Research map / 3D vision / Human pose estimation
3D Action Recognition From Novel Viewpoints
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 Fourier Temporal Pyramid and group-sparse action-specific neuron selection to HPM (ablation) | HPM · Northwestern-UCLA Multiview Action3D, camera 3 test | recognition accuracy (%): 78.1 -> 92.0 | Helped |
| Add Fourier Temporal Pyramid and group-sparse action-specific neuron selection to HPM (ablation) | HPM · UWA3D Multiview ActivityII, mean across view pairs | recognition accuracy (%): 58.9 -> 76.9 | Helped |
| Use synthetic-data-trained HPM+TM rather than NKTM | Cross-view action recognition · UWA3D Multiview ActivityII, mean across view pairs | recognition accuracy (%): 63.5 -> 76.9 | Helped |
| Use HPM+TM rather than HOPC | Cross-view action recognition · Northwestern-UCLA Multiview Action3D, camera 3 test | recognition accuracy (%): 80.0 -> 92.0 | Helped |
Closest papers by meaning
- PA3D: Pose-Action 3D Machine for Video Recognition (CVPR 2019 · similarity 0.89)
- Recognizing Actions in Videos From Unseen Viewpoints (CVPR 2021 · similarity 0.89)
- Deep Representation Learning for Human Motion Prediction and Classification (CVPR 2017 · similarity 0.89)
- Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition (CVPR 2021 · similarity 0.89)
- T-C3D: Temporal Convolutional 3D Network for Real-Time Action Recognition (AAAI 2018 · similarity 0.88)
- 2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (CVPR 2018 · similarity 0.88)
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.