Research map / Detection and segmentation / Open-set and few-shot detection
InfoDet: A Dataset for Infographic Element Detection
Jiangning Zhu, Yuxing Zhou, Zheng Wang, Juntao Yao, Yima Gu, Yuhui Yuan, Shixia Liu
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 grounded CoT (detected boxes plus text descriptions) over Direct prompting | o4-mini · ChartQAPro overall | enhanced relaxed accuracy: 63.2 -> 64.9 | Improved |
| add grounded CoT over Direct prompting | o1 · ChartQAPro overall | enhanced relaxed accuracy: 61.4 -> 64.1 | Improved |
| add grounded CoT over Direct prompting | o3 · ChartQAPro overall | enhanced relaxed accuracy: 60.6 -> 61.6 | Improved |
| use standard CoT or PoT prompting | o1, o3, o4-mini · ChartQAPro overall | enhanced relaxed accuracy: o4-mini 63.2 -> 62.5 (CoT), 59.7 (PoT) | No clear effect |
| combine visual and textual prompts instead of visual only (ablation) | grounded CoT on o1 · ChartQAPro overall | enhanced relaxed accuracy: 62.8 -> 64.1 | Improved |
| combine visual and textual prompts instead of textual only (ablation) | grounded CoT on o1 · ChartQAPro overall | enhanced relaxed accuracy: 61.6 -> 64.1 | Improved |
| separate visual prompt into two layers (charts/HROs and texts) (ablation) | grounded CoT on o1 · ChartQAPro overall | enhanced relaxed accuracy: 62.3 -> 64.1 | Improved |
| add in-context examples to grounded CoT (ablation) | grounded CoT on o1 · ChartQAPro overall | enhanced relaxed accuracy: 64.1 -> 61.5 | Hurt |
| few-shot prompting with annotated example infographics | foundation detectors · InfoDet element-level | AP: MQ-GLIP chart AP 13.5 -> 16.2 | No clear effect |
| fine-tune on full InfoDet training set instead of 4-shot (ablation) | Co-DETR · InfoDet element-level | chart AP: 27.6 -> 88.2 | Improved |
| fine-tune traditional detector on InfoDet rather than zero-shot foundation model | Faster R-CNN vs DINO-X · InfoDet element-level chart AP | chart AP: 14.0 -> 78.9 | Improved |
| pre-train on InfoDet in addition to ImageNet-22K, Objects365, COCO (ablation) | InternImage · Rico | detection score: 51.8 -> 53.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation (ICLR 2026 · similarity 0.89)
- InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts (NeurIPS 2025 · similarity 0.87)
- Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection (NeurIPS 2026 · similarity 0.87)
- ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding (CVPR 2026 · similarity 0.86)
- EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding (AAAI 2025 · similarity 0.85)
- ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing (ICML 2026 · similarity 0.85)
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.
