Research map / Vision-language and multimodal / Human and embodied modeling
Image Captioning with Context-Aware Auxiliary Guidance
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CAAG to AoANet | AoANet · MSCOCO Karpathy test split | CIDEr-D: 129.8 -> 132.2 | Helped |
| Add CAAG to Up-Down | Up-Down · MSCOCO Karpathy test split | CIDEr-D: 120.1 -> 128.8 | Helped |
| Add CAAG to Att2all | Att2all · MSCOCO Karpathy test split | CIDEr-D: 114.0 -> 121.7 | Helped |
| Add CAAG to AoANet | AoANet · MSCOCO official test server (c40) | CIDEr-D: 129.6 -> 130.7 | Helped |
| Add CAAG, but do not use it during inference (ablation) | Up-Down · MSCOCO Karpathy test split | CIDEr-D: 123.4 -> 126.7 | Helped |
| Use the advantage-based CAAG objective instead of cross-entropy (ablation) | Up-Down+CAAG · MSCOCO Karpathy test split | CIDEr-D: 127.2 -> 128.8 | Helped |
| Use soft attention instead of hard attention over global-context tokens (ablation) | Up-Down+CAAG · MSCOCO Karpathy test split | CIDEr-D: 127.5 -> 128.8 | Helped |
| Add CAAG to Up-Down (ablation) | Up-Down · MSCOCO Karpathy test split | CIDEr-D: 123.4 -> 128.8 | Helped |
Closest papers by meaning
- CALVIN: Improved Contextual Video Captioning via Instruction Tuning (NeurIPS 2024 · similarity 0.87)
- Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning (CVPR 2025 · similarity 0.86)
- Noise-Aware Image Captioning with Progressively Exploring Mismatched Words (AAAI 2024 · similarity 0.86)
- FlexCap: Describe Anything in Images in Controllable Detail (NeurIPS 2024 · similarity 0.86)
- CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning (ICLR 2026 · similarity 0.85)
- BalCapRL : A Balanced Framework for RL-Based MLLM Image Captioning (NeurIPS 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.