Research map / Architectures and efficiency / RNNs and normalization
Tensor-Train Recurrent Neural Networks for Video Classification
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 Tensor-Train factorization to the GRU input-to-hidden mapping | GRU · UCF11 | accuracy: 0.488 ± 0.033 -> 0.813 ± 0.011 | Helped |
| Add Tensor-Train factorization to the LSTM input-to-hidden mapping | LSTM · UCF11 | accuracy: 0.492 ± 0.026 -> 0.796 ± 0.035 | Helped |
| Add Tensor-Train factorization to the GRU input-to-hidden mapping | GRU · Hollywood2 | mean average precision: 0.249 -> 0.537 | Helped |
| Add Tensor-Train factorization to the LSTM input-to-hidden mapping | LSTM · Hollywood2 | mean average precision: 0.108 -> 0.546 | Helped |
| Add Tensor-Train factorization to the GRU input-to-hidden mapping | GRU · YouTube Celebrities Face | accuracy: 0.342 ± 0.023 -> 0.800 ± 0.018 | Helped |
| Add Tensor-Train factorization to the LSTM input-to-hidden mapping | LSTM · YouTube Celebrities Face | accuracy: 0.332 ± 0.033 -> 0.755 ± 0.033 | Helped |
| Use a recurrent TT-GRU rather than a six-frame TT-MLP | TT-GRU and TT-MLP · YouTube Celebrities Face | accuracy: 0.512 ± 0.057 -> 0.800 ± 0.018 | Helped |
Closest papers by meaning
- Learning Compact Recurrent Neural Networks With Block-Term Tensor Decomposition (CVPR 2018 · similarity 0.91)
- Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition (AAAI 2019 · similarity 0.89)
- Wider and Deeper, Cheaper and Faster: Tensorized LSTMs for Sequence Learning (NeurIPS 2017 · similarity 0.89)
- A Tensor Decomposition Perspective on Second-order RNNs (ICML 2024 · similarity 0.88)
- Towards Extremely Compact RNNs for Video Recognition With Fully Decomposed Hierarchical Tucker Structure (CVPR 2021 · similarity 0.88)
- Learning Useful Representations of Recurrent Neural Network Weight Matrices (ICML 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.