Research map / Video / Video-language understanding
Memory-Attended Recurrent Network 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 the attended memory decoder to the basis decoder (ablation) | Video captioning system · MSR-VTT | CIDEr: 45.7 -> 46.8; 1.1% | Helped |
| Add the attended memory decoder to the basis decoder (ablation) | Video captioning system · MSVD | CIDEr: 89.9 -> 91.7; 1.8% | Helped |
| Add Attention-Coherent Loss (ablation) | Basis decoder + memory · MSR-VTT | CIDEr: 46.8 -> 47.1 | Helped |
| Add Attention-Coherent Loss (ablation) | Basis decoder + memory · MSVD | CIDEr: 91.7 -> 92.2 | Helped |
| Add word embedding to the memory (ablation) | Basis decoder · MSR-VTT | CIDEr: 45.7 -> 46.1 | Helped |
| Add word embedding to the memory (ablation) | Basis decoder · MSVD | CIDEr: 89.9 -> 90.7 | Helped |
| Add visual context to the word-embedding memory (ablation) | Basis decoder · MSR-VTT | CIDEr: 46.1 -> 46.6 | Helped |
| Add visual context to the word-embedding memory (ablation) | Basis decoder · MSVD | CIDEr: 90.7 -> 91.7 | Helped |
| Add category auxiliary features to the memory (ablation) | Basis decoder + word embedding + visual context · MSR-VTT | CIDEr: 46.6 -> 46.8 | Helped |
| Add the MARN memory decoder | Video captioning model · MSR-VTT | METEOR: 27.7 -> 28.1 | Helped |
| Add the MARN memory decoder | Video captioning model · MSR-VTT | BLEU-4: 40.1 -> 40.4 | Hurt |
| Add the MARN memory decoder | Video captioning model · MSVD | BLEU-4: 47.5 -> 48.6 | Hurt |
Closest papers by meaning
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks (CVPR 2016 · similarity 0.90)
- Hierarchical Boundary-Aware Neural Encoder for Video Captioning (CVPR 2017 · similarity 0.89)
- Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning (AAAI 2019 · similarity 0.88)
- Hierarchical Recurrent Neural Encoder for Video Representation With Application to Captioning (CVPR 2016 · similarity 0.87)
- HiCM²: Hierarchical Compact Memory Modeling for Dense Video Captioning (AAAI 2025 · similarity 0.87)
- 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.