Research map / Video / Action recognition
Video Modeling With Correlation Networks
Check 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 learnable filters to the correlation operator (ablation) | CorrNet-26 · Kinetics | accuracy (%): 73.9 -> 75.1 | Helped |
| add learnable filters to the correlation operator (ablation) | CorrNet-26 · Something | accuracy (%): 46.5 -> 47.4 | Helped |
| retain grouping in the correlation operator (ablation) | CorrNet-26 · Kinetics | accuracy (%): 74.2 -> 75.1 | Helped |
| retain grouping in the correlation operator (ablation) | CorrNet-26 · Something | accuracy (%): 46.1 -> 47.4 | Helped |
| use correlation-sum instead of correlation-concat (ablation) | CorrNet-26 · Kinetics | accuracy (%): 73.2 -> 75.1 | Helped |
| use correlation-sum instead of correlation-concat (ablation) | CorrNet-26 · Something | accuracy (%): 45.9 -> 47.4 | Helped |
| increase input clip length from 16 to 32 frames | CorrNet-26 · Kinetics | top-1 accuracy (%): 73.4 -> 75.1 | Helped |
| increase input clip length from 16 to 32 frames | CorrNet-26 · Something | top-1 accuracy (%): 38.5 -> 47.4 | Helped |
| increase input clip length from 16 to 32 frames | CorrNet-26 · Diving | top-1 accuracy (%): 27.0 -> 35.5 | Helped |
| increase matching neighborhood size K, with diminishing returns beyond K=7 (ablation) | CorrNet-26 · classification evaluation | accuracy | Helped |
Closest papers by meaning
- Spatiotemporal Pyramid Network for Video Action Recognition (CVPR 2017 · similarity 0.90)
- A Closer Look at Spatiotemporal Convolutions for Action Recognition (CVPR 2018 · similarity 0.90)
- ACTION-Net: Multipath Excitation for Action Recognition (CVPR 2021 · similarity 0.89)
- Convolutional Two-Stream Network Fusion for Video Action Recognition (CVPR 2016 · similarity 0.89)
- Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition (CVPR 2021 · similarity 0.89)
- T-C3D: Temporal Convolutional 3D Network for Real-Time Action Recognition (AAAI 2018 · similarity 0.89)
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.