Research map / Video / Video-language understanding
Syntax-Aware Action Targeting for Video Captioning
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 syntax-aware action targeting with predicate guidance | Baseline video captioner · MSR-VTT test | CIDEr: 46.1 -> 49.1 | Helped |
| Add syntax-aware action targeting | Baseline video captioner · MSVD test | CIDEr: 78.9 -> 81.0 | Helped |
| Train SAAT with reinforcement learning instead of cross-entropy | SAAT · MSR-VTT test | CIDEr: 49.1 -> 51.0 | Helped |
| Guide caption generation with subject, predicate, and object rather than predicate alone (ablation) | SAAT · MSR-VTT test | CIDEr: 49.1 -> 46.1 | Hurt |
| Guide caption generation with subject, predicate, and object rather than predicate alone (ablation) | SAAT · MSR-VTT test | ROUGE L: 60.9 -> 60.4 | Helped |
| Guide caption generation with subject, predicate, and object rather than predicate alone (ablation) | SAAT · MSR-VTT test | predicate accuracy: 60.4 -> 60.5 | No clear effect |
| Add syntax-component guidance (ablation) | Baseline video captioner · MSR-VTT test | ROUGE L: 59.9 -> 60.9 | Helped |
| Add predicate-guided captioning (ablation) | Baseline video captioner · sports scenes | verb accuracy: 63.6 -> 64.5 | Helped |
| Add predicate-guided captioning (ablation) | Baseline video captioner · food scenes | verb accuracy: 50.8 -> 59.5 | Helped |
| Add predicate-guided captioning (ablation) | Baseline video captioner · cooking scenes | verb accuracy: 63.6 -> 69.1 | Helped |
| Use predicate-only SAAT guidance instead of subject-predicate-object guidance (ablation) | SAAT · sports scenes | verb accuracy: 61.4 -> 64.5 | Helped |
| Use predicate-only SAAT guidance instead of subject-predicate-object guidance (ablation) | SAAT · food scenes | verb accuracy: 55.1 -> 59.5 | Helped |
Closest papers by meaning
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.88)
- Comprehensive Visual Grounding for Video Description (AAAI 2024 · similarity 0.87)
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024 · similarity 0.87)
- Kronecker Mask and Interpretive Prompts are Language-Action Video Learners (ICLR 2025 · similarity 0.86)
- Dense Video Object Captioning from Disjoint Supervision (ICLR 2025 · similarity 0.86)
- OmniViD: A Generative Framework for Universal Video Understanding (CVPR 2024 · 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.