Search Results for author:
Found 3 papers, 2 papers with code
SpaDen : Sparse and Dense Keypoint Estimation for Real-World Chart Understanding
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.
RealCQA: Scientific Chart Question Answering as a Test-bed for First-Order Logic
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)
Context-Aware Chart Element Detection
As a prerequisite of chart data extraction, the accurate detection of chart basic elements is essential and mandatory.
