Research map / Video / Action recognition
Selective Volume Mixup for Video Action Recognition
Yi Tan, Zhaofan Qiu, Yanbin Hao, Ting Yao, Tao Mei
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 SV-Mix augmentation | TSM · Sth-Sth V1 | top-1 accuracy (%): 45.5 -> 47.2 | Improved |
| add SV-Mix augmentation | ViViT · Diving48 | top-1 accuracy (%): 70.0 -> 76.2 | Improved |
| add SV-Mix augmentation | Uniformer · UCF101 | top-1 accuracy (%): 93.2 -> 97.1 | Improved |
| add SV-Mix augmentation | MViTv2 · Mini-Kinetics | top-1 accuracy (%): 79.3 -> 79.5 | Improved |
| use Mixup augmentation on video | TSM · Sth-Sth V1 | top-1 accuracy (%): 45.5 -> 44.6 | Hurt |
| replace Cutmix/Mixup with SV-Mix | TSM · UCF101 | top-1 accuracy (%): 86.9 -> 88.4 | Improved |
| add spatial selective module over Cutmix (ablation) | TSM · Sth-Sth V1 | top-1 accuracy (%): 45.7 -> 47.0 | Improved |
| add temporal selective module over Mixup (ablation) | TSM · Sth-Sth V1 | top-1 accuracy (%): 44.6 -> 46.6 | Improved |
| combine temporal and spatial modules by random switching (ablation) | SV-Mix · Sth-Sth V1 | top-1 accuracy (%): 47.0 -> 47.2 | Improved |
| use disentangled (EMA target) training instead of entangled training (ablation) | SV-Mix spatial selective · Sth-Sth V1 | top-1 accuracy (%): 45.6 -> 47.0 | Improved |
| use disentangled training instead of entangled training (ablation) | SV-Mix both modules · Sth-Sth V1 | top-1 accuracy (%): 45.8 -> 47.2 | Improved |
| add lambda embedding (ablation) | SV-Mix · Sth-Sth V1 | top-1 accuracy (%): 45.1 -> 46.9 | Improved |
Closest papers by meaning
- Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition (ECCV 2022 · similarity 0.89)
- Few-Shot Action Recognition via Intra- and Inter-Video Information Maximization (TPAMI 2026 · similarity 0.87)
- Discriminative Video Representation Learning Using Support Vector Classifiers (TPAMI 2019 · similarity 0.86)
- Exploring Temporally Dynamic Data Augmentation for Video Recognition (ICLR 2023 · similarity 0.86)
- Few-Shot Action Recognition with Hierarchical Matching and Contrastive Learning (ECCV 2022 · similarity 0.86)
- Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN (AAAI 2024 · similarity 0.84)
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.
