Research map / Video / Video-language understanding
Hierarchical Boundary-Aware Neural Encoder 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 |
|---|---|---|---|
| Replace a plain LSTM video encoder with a learned boundary-aware encoder | Video captioning encoder · M-VAD | METEOR: 6.7 -> 7.3; improvement of 0.6% | Helped |
| Replace a plain LSTM video encoder with a learned boundary-aware encoder | Video captioning encoder · MPII-MD | METEOR: 0.6% | Helped |
| Use learned temporal boundaries rather than equally spaced chunks with the same number of segments (ablation) | Boundary-aware encoder · M-VAD | METEOR: 0.2% | Helped |
| Use learned temporal boundaries rather than equally spaced chunks with the same number of segments (ablation) | Boundary-aware encoder · MPII-MD | METEOR: 0.5% | Helped |
| Use learned boundaries rather than detected shot boundaries (ablation) | Boundary-aware encoder · M-VAD | METEOR: 7.1% -> 7.3%; 0.2% | Helped |
| Use learned boundaries rather than detected shot boundaries (ablation) | Boundary-aware encoder · MPII-MD | METEOR: 6.6% -> 7.0% | Helped |
| Use the boundary-aware encoder instead of HRNE | Video captioning · MSVD | BLEU-4: 46.7 -> 42.5 | Hurt |
| Use the boundary-aware encoder instead of HRNE | Video captioning · MSVD | METEOR: 33.9 -> 32.4 | Hurt |
Closest papers by meaning
- Hierarchical Recurrent Neural Encoder for Video Representation With Application to Captioning (CVPR 2016 · similarity 0.92)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.87)
- HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning (AAAI 2025 · similarity 0.86)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 2025 · similarity 0.86)
- DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement (CVPR 2024 · similarity 0.85)
- CALVIN: Improved Contextual Video Captioning via Instruction Tuning (NeurIPS 2024 · 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.