ran · our draft was wrong
2ran; the contract check could not run
1unverified

Licence: 4 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from bo-miao/HTR. “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.

bo-miao/HTR official repository 15 samples, 14 ran (10 instrument-failed) · 1 unverified
aligned_bilinear in 17 papers models/htr.py ran · our draft was wrong fingerprinted MIT (permissive) · 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 MIT (permissive) here; the stored copy is pointer only · ef1a3e10a9dbf4a9 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_list_and get_mcs.py ran · our draft was wrong fingerprinted MIT (permissive) · d09cc4c762bea5ad · report fixture: signature x:list/1/int · returned int · level recorded 2026-09-24
compute_list_mean get_mcs.py ran · violated contract fingerprinted MIT (permissive) · 1acc2d14b5949a5e · report fixture: signature x:list/1/int · returned float · level recorded 2026-09-24
compute_locations in 14 papers models/htr.py ran · honoured contract MIT (permissive) here; the stored copy is 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_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/segmentation.py ran · violated contract fingerprinted MIT (permissive) · ac8fe530cdad4d8c · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int · returned Tensor · level recorded 2026-09-22
get_norm in 48 papers models/segmentation.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 480db93fba382e34 · report fixture: signature norm:str/0/str, out_channels:int/0/int · returned GroupNorm · level recorded 2026-09-24
parse_dynamic_params in 14 papers models/htr.py ran · our draft was wrong MIT (permissive) · 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
pick_key_frames_id inference_davis.py ran · violated contract fingerprinted MIT (permissive) · bd254b679b58f849 · report fixture: signature class_info:list/1/float · returned int · level recorded 2026-09-24
rescale_bboxes in 13 papers inference_davis.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 2626a807bce7587a · report fixture: signature out_bbox:Tensor/2/float, size:tuple/1/int · returned Tensor · level recorded 2026-09-24
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/segmentation.py ran · our draft was wrong fingerprinted MIT (permissive) · 5c0711aada67957e · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded, date not recorded
vos_dice_loss models/criterion.py ran · our draft was wrong MIT (permissive) · 50c37a861e9c7b30 · report fixture: signature input_mask:Tensor/4/float, cls_gt:Tensor/3/float · returned Tensor · level recorded 2026-09-24
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/swin_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · f9fd6241d935f07b · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-22
window_reverse in 296 papers models/swin_transformer.py ran · our draft was wrong MIT (permissive) · fb32094c6dbece71 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
evaluate_mcs get_mcs.py unverified MIT (permissive) · f6cb67c029ab76f1 · report

Tasks

HTRObjectReferring Expression SegmentationReferring Video Object SegmentationSegmentationSemantic SegmentationVideo Object SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation DAVIS 2017 (val) HTR J&F 1st frame 65.6 #4 of 18 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) HTR (Pre-training) F 68.9 #10 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) HTR (Pre-training) J 65.3 #10 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) HTR (Pre-training) J&F 67.1 #10 of 33 Archive leaderboard report
Referring Video Object Segmentation MeViS HTR F 45.5 #9 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS HTR J 39.9 #9 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS HTR J&F 42.7 #9 of 16 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS HTR F 68.9 #5 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS HTR J 65.3 #5 of 18 Archive leaderboard report
Referring Video Object Segmentation Refer-YouTube-VOS HTR J&F 67.1 #5 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.

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