Research map / Vision-language and multimodal / Visual question answering
Multimodal Dual Attention Memory for Video Story Question Answering
Kyung-Min Kim, Seong-Ho Choi, Jin-Hwa Kim, Byoung-Tak Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 self-attention module (ablation) | MDAM · PororoQA test | accuracy (%): 47.3 -> 48.9 | Improved |
| fuse multimodal information late (after dual attention) instead of early (ablation) | MDAM · PororoQA test | accuracy (%): 46.1 -> 48.9 | Improved |
| use residual-learning fusion instead of element-wise multiplication (ablation) | MDAM · PororoQA test | accuracy (%): 41.5 -> 48.9 | Improved |
| add captions to frames as input (ablation) | MDAM-FrameOnly · PororoQA test | accuracy (%): 42.1 -> 48.9 | Improved |
| add scene frames to captions as input (ablation) | MDAM-CaptOnly · PororoQA test | accuracy (%): 42.5 -> 48.9 | Improved |
| late fusion rather than early fusion (ablation) | MDAM · MovieQA val | accuracy (%) | Improved |
| residual fusion rather than element-wise multiplication (ablation) | MDAM · MovieQA val | accuracy (%) | Improved |
| increase attention depth L_attn and fusion depth L_m (ablation) | MDAM · MovieQA val | accuracy (%) | Hurt |
Closest papers by meaning
- Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering (CVPR 2019 · similarity 0.92)
- Progressive Attention Memory Network for Movie Story Question Answering (CVPR 2019 · similarity 0.88)
- Glance and Focus: Memory Prompting for Multi-Event Video Question Answering (NeurIPS 2023 · similarity 0.88)
- LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding (NeurIPS 2024 · similarity 0.88)
- MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding (CVPR 2024 · similarity 0.87)
- AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction (CVPR 2025 · 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.
