Research map / Vision-language and multimodal / Human and embodied modeling
RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words
Check 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 Grid-Augmented geometry features to the base Transformer (ablation) | Image captioning with ResNext101 grid features · MSCOCO | CIDEr: 131.2 -> 132.1 | Helped |
| Add Adaptive Attention to the base Transformer (ablation) | Image captioning with ResNext101 grid features · MSCOCO | CIDEr: 131.2 -> 132.6 | Helped |
| Add both Grid-Augmented and Adaptive Attention modules (ablation) | Image captioning with ResNext101 grid features · MSCOCO | CIDEr: 131.2 -> 133.3 | Helped |
| Add Grid-Augmented geometry features to the base Transformer (ablation) | Image captioning with ResNext152 grid features · MSCOCO | CIDEr: 133.2 -> 134.2 | Helped |
| Add Adaptive Attention to the base Transformer (ablation) | Image captioning with ResNext152 grid features · MSCOCO | CIDEr: 133.2 -> 134.3 | Helped |
| Add both Grid-Augmented and Adaptive Attention modules (ablation) | Image captioning with ResNext152 grid features · MSCOCO | CIDEr: 133.2 -> 135.6 | Helped |
Closest papers by meaning
- In Defense of Grid Features for Visual Question Answering (CVPR 2020 · similarity 0.89)
- Revisiting the Role of Language Priors in Vision-Language Models (ICML 2024 · similarity 0.88)
- FlexCap: Describe Anything in Images in Controllable Detail (NeurIPS 2024 · similarity 0.88)
- Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models (ICLR 2024 · similarity 0.87)
- Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding (CVPR 2025 · similarity 0.87)
- RegionGPT: Towards Region Understanding Vision Language Model (CVPR 2024 · 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.