Research map / Video / Video-language understanding
Top-Down Visual Saliency Guided by Captions
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 |
|---|---|---|---|
| Use Caption-Guided Visual Saliency instead of Soft-Attn | S2VT video captioning · MSVD | METEOR: 30.0 -> 31.0 | Helped |
| Use Caption-Guided Visual Saliency instead of Soft-Attn | S2VT video captioning · MSR-VTT | METEOR: 25.4 -> 25.9 | Helped |
| Use Caption-Guided Visual Saliency instead of Soft-Attn | S2VT image captioning · Flickr30k | METEOR: 18.5 -> 18.3 | Hurt |
| Use caption-guided saliency rather than center-point localization | Flickr30kEntities noun-phrase localization · Flickr30kEntities | pointing game accuracy (Avg per NP): 0.492 -> 0.501 | Helped |
| Use caption-guided saliency rather than uniform random localization | Flickr30kEntities noun-phrase localization · Flickr30kEntities | pointing game accuracy (Avg per NP): 0.268 -> 0.501 | Helped |
| Use caption-guided saliency instead of supervised soft attention | Flickr30kEntities noun-phrase grounding · Flickr30kEntities | attention correctness (Avg per NP): 0.433 -> 0.473 | Helped |
| Use caption-guided saliency instead of soft attention | Flickr30kEntities noun-phrase grounding · Flickr30kEntities | attention correctness (Avg per NP): 0.387 -> 0.473 | Helped |
| Use caption-guided saliency instead of the uniform baseline | Flickr30kEntities noun-phrase grounding · Flickr30kEntities | attention correctness (Avg per NP): 0.325 -> 0.473 | Helped |
Closest papers by meaning
- Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception (CVPR 2025 · similarity 0.87)
- Top-Down Semantic Refinement for Image Captioning (AAAI 2026 · similarity 0.87)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.86)
- Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning (CVPR 2025 · similarity 0.86)
- CALVIN: Improved Contextual Video Captioning via Instruction Tuning (NeurIPS 2024 · similarity 0.86)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.86)
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.