Research map / Video / Video-language understanding
Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks
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 the hierarchical sentence and paragraph generators instead of LSTM-E | Video captioning on YouTubeClips · YouTubeClips | BLEU@4: 0.453 -> 0.499 | Helped |
| Use the hierarchical sentence and paragraph generators instead of LRCN | Video paragraph captioning · TACoS-MultiLevel | BLEU@4: 0.292 -> 0.305 | Helped |
| Add C3D motion features to VggNet appearance features (ablation) | h-RNN · YouTubeClips | BLEU@4: 0.443 -> 0.499 | Helped |
| Add VggNet appearance features to C3D motion features (ablation) | h-RNN · YouTubeClips | BLEU@4: 0.474 -> 0.499 | Helped |
| Add Dense Trajectories motion features to VggNet appearance features (ablation) | h-RNN · TACoS-MultiLevel | BLEU@4: 0.256 -> 0.305 | Helped |
| Add VggNet appearance features to Dense Trajectories motion features (ablation) | h-RNN · TACoS-MultiLevel | BLEU@4: 0.274 -> 0.305 | Helped |
| Add hierarchical paragraph modeling instead of generating each sentence independently (ablation) | Video paragraph captioning · TACoS-MultiLevel | BLEU@4: 0.295 -> 0.305 | Helped |
| Replace sentence-level state concatenation with a hierarchical paragraph generator (ablation) | Video paragraph captioning · TACoS-MultiLevel | BLEU@4: 0.297 -> 0.305 | Helped |
Closest papers by meaning
- Memory-Attended Recurrent Network for Video Captioning (CVPR 2019 · similarity 0.90)
- Hierarchical Boundary-Aware Neural Encoder for Video Captioning (CVPR 2017 · similarity 0.89)
- A Hierarchical Approach for Generating Descriptive Image Paragraphs (CVPR 2017 · similarity 0.89)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.89)
- HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning (AAAI 2025 · similarity 0.86)
- Distilling Vision-Language Models on Millions of Videos (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.