Research map / Vision-language and multimodal / Human and embodied modeling
Heterogeneous Graph Learning for Visual Commonsense Reasoning
Weijiang Yu, Jingwen Zhou, Weihao Yu, Xiaodan Liang, Nong Xiao
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 CVM to HGL (ablation) | HGL · VCR val Q→A | accuracy: 68.4 -> 69.4 | Improved |
| add CVM to HGL (ablation) | HGL · VCR val QA→R | accuracy: 69.7 -> 70.6 | Improved |
| add CVM to HGL (ablation) | HGL · VCR val Q→AR | accuracy: 48.3 -> 49.1 | Improved |
| add QAHG to HGL (ablation) | HGL · VCR val Q→A | accuracy: 67.8 -> 69.4 | Improved |
| add QAHG to HGL (ablation) | HGL · VCR val QA→R | accuracy: 69.9 -> 70.6 | Improved |
| add QAHG to HGL (ablation) | HGL · VCR val Q→AR | accuracy: 48.2 -> 49.1 | Improved |
| add VAHG to HGL (ablation) | HGL · VCR val Q→A | accuracy: 68.0 -> 69.4 | Improved |
| add VAHG to HGL (ablation) | HGL · VCR val QA→R | accuracy: 68.8 -> 70.6 | Improved |
| add VAHG to HGL (ablation) | HGL · VCR val Q→AR | accuracy: 48.0 -> 49.1 | Improved |
| add CVM to the baseline (ablation) | Baseline · VCR val Q→A | accuracy: 63.8 -> 65.6 | Improved |
| add CVM to the baseline (ablation) | Baseline · VCR val QA→R | accuracy: 67.2 -> 68.4 | Improved |
| add QAHG to the baseline (ablation) | Baseline · VCR val Q→A | accuracy: 63.8 -> 66.1 | Improved |
Closest papers by meaning
- Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models (ICML 2025 · similarity 0.90)
- Multimodal Commonsense Knowledge Distillation for Visual Question Answering (Student Abstract) (AAAI 2025 · similarity 0.89)
- GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning (NeurIPS 2024 · similarity 0.88)
- VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs (CVPR 2026 · similarity 0.88)
- GraphVis: Boosting LLMs with Visual Knowledge Graph Integration (NeurIPS 2024 · similarity 0.88)
- VGR: Visual Grounded Reasoning (ICLR 2026 · similarity 0.87)
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.
