no code implementations • 3 Aug 2023 • Saleem Ahmed, Pengyu Yan, David Doermann, Srirangaraj Setlur, Venu Govindaraju
A combination of sparse and dense per-pixel objectives coupled with a uni-modal self-attention-based feature-fusion layer is applied to learn KP embeddings.
1 code implementation • 3 Aug 2023 • Saleem Ahmed, Bhavin Jawade, Shubham Pandey, Srirangaraj Setlur, Venu Govindaraju
We present a comprehensive study of chart visual question-answering(QA) task, to address the challenges faced in comprehending and extracting data from chart visualizations within documents.
Ranked #3 on Chart Question Answering on RealCQA (using extra training data)
1 code implementation • 7 May 2023 • Pengyu Yan, Saleem Ahmed, David Doermann
As a prerequisite of chart data extraction, the accurate detection of chart basic elements is essential and mandatory.