Papers › Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and...

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

14 Mar 2021CVPR 2021 1arXiv:2103.07941archive 2025-07-28

Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang

We present Modular interactive VOS (MiVOS) framework which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance. Trained separately, the interaction module converts user interactions to an object mask, which is then temporally propagated by our propagation module using a novel top-k filtering strategy in reading the space-time memory. To effectively take the user's intent into account, a novel difference-aware module is proposed to learn how to properly fuse the masks before and after each interaction, which are aligned with the target frames by employing the space-time memory. We evaluate our method both qualitatively and quantitatively with different forms of user interactions (e.g., scribbles, clicks) on DAVIS to show that our method outperforms current state-of-the-art algorithms while requiring fewer frame interactions, with the additional advantage in generalizing to different types of user interactions. We contribute a large-scale synthetic VOS dataset with pixel-accurate segmentation of 4.8M frames to accompany our source codes to facilitate future research.

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="2103.07941")

Code

Syntology Ran 9 of 18 code samples harvested from 4 repositories linked to this paper; 9 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 2 ran; community (archive-listed): 14 samples from 3 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hkchengrex/MiVOS officialmentioned on GitHubpytorch report
Vujas-Eteph/CiVOS mentioned on GitHubpytorch report
hkchengrex/Mask-Propagation mentioned on GitHubpytorch report
hkchengrex/Scribble-to-Mask mentioned on GitHubpytorch report
limingxing00/rde-vos-cvpr2022 mentioned 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

18 samples harvested; 9 ran; 0 honoured the contract we drafted; 9 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.

3ran · our draft was wrong
2ran · fixture could not drive it
4ran
9unverified

Licence: 0 of the 18 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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.

AttentionMemory hkchengrex/MiVOS/model/propagation/prop_net.py official repository ran MIT (permissive) · e72b80185fd5e21a · report
softmax_w_g_top hkchengrex/MiVOS/model/propagation/prop_net.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · ada9a3eef6b445bd · report
EvalMemoryReader hkchengrex/MiVOS/model/propagation/prop_net.py official repository unverified MIT (permissive) · 9958d67d9d027e4f · report
PropagationNetwork hkchengrex/MiVOS/model/propagation/prop_net.py official repository unverified MIT (permissive) · b9081800a0d70e91 · report
AttentionMemory Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · 9a8a4b812337da11 · report
EvalMemoryReader Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) ran · metamorphic tier: deterministic BSD-3-Clause (permissive) · d7a09a5e37f31c1e · report
MemoryReader hkchengrex/Mask-Propagation/model/network.py community (archive-listed) ran fingerprinted MIT (permissive) · d9ba63b1718e1e05 · report
aggregate_wbg Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) ran · fixture could not drive it fingerprinted BSD-3-Clause (permissive) · d763f9348cf73778 · report
make_gaussian Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) ran · our draft was wrong BSD-3-Clause (permissive) · de847b7a64641452 · report
pad_divide_by Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) ran · fixture could not drive it fingerprinted BSD-3-Clause (permissive) · 29ef75051beaf38a · report
softmax_w_g_top Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 7d8c831d1808fdcc · report
Decoder Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) unverified BSD-3-Clause (permissive) · 3c2bb88e4d9e2e6f · report
FusionNet Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) unverified BSD-3-Clause (permissive) · 3d4477934fb35965 · report
InferenceCore Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) unverified BSD-3-Clause (permissive) · 1f74746f70cfb8ea · report
MemoryReader limingxing00/rde-vos-cvpr2022/model/network.py community (archive-listed) unverified MIT (permissive) · 8cb186830eed0c02 · report
PropagationNetwork Vujas-Eteph/CiVOS/inference_core.py community (archive-listed) unverified BSD-3-Clause (permissive) · 2d76453bfdfe5c8f · report
PropagationNetwork hkchengrex/Mask-Propagation/model/network.py community (archive-listed) unverified MIT (permissive) · 046904ddbd853941 · report
RDE_VOS limingxing00/rde-vos-cvpr2022/model/network.py community (archive-listed) unverified MIT (permissive) · afa77ff620b598c6 · report

Tasks

Interactive Video Object SegmentationSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Datasets

Introduced by this paper, per the archive.

BL30K

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Interactive Video Object Segmentation DAVIS 2017 MiVOS AUC-J 0.849 #1 of 7 Archive leaderboard report
Interactive Video Object Segmentation DAVIS 2017 MiVOS AUC-J&F 0.879 #1 of 7 Archive leaderboard report
Interactive Video Object Segmentation DAVIS 2017 MiVOS J&F@60s 0.885 #1 of 7 Archive leaderboard report
Interactive Video Object Segmentation DAVIS 2017 MiVOS J@60s 0.854 #1 of 7 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS F-measure (Decay) 5.1 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS F-measure (Mean) 92.4 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS F-measure (Recall) 96.4 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS J&F 91.0 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS Jaccard (Decay) 6.6 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS Jaccard (Mean) 89.7 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS Jaccard (Recall) 97.5 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 MiVOS Speed (FPS) 16.9 #22 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MiVOS F-measure (Decay) 14.5 #30 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MiVOS F-measure (Mean) 80.2 #30 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MiVOS F-measure (Recall) 87.6 #30 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MiVOS J&F 76.5 #30 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MiVOS Jaccard (Decay) 14.9 #30 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MiVOS Jaccard (Mean) 72.7 #30 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) MiVOS Jaccard (Recall) 81.2 #30 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS F-measure (Decay) 8.2 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS F-measure (Mean) 87.4 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS F-measure (Recall) 93.1 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS J&F 84.5 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS Jaccard (Decay) 7.0 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS Jaccard (Mean) 81.7 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS Jaccard (Recall) 90.9 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) MiVOS Speed (FPS) 11.2 #28 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 MiVOS F-Measure (Seen) 84.7 #34 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 MiVOS F-Measure (Unseen) 85.5 #34 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 MiVOS Jaccard (Seen) 80.6 #34 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 MiVOS Jaccard (Unseen) 77.3 #34 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 MiVOS Overall 82.0 #34 of 53 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

Introduced by this paper: MiVOS

MiVOSVOS

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