Research map / Vision-language and multimodal / Visual question answering
Classification-Regression for Chart Comprehension
Matan Levy, Rami Ben-Ari, Dani Lischinski
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add legend marker input to visual branch (ablation) | CRCT-10% · PlotQA-D1 test (trained on 10% of D1) | overall accuracy: 50.45 -> 57.75 | Improved |
| add textual class label embeddings (ablation) | CRCT-10% · PlotQA-D1 test (trained on 10% of D1) | regression accuracy: 15.51 -> 20.74 | Improved |
| add visual class label embeddings (ablation) | CRCT-10% · PlotQA-D1 test (trained on 10% of D1) | regression accuracy: 17.35 -> 20.74 | Improved |
| add visual class embedding (ablation) | CRCT-10% · PlotQA-D1 test (trained on 10% of D1) | classification accuracy: 73.68 -> 72.86 | Hurt |
| add visual class embedding (ablation) | CRCT-10% · PlotQA-D1 test (trained on 10% of D1) | overall accuracy: 57.36 -> 57.75 | Improved |
| add full visual features beyond bounding box coordinates (ablation) | CRCT-10% · PlotQA-D1 test (trained on 10% of D1) | overall accuracy: 54.19 -> 57.75 | Improved |
| use a unified classification-regression network instead of two pipelines (ablation) | CRCT-10% · PlotQA-D1 test (trained on 10% of D1) | overall accuracy: 53.64 -> 57.75 | Improved |
| use ground-truth detections instead of detector outputs (ablation) | CRCT · PlotQA-D1 test | accuracy | No clear effect |
| add quantized Y-tick answers to PReFIL classification head | PReFIL · PlotQA-D1 test | accuracy | Improved |
| reduce CRCT training data to 10% of PlotQA-D1 (ablation) | CRCT · PlotQA-D1 test | overall accuracy: 76.94 -> 57.75 | Hurt |
Closest papers by meaning
- Synthesize Step-by-Step: Tools Templates and LLMs as Data Generators for Reasoning-Based Chart VQA (CVPR 2024 · similarity 0.89)
- Union Is Strength! Unite the Power of LLMs and MLLMs for Chart Question Answering (AAAI 2025 · similarity 0.88)
- EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding (AAAI 2025 · similarity 0.87)
- ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models (NeurIPS 2025 · similarity 0.87)
- InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts (NeurIPS 2025 · similarity 0.87)
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding (CVPR 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
