Papers › Hierarchical Memory Matching Network for Video Object Segmentation

Hierarchical Memory Matching Network for Video Object Segmentation

23 Sep 2021ICCV 2021 10arXiv:2109.11404archive 2025-07-28

Hongje Seong, Seoung Wug Oh, Joon-Young Lee, Seongwon Lee, Suhyeon Lee, Euntai Kim

We present Hierarchical Memory Matching Network (HMMN) for semi-supervised video object segmentation. Based on a recent memory-based method [33], we propose two advanced memory read modules that enable us to perform memory reading in multiple scales while exploiting temporal smoothness. We first propose a kernel guided memory matching module that replaces the non-local dense memory read, commonly adopted in previous memory-based methods. The module imposes the temporal smoothness constraint in the memory read, leading to accurate memory retrieval. More importantly, we introduce a hierarchical memory matching scheme and propose a top-k guided memory matching module in which memory read on a fine-scale is guided by that on a coarse-scale. With the module, we perform memory read in multiple scales efficiently and leverage both high-level semantic and low-level fine-grained memory features to predict detailed object masks. Our network achieves state-of-the-art performance on the validation sets of DAVIS 2016/2017 (90.8% and 84.7%) and YouTube-VOS 2018/2019 (82.6% and 82.5%), and test-dev set of DAVIS 2017 (78.6%). The source code and model are available online: https://github.com/Hongje/HMMN.

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="2109.11404")

Code

Syntology Ran 5 of 8 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hongje/hmmn 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

8 samples harvested; 5 ran; 0 honoured the contract we drafted; 3 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.

5ran
3unverified

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 Hongje/HMMN. “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.

Decoder Hongje/HMMN/model.py official repository ran no licence file found · pointer only · 4d499c7a1c54839a · report
KeyValue Hongje/HMMN/model.py official repository ran fingerprinted no licence file found · pointer only · 3929cee794ef7996 · report
Memory Hongje/HMMN/model.py official repository ran no licence file found · pointer only · c73e4c9b0c5e54c7 · report
Memory_topk Hongje/HMMN/model.py official repository ran no licence file found · pointer only · 3c110faa7db7d2ff · report
Refine Hongje/HMMN/model.py official repository ran no licence file found · pointer only · 0aa276a048959a5a · report
Encoder_M Hongje/HMMN/model.py official repository unverified no licence file found · pointer only · 0b783799ea293620 · report
Encoder_Q Hongje/HMMN/model.py official repository unverified no licence file found · pointer only · 6d12e62e34457264 · report
HMMN Hongje/HMMN/model.py official repository unverified no licence file found · pointer only · e25774e68ee0a333 · report

Tasks

ObjectRetrievalSemantic SegmentationSemi-Supervised Video Object SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) HMMN D16 val (F) 90.6 #1 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) HMMN D16 val (G) 89.4 #1 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) HMMN D16 val (J) 88.2 #1 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) HMMN D17 val (F) 83.1 #1 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) HMMN D17 val (G) 80.4 #1 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) HMMN D17 val (J) 77.7 #1 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS (no YouTube-VOS training) HMMN FPS 10.0 #1 of 26 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 HMMN F-measure (Mean) 92.0 #24 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 HMMN J&F 90.8 #24 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2016 HMMN Jaccard (Mean) 89.6 #24 of 78 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) HMMN F-measure (Mean) 82.5 #24 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) HMMN J&F 78.6 #24 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (test-dev) HMMN Jaccard (Mean) 74.7 #24 of 59 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) HMMN F-measure (Mean) 87.5 #27 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) HMMN J&F 84.7 #27 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation DAVIS 2017 (val) HMMN Jaccard (Mean) 81.9 #27 of 81 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 HMMN F-Measure (Seen) 87.0 #31 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 HMMN F-Measure (Unseen) 84.6 #31 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 HMMN Jaccard (Seen) 82.1 #31 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 HMMN Jaccard (Unseen) 76.8 #31 of 53 Archive leaderboard report
Semi-Supervised Video Object Segmentation YouTube-VOS 2018 HMMN Overall 82.6 #31 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.

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