ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation.
Chufan ShiCheng YangYaxin LiuBo ShuiJunjie WangMohan JingLinran XuXinyu ZhuSiheng LiYuxiang ZhangGongye LiuXiaomei NieDeng CaiYujiu YangPublished in: CoRR (2024)
Keyphrases
- cross modal
- code generation
- multi modal
- perceptual information
- application development
- software development
- model driven
- modeling language
- multimedia retrieval
- multimedia databases
- knowledge base
- formal specification
- rapid prototyping
- visual recognition
- image retrieval
- software reuse
- visual data
- visual similarity
- design patterns
- multimedia
- high dimensional
- object detection
- data processing
- data management
- data driven
- data sets
- visual features