Papers › Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation

Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation

4 Apr 2024CVPR 2024 1arXiv:2404.03645archive 2025-07-28

Shuting He, Henghui Ding

Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and directly perform identification at the video-level, mixing up static image-level cues with temporal motion cues. However, image-level features cannot well comprehend motion cues in sentences, and static cues are not crucial for temporal perception. In fact, static cues can sometimes interfere with temporal perception by overshadowing motion cues. In this work, we propose to decouple video-level referring expression understanding into static and motion perception, with a specific emphasis on enhancing temporal comprehension. Firstly, we introduce an expression-decoupling module to make static cues and motion cues perform their distinct role, alleviating the issue of sentence embeddings overlooking motion cues. Secondly, we propose a hierarchical motion perception module to capture temporal information effectively across varying timescales. Furthermore, we employ contrastive learning to distinguish the motions of visually similar objects. These contributions yield state-of-the-art performance across five datasets, including a remarkable 9.2 𝒥&ℱ improvement on the challenging MeViS dataset. Code is available at https://github.com/heshuting555/DsHmp.

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="2404.03645")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

heshuting555/dshmp officialmentioned in papermentioned on GitHubpytorch 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

7 samples harvested; 2 ran; 0 honoured the contract we drafted; 5 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.

2ran
5unverified

Licence: 7 of the 7 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 heshuting555/DsHmp. “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.

default_argument_parser heshuting555/DsHmp/dshmp/engine/defaults.py official repository ran no licence file found · pointer only · 9835cf213d40b39e · report
multi_pos_cross_entropy heshuting555/DsHmp/dshmp/modeling/contrastive_loss.py official repository ran fingerprinted no licence file found · pointer only · 596ba9632eba6fdb · report
batch_dice_loss heshuting555/DsHmp/dshmp/modeling/vita_matcher.py official repository unverified no licence file found · pointer only · bc2cb481a75c370d · report
batch_sigmoid_ce_loss heshuting555/DsHmp/dshmp/modeling/vita_matcher.py official repository unverified no licence file found · pointer only · 1edd24985036b0bf · report
calculate_uncertainty heshuting555/DsHmp/dshmp/modeling/vita_criterion.py official repository unverified no licence file found · pointer only · 2dcb8123d89bb1ff · report
dice_loss heshuting555/DsHmp/dshmp/modeling/vita_criterion.py official repository unverified no licence file found · pointer only · 89f75e54ff128be0 · report
sigmoid_ce_loss heshuting555/DsHmp/dshmp/modeling/vita_criterion.py official repository unverified no licence file found · pointer only · d0c61e8dba511aa3 · report

Tasks

Contrastive LearningReferring ExpressionReferring Expression SegmentationReferring Video Object SegmentationSentenceSentence EmbeddingsVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) DsHmp (Video-Swin-Base) F 69.1 #11 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) DsHmp (Video-Swin-Base) J 65 #11 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) DsHmp (Video-Swin-Base) J&F 67.1 #11 of 33 Archive leaderboard report
Referring Video Object Segmentation MeViS DsHmp F 49.8 #8 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS DsHmp J 43 #8 of 16 Archive leaderboard report
Referring Video Object Segmentation MeViS DsHmp J&F 46.4 #8 of 16 Archive leaderboard report
Referring Video Object Segmentation Ref-DAVIS17 DsHmp F 68.1 #5 of 11 Archive leaderboard report
Referring Video Object Segmentation Ref-DAVIS17 DsHmp J 61.7 #5 of 11 Archive leaderboard report
Referring Video Object Segmentation Ref-DAVIS17 DsHmp J&F 64.9 #5 of 11 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

Contrastive Learning

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