Research map / Video / Video-language understanding
Hierarchical Modular 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 entity module (ablation) | HMN · MSVD | CIDEr: 88.3 -> 104.0 | Helped |
| add the entity module (ablation) | HMN · MSR-VTT | CIDEr: 46.6 -> 51.5 | Helped |
| add the predicate module (ablation) | HMN · MSVD | CIDEr: 98.9 -> 104.0 | Helped |
| add the predicate module (ablation) | HMN · MSR-VTT | CIDEr: 49.8 -> 51.5 | Helped |
| add the sentence module (ablation) | HMN · MSVD | CIDEr: 94.8 -> 104.0 | Helped |
| add the sentence module (ablation) | HMN · MSR-VTT | CIDEr: 49.4 -> 51.5 | Helped |
| retain the entity-to-predicate connection (ablation) | HMN · MSVD | CIDEr: 101.3 -> 104.0 | Helped |
| retain the entity-to-sentence connection (ablation) | HMN · MSVD | CIDEr: 100.6 -> 104.0 | Helped |
| retain the predicate-to-sentence connection (ablation) | HMN · MSR-VTT | CIDEr: 50.7 -> 51.5 | Helped |
| use entity rather than noun supervision (ablation) | HMN entity module · MSVD | CIDEr: 98.1 -> 104.0 | Helped |
| use predicate rather than verb supervision (ablation) | HMN predicate module · MSVD | CIDEr: 102.1 -> 104.0 | Helped |
| select principal objects rather than using all detected objects (ablation) | HMN · MSVD | CIDEr: 92.7 -> 104.0 | Helped |
Closest papers by meaning
- Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks (CVPR 2016 · similarity 0.89)
- Video Captioning via Hierarchical Reinforcement Learning (CVPR 2018 · similarity 0.88)
- Video ReCap: Recursive Captioning of Hour-Long Videos (CVPR 2024 · similarity 0.88)
- Exploiting Auxiliary Caption for Video Grounding (AAAI 2024 · similarity 0.87)
- Distilling Vision-Language Models on Millions of Videos (CVPR 2024 · similarity 0.87)
- Set Prediction Guided by Semantic Concepts for Diverse Video Captioning (AAAI 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.