Research map / Video / Action recognition
Action Recognition With Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
Weiyao Lin, Chongyang Zhang, Ke Lu, Bin Sheng, Jianxin Wu, Bingbing Ni, Xin Liu, Hongkai Xiong
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 adaptive class group forming (ablation) | CO2FI · UCF101 split 1 | accuracy: 90.0% -> 92.8% | Improved |
| Use multiple action classes in the granularity groups rather than only the ground-truth class (ablation) | CO2FI · UCF101 split 1 | accuracy: 90.4% -> 92.8% | Improved |
| Add the coarsest action class granularity (ablation) | CO2FI · UCF101 split 1 | accuracy: 91.7% -> 92.8% | Improved |
| Fuse streams at the same time point (ablation) | Two-stream baseline · UCF101 split 1 | accuracy: 89.8% -> 89.7% | Hurt |
| Fuse asynchronous stream features at Δ=1 (ablation) | Two-stream baseline · UCF101 split 1 | accuracy: 89.8% -> 90.3% | Improved |
| Fuse asynchronous stream features at Δ=5 (ablation) | Two-stream baseline · UCF101 split 1 | accuracy: 89.8% -> 91.0% | Improved |
| Fuse asynchronous stream features at Δ=5 (ablation) | Two-stream baseline · HMDB51 split 1 | accuracy: 58.4% -> 60.9% | Improved |
| Add asynchronous fusion to CO2FI (ablation) | CO2FI · UCF101 split 1 | accuracy: 92.8% -> 93.7% | Improved |
| Add asynchronous fusion to CO2FI (ablation) | CO2FI · HMDB51 split 1 | accuracy: 67.9% -> 69.5% | Improved |
| Fuse the method with IDT features | CO2FI + ASYN · UCF101 3 splits | accuracy: 94.3% -> 95.2% | Improved |
| Fuse the method with IDT features | CO2FI + ASYN · HMDB51 3 splits | accuracy: 69.0% -> 72.6% | Improved |
Closest papers by meaning
- Convolutional Two-Stream Network Fusion for Video Action Recognition (CVPR 2016 · similarity 0.88)
- Action Recognition With Spatial-Temporal Discriminative Filter Banks (ICCV 2019 · similarity 0.87)
- Chained Multi-Stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection (ICCV 2017 · similarity 0.87)
- Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition (ECCV 2016 · similarity 0.87)
- AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition (ICLR 2021 · similarity 0.87)
- DVANet: Disentangling View and Action Features for Multi-View Action Recognition (AAAI 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.
