Research map / Video / Video segmentation and tracking
Hierarchical Recurrent Neural Encoder for Video Representation With Application to 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 the hierarchical recurrent encoder in place of average-pooled frame features | Video captioning · MSVD | METEOR: 28.7 -> 32.1 | Helped |
| add the hierarchical recurrent encoder in place of a single-layer LSTM encoder | Video captioning · MSVD | METEOR: 29.2 -> 32.1 | Helped |
| add attention to HRNE (ablation) | HRNE · MSVD | METEOR: 32.1 -> 33.1 | Helped |
| add attention to HRNE (ablation) | HRNE · MSVD | B@4: 43.6 -> 43.8 | Helped |
| add attention to HRNE (ablation) | HRNE · M-VAD | METEOR: 5.8 -> 6.8 | Helped |
| use HRNE instead of the strongest reported multi-feature baseline | Video captioning · MSVD | METEOR: 32.6 -> 33.1 | Helped |
| use HRNE instead of p-RNN | Video captioning · MSVD | B@4: 44.3 -> 43.6 | Hurt |
Closest papers by meaning
- Hierarchical Boundary-Aware Neural Encoder for Video Captioning (CVPR 2017 · similarity 0.92)
- Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning (AAAI 2019 · similarity 0.90)
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks (CVPR 2016 · similarity 0.89)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.86)
- HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning (AAAI 2025 · similarity 0.85)
- DejaVid: Encoder-Agnostic Learned Temporal Matching for Video Classification (CVPR 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.