Database Paper Browser

Back to papers

Improving Information Extraction from Visually Rich Documents using Visual Span Representations

Summary: Artemis, a visually aware IE method for heterogeneous visually rich documents, encodes visual+textual+layout context into fixed-length span representations. Minimal supervision for visual-span boundaries; multimodal embeddings boost IE, up to 17 F1 points on four datasets. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID
12597
Venue
VLDB
Year
2021
Pagerank
4.3690661e-05
Overall Rank
9,252 | 35.64%
DOI
10.14778/3446095.3446104

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank Citing Paper Year Venue Pagerank
10,126 Visual Template Inference for Data Extraction from Documents 2026 SIGMOD 4.1945683e-05
11,256 Self-Training for Label-Efficient Information Extraction from Semi-Structured Web-Pages 2023 VLDB 4.1945683e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 6 of 6 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