Research map / Architectures and efficiency / RNNs and normalization
Compressing Recurrent Neural Networks with Tensor Ring for 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 |
|---|---|---|---|
| Replace the LSTM input-to-hidden transformation with a tensor ring layer | LSTM · UCF11, end-to-end training | accuracy: 0.681 -> 0.869 | Helped |
| Use tensor ring decomposition instead of tensor train decomposition for weight recovery | Weight-matrix recovery · Synthetic weight recovery, noise variance 0.05 | RMSE: 0.18 -> 0.09 | Helped |
| Replace LSTM with TR-LSTM | CNN + LSTM · UCF11, Inception-V3 features | accuracy: 92.3% -> 93.8}% | Helped |
| Replace LSTM with TR-LSTM | CNN + LSTM · HMDB51, Inception-V3 features | accuracy: 62.9% -> 63.8}% | Helped |
Closest papers by meaning
- Learning Compact Recurrent Neural Networks With Block-Term Tensor Decomposition (CVPR 2018 · similarity 0.92)
- Towards Extremely Compact RNNs for Video Recognition With Fully Decomposed Hierarchical Tucker Structure (CVPR 2021 · similarity 0.90)
- Tensor-Train Recurrent Neural Networks for Video Classification (ICML 2017 · similarity 0.89)
- Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning (NeurIPS 2017 · similarity 0.88)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.85)
- A Tensor Decomposition Perspective on Second-order RNNs (ICML 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.