Research map / Video / Video segmentation and tracking
VideoOneNet: Bidirectional Convolutional Recurrent OneNet with Trainable Data Steps for Video Processing
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 bidirectional convolutional recurrent prior network plus trainable BCRNN data step (full VideoOneNet) vs. convolutional OneNet | OneNet prior and data steps · Rotated MNIST, Scanned CIFAR-10, UCF-101 (multiple tasks) | PSNR | Helped |
| Replace fixed linear ADMM data step with trainable BCRNN data step (ablation) | OneNet · Rotated MNIST deblurring (DD/TDD/MD) | PSNR | Helped |
| Add bidirectional convolutional recurrent connections to prior network (ablation) | OneNet · Video tasks with temporal structure (frame interpolation, frame prediction) | PSNR | Helped |
| Add trainable data step or recurrent prior alone (ablation) | OneNet · Other tasks (spatial inpainting, super resolution) | PSNR | Helped |
| Use both recurrent prior and trainable data step together (ablation) | OneNet · All video tasks | PSNR | Helped |
| Replace OneNet prior with 3D wavelet sparsity prior | 3D Wavelet Sparsity baseline · Rotated MNIST, Scanned CIFAR-10, UCF-101 | PSNR | Hurt |
| Add BCRNN components on Scanned CIFAR-10 colorization | VideoOneNet · Scanned CIFAR-10 colorization | PSNR | Hurt |
Closest papers by meaning
- Recurrent Residual Module for Fast Inference in Videos (CVPR 2018 · similarity 0.87)
- Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring (CVPR 2019 · similarity 0.86)
- Deep Recurrent Neural Network with Multi-Scale Bi-directional Propagation for Video Deblurring (AAAI 2022 · similarity 0.86)
- DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos (CVPR 2022 · similarity 0.86)
- Sideways: Depth-Parallel Training of Video Models (CVPR 2020 · similarity 0.86)
- Progressive Image Deraining Networks: A Better and Simpler Baseline (CVPR 2019 · 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.