Research map / Video / Action recognition
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
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 A-VID to RSP (ablation) | RSPNet with TSM-18 · UCF101 | top-1 accuracy: 54.5 -> 61.2 | Helped |
| Add A-VID to RSP (ablation) | RSPNet with TSM-18 · HMDB51 | top-1 accuracy: 26.5 -> 32.2 | Helped |
| Add RSP to A-VID (ablation) | RSPNet with TSM-18 · UCF101 | top-1 accuracy: 60.8 -> 61.2 | Helped |
| Add RSP to A-VID (ablation) | RSPNet with TSM-18 · HMDB51 | top-1 accuracy: 30.2 -> 32.2 | Helped |
| Add speed randomization to video instance discrimination (ablation) | RSPNet with TSM-18 · UCF101 | top-1 accuracy: 57.5 -> 61.2 | Helped |
| Add speed randomization to video instance discrimination (ablation) | RSPNet with TSM-18 · HMDB51 | top-1 accuracy: 30.1 -> 32.2 | Helped |
| Use relative speed labels instead of predicting each clip's speed (ablation) | RSPNet with TSM-18 and A-VID · UCF101 | top-1 accuracy: 59.8 -> 61.2 | Helped |
| Use relative speed labels instead of predicting each clip's speed (ablation) | RSPNet with TSM-18 and A-VID · HMDB51 | top-1 accuracy: 29.7 -> 32.2 | Helped |
Closest papers by meaning
- SpeedNet: Learning the Speediness in Videos (CVPR 2020 · similarity 0.90)
- Semi-Supervised Action Recognition With Temporal Contrastive Learning (CVPR 2021 · similarity 0.90)
- Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion (AAAI 2021 · similarity 0.89)
- TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition (CVPR 2023 · similarity 0.88)
- Video Playback Rate Perception for Self-Supervised Spatio-Temporal Representation Learning (CVPR 2020 · similarity 0.88)
- Unsupervised Learning of View-invariant Action Representations (NeurIPS 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.