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 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="2403.19407")

Code

Syntology Ran 14 of 15 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 8 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bo-miao/HTR 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

15 samples harvested; 14 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran · fixture could not drive it
8ran
1unverified

Licence: 0 of the 15 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 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. “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.

aligned_bilinear bo-miao/HTR/models/htr.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 29dbbaafa4be18e1 · report
box_cxcywh_to_xyxy bo-miao/HTR/inference_davis.py official repository ran fingerprinted MIT (permissive) · ef1a3e10a9dbf4a9 · report
compute_list_and bo-miao/HTR/get_mcs.py official repository ran fingerprinted MIT (permissive) · d09cc4c762bea5ad · report
compute_list_mean bo-miao/HTR/get_mcs.py official repository ran fingerprinted MIT (permissive) · 1acc2d14b5949a5e · report
compute_locations bo-miao/HTR/models/htr.py official repository ran · honoured contract MIT (permissive) · ed1a308adb65f645 · report
dice_loss bo-miao/HTR/models/segmentation.py official repository ran · violated contract fingerprinted MIT (permissive) · ac8fe530cdad4d8c · report
get_norm bo-miao/HTR/models/segmentation.py official repository ran MIT (permissive) · 480db93fba382e34 · report
parse_dynamic_params bo-miao/HTR/models/htr.py official repository ran MIT (permissive) · 46f34dc9f9a94b67 · report
pick_key_frames_id bo-miao/HTR/inference_davis.py official repository ran fingerprinted MIT (permissive) · bd254b679b58f849 · report
rescale_bboxes bo-miao/HTR/inference_davis.py official repository ran fingerprinted MIT (permissive) · 2626a807bce7587a · report
sigmoid_focal_loss bo-miao/HTR/models/segmentation.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5c0711aada67957e · report
vos_dice_loss bo-miao/HTR/models/criterion.py official repository ran MIT (permissive) · 50c37a861e9c7b30 · report
window_partition bo-miao/HTR/models/swin_transformer.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · f9fd6241d935f07b · report
window_reverse bo-miao/HTR/models/swin_transformer.py official repository ran · our draft was wrong MIT (permissive) · fb32094c6dbece71 · report
evaluate_mcs bo-miao/HTR/get_mcs.py official repository 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