Datasets › UMVM
UMVM
We present a further analysis of visual modality incompleteness, benchmarking latest MMEA models on our proposed dataset MMEA-UMVM.
To create our MMEA-UMVM(uncertainly missing visual modality) datasets, we perform random image dropping on MMEA datasets. Specifically, we randomly discard entity images to achieve varying degrees of visual modality missing, ranging from 0.05 to the maximum R_(img) of the raw datasets with a step of 0.05 or 0.1. Finally, we get a total number of 97 data split.
Refer to the following paper for more details: Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment
Benchmarks archive 2025-07-28
All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Multi-modal Entity Alignment | UMVM-dbp-fr-en | UMAEA (w/o surf) Hits@1 0.873 | Rethinking Uncertainly Missing and Ambiguous Visual... | zjukg/umaea | 10 | Compare |
| Multi-modal Entity Alignment | UMVM-dbp-ja-en | UMAEA (w/o surf) Hits@1 0.857 | Rethinking Uncertainly Missing and Ambiguous Visual... | zjukg/umaea | 10 | Compare |
| Multi-modal Entity Alignment | UMVM-dbp-zh-en | UMAEA (w/o surf) Hits@1 0.856 | Rethinking Uncertainly Missing and Ambiguous Visual... | zjukg/umaea | 10 | Compare |
Papers archive 2025-07-28
5 shown of 5 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 6. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment | 1 | 6 | 30 Jul 2023 | ran 5 of 14 samples (9 unverified) |
| MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid | 1 | 6 | 29 Dec 2022 | ran 5 of 13 samples (8 unverified) |
| Multi-modal Contrastive Representation Learning for Entity Alignment | 1 | 6 | 2 Sep 2022 | ran 3 of 10 samples (7 unverified) |
| Multi-modal Siamese Network for Entity Alignment | 1 | 6 | 14 Aug 2022 | not harvested |
| Visual Pivoting for (Unsupervised) Entity Alignment | 2 | 6 | 28 Sep 2020 | ran 3 of 9 samples (6 unverified) |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- UMVM-oea-en-fr
- UMVM-oea-en-de
- UMVM-oea-d-w-v2
- UMVM-oea-d-w-v1
- UMVM-dbp-fr-en
- UMVM-dbp-ja-en
- UMVM-dbp-zh-en
- UMVM
8 variant names, as the archive lists them.
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