Research map / Video / Action recognition
Deep Representation Learning for Human Motion Prediction and Classification
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 |
|---|---|---|---|
| Use a temporal encoder trained to predict future frames from past frames instead of a deep sparse autoencoder | Human motion representation learning · CMU mocap action classification | classification rate | Helped |
| Use H-TE instead of S-TE or C-TE (ablation) | Temporal encoder motion prediction · H3.6M specific-action prediction | prediction error | Helped |
| Use C-TE instead of H-TE (ablation) | Temporal encoder motion prediction · H3.6M general motion prediction, short term | forecast error | Helped |
| Use S-TE instead of C-TE (ablation) | Temporal encoder motion prediction · H3.6M general motion prediction, long term | forecast error | Mixed |
| Fine-tune H-TE on action-specific training data (ablation) | H-TE · H3.6M specific-action prediction | prediction error | Helped |
| Use feed-forward temporal encoders instead of recurrent models | Human motion prediction · H3.6M specific-action prediction at 160 ms and longer | prediction error | Helped |
| Use LSTM3L instead of temporal encoders | Human motion prediction · H3.6M specific-action prediction, initial predictions | prediction error | Helped |
| Mask all input data for one limb | Temporal encoder motion prediction · H3.6M, eating | prediction error | Hurt |
Closest papers by meaning
- Learning Dynamic Relationships for 3D Human Motion Prediction (CVPR 2020 · similarity 0.90)
- Convolutional Sequence to Sequence Model for Human Dynamics (CVPR 2018 · similarity 0.90)
- On Human Motion Prediction Using Recurrent Neural Networks (CVPR 2017 · similarity 0.90)
- Human Motion Prediction via Learning Local Structure Representations and Temporal Dependencies (AAAI 2019 · similarity 0.89)
- Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition (CVPR 2025 · similarity 0.86)
- Motion Diversification Networks (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.