Research map / Video / Action recognition
Memory-Augmented Temporal Dynamic Learning for Action Recognition
Read the paperCheck 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 memory-augmented temporal dynamic network to the ResNet+TSN baseline | ResNet+TSN · UCF101 | accuracy: 94.1 -> 94.8; 0.7% | Helped |
| Add the memory-augmented temporal dynamic network to the ResNet+TSN baseline | ResNet+TSN · HMDB51 | accuracy: 69.0 -> 71.8; 2.5% | Helped |
| Add the memory-augmented temporal dynamic network | VGG16 spatial stream · UCF101 split 1 | accuracy: 77.4 -> 80.0; 2.6 | Helped |
| Add the memory-augmented temporal dynamic network | VGG16 temporal stream · UCF101 split 1 | accuracy: 75.2 -> 82.7; 7.5 | Helped |
| Use memory-augmented temporal learning instead of ConvLSTM | UCF101 human-object interaction · UCF101 split 1 human-object interaction | accuracy: 76.0 -> 83.3; 7.3% | Helped |
| Use memory-augmented temporal learning instead of ConvLSTM | UCF101 human-human interaction · UCF101 split 1 human-human interaction | accuracy: 89.1 -> 91.5; 2.4% | Helped |
| Use memory-augmented temporal learning instead of ConvLSTM | UCF101 body motion only · UCF101 split 1 body motion only | accuracy: 88.1 -> 89.3; 1.2% | Helped |
Closest papers by meaning
- Temporal Hallucinating for Action Recognition With Few Still Images (CVPR 2018 · similarity 0.89)
- Temporal Pyramid Network for Action Recognition (CVPR 2020 · similarity 0.89)
- Temporal Convolutional Networks for Action Segmentation and Detection (CVPR 2017 · similarity 0.88)
- Video Prediction Recalling Long-Term Motion Context via Memory Alignment Learning (CVPR 2021 · similarity 0.88)
- TDN: Temporal Difference Networks for Efficient Action Recognition (CVPR 2021 · similarity 0.88)
- VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention (AAAI 2025 · similarity 0.87)
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.