Database Paper Browser

Back to papers

OpenMEL: Unsupervised Multimodal Entity Linking Using Noise-Free Expanded Queries and Global Coherence

Summary: OpenMEL: unsupervised MEL that expands noisy multimodal mentions with full-context and external knowledge plus three-level visual inputs for adaptive denoising. Ranks entities by a bounded-node maximum spanning-tree (tree cover) solved by a greedy algorithm with provable guarantees, yielding SOTA on three benchmarks. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13892
Venue
VLDB
Year
2025
Pagerank
4.1945683e-05
Overall Rank
10,615 | 26.16%
DOI
10.14778/3742728.3742740

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 7 of 7 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers