chore: update locked deps (#1239)
Some checks failed
Run Docs CD / build-deploy-docs (push) Failing after 1m27s
Run Docs CI / build-docs (push) Failing after 51s

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-03-25 15:48:02 +01:00
committed by GitHub
parent 825b226fab
commit 38b7108a22
13 changed files with 460 additions and 442 deletions

View File

@@ -51,6 +51,8 @@ To meet the design criteria listed above, we developed a new model called TableF
The paper is structured as follows. In Sec. 2, we give a brief overview of the current state-of-the-art. In Sec. 3, we describe the datasets on which we train. In Sec. 4, we introduce the TableFormer model-architecture and describe
$^{1}$https://github.com/IBM/SynthTabNet
its results &amp; performance in Sec. 5. As a conclusion, we describe how this new model-architecture can be re-purposed for other tasks in the computer-vision community.
## 2. Previous work and State of the Art
@@ -393,6 +395,8 @@ phan cell.
Aditional images with examples of TableFormer predictions and post-processing can be found below.
Figure 8: Example of a table with multi-line header.
Figure 9: Example of a table with big empty distance between cells.
<!-- image -->
@@ -403,8 +407,12 @@ Figure 10: Example of a complex table with empty cells.
<!-- image -->
Figure 11: Simple table with different style and empty cells.
<!-- image -->
Figure 12: Simple table predictions and post processing.
Figure 13: Table predictions example on colorful table.
<!-- image -->
@@ -425,6 +433,8 @@ Figure 15: Example with triangular table.
<!-- image -->
Figure 16: Example of how post-processing helps to restore mis-aligned bounding boxes prediction artifact.
Figure 17: Example of long table. End-to-end example from initial PDF cells to prediction of bounding boxes, post processing and prediction of structure.
<!-- image -->