Research map / Video / Action recognition
Human Action Recognition and Prediction: A Survey
Yu Kong, Yun Fu
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 online hard example mining (OHEM) | Single-stream R-C3D · THUMOS'14 | mAP@0.5: 28.9 -> 35.8 | Improved |
| add a second (two-stream) input stream | R-C3D · THUMOS'14 | mAP@0.5: 28.9 -> 36.1 | Improved |
| use boundary-sensitive proposal networks (BMN) instead of end-to-end detection | End-to-End · THUMOS'14 | mAP@0.5: 17.1 -> 38.8 | Improved |
| add a recurrent LSTM layer over CNN features instead of temporal pooling | hybrid CNN-LSTM networks · action recognition | accuracy | Improved |
Closest papers by meaning
- About Time: Advances, Challenges, and Outlooks of Action Understanding (IJCV 2025 · similarity 0.89)
- A Comprehensive Review of Few-Shot Action Recognition (IJCV 2025 · similarity 0.89)
- Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization (ECCV 2018 · similarity 0.88)
- Human Action Recognition From Various Data Modalities: A Review (TPAMI 2022 · similarity 0.87)
- UCF-STAR: A Large Scale Still Image Dataset for Understanding Human Actions (AAAI 2020 · similarity 0.87)
- Pulling Actions out of Context: Explicit Separation for Effective Combination (CVPR 2018 · 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.
