Research map / Video / Video segmentation and tracking
Motion Guided Spatial Attention for Video Captioning
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 GARU (ablation) | MGSA · MSVD test | CIDEr: 83.3 -> 86.4 | Helped |
| add GARU (ablation) | Spatial Attention · MSVD test | CIDEr: 72.2 -> 81.8 | Helped |
| motion-guided (optical flow) attention instead of feature-based spatial attention (ablation) | attention encoder w/o GARU · MSVD test | CIDEr: 72.2 -> 83.3 | Helped |
| add GARU (ablation) | MGSA · MSVD test | METEOR: 33.1 -> 34.7 | Helped |
| add C3D features | MGSA(I) · MSVD test | CIDEr: 86.4 -> 86.7 | No clear effect |
| add C3D features | MGSA(I) · MSR-VTT test | CIDEr: 48.1 -> 47.5 | Hurt |
| add audio and C3D features | MGSA(I) · MSR-VTT test | BLEU@4: 41.7 -> 45.4 | Helped |
| Inception-ResNet-V2 instead of GoogleNet features | MGSA · MSVD test | CIDEr: 74.2 -> 86.4 | Helped |
| deeper flow CNN (ablation) | MGSA · MSVD | captioning metrics | No clear effect |
Closest papers by meaning
- CSTA: CNN-based Spatiotemporal Attention for Video Summarization (CVPR 2024 · similarity 0.87)
- STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding (CVPR 2025 · similarity 0.86)
- Dense Video Object Captioning from Disjoint Supervision (ICLR 2025 · similarity 0.86)
- Progress-Aware Video Frame Captioning (CVPR 2025 · similarity 0.86)
- MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models (CVPR 2025 · similarity 0.85)
- VideoGrain: Modulating Space-Time Attention for Multi-Grained Video Editing (ICLR 2025 · 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.