Research map / Video / Action recognition
Exploiting Motion Information from Unlabeled Videos for Static Image 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 |
|---|---|---|---|
| Use VRE and MRA together to exploit unlabeled video motion | Static image action recognition · UCF101→VOC | accuracy: 16.22 -> 21.06 | Helped |
| Use VRE and MRA together to exploit unlabeled video motion | Static image action recognition · UCF101→Stanford40 | accuracy: 15.42 -> 18.76 | Helped |
| Use VRE and MRA together to exploit unlabeled video motion | Static image action recognition · HMDB→VOC | accuracy: 16.22 -> 22.94 | Helped |
| Use VRE and MRA together to exploit unlabeled video motion | Static image action recognition · HMDB→Stanford40 | accuracy: 15.42 -> 19.11 | Helped |
| Add pseudo-label video motion classification loss (ablation) | VRE / UNREG · UCF101→VOC | accuracy: 16.22 -> 19.39 | Helped |
| Add pseudo-label video motion classification loss (ablation) | VRE / UNREG · HMDB→VOC | accuracy: 16.22 -> 19.72 | Helped |
| Add first-order smoothness regularization (ablation) | VRE / UNREG · UCF101→VOC | accuracy: 16.22 -> 18.89 | Helped |
| Add first-order smoothness regularization (ablation) | VRE / UNREG · HMDB→VOC | accuracy: 16.22 -> 18.61 | Helped |
| Add second-order smoothness regularization (ablation) | VRE / UNREG · UCF101→VOC | accuracy: 16.22 -> 18.72 | Helped |
| Add second-order smoothness regularization (ablation) | VRE / UNREG · HMDB→VOC | accuracy: 16.22 -> 18.11 | Helped |
| Add MRA motion-representation augmentation to VRE (ablation) | VRE-only method · UCF101→VOC | accuracy: 20.06 -> 21.06 | Helped |
| Add MRA motion-representation augmentation to VRE (ablation) | VRE-only method · HMDB→VOC | accuracy: 20.44 -> 22.94 | Helped |
Closest papers by meaning
- Unsupervised Learning of View-invariant Action Representations (NeurIPS 2018 · similarity 0.88)
- Self-Supervised Motion Learning From Static Images (CVPR 2021 · similarity 0.87)
- Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision (AAAI 2019 · similarity 0.86)
- Learning from Weakly-Labeled Web Videos via Exploring Sub-concepts (AAAI 2022 · similarity 0.86)
- Semi-Supervised Action Recognition With Temporal Contrastive Learning (CVPR 2021 · similarity 0.86)
- Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training (CVPR 2024 · similarity 0.85)
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.