Research map / Learning theory and algorithms / Matrix and tensor methods
Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition Under Reshuffling
Chao Li, Mohammad Emtiyaz Khan, Zhun Sun, Gang Niu, Bo Han, Shengli Xie, Qibin Zhao
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 |
|---|---|---|---|
| Use Reshuffled-TD instead of LSB, 1 bit/chn | Image steganography · DTD cover + CART secret | SIR (cover): 26.70 -> 20.40 | Hurt |
| Use Reshuffled-TD instead of DWT, 3 bits/chn | Image steganography · DTD cover + CART secret | SIR (secret): 17.81 -> 21.64 | Improved |
| Use Reshuffled-TD instead of LSB, 1 bit/chn | Image steganography · DTD cover + DTD secret | SIR (cover): 23.77 -> 23.69 | Hurt |
| Use Reshuffled-TD instead of DWT, 3 bits/chn | Image steganography · DTD cover + DTD secret | SIR (secret): 9.05 -> 11.36 | Improved |
| Use Reshuffled-TD instead of DWT, 2 bits/chn | Image steganography · DTD cover + FIVEK secret | SIR (cover): 24.70 -> 23.36 | Hurt |
| Use Reshuffled-TD instead of DPS | Image steganography · DTD cover + FIVEK secret | SIR (secret): 8.97 -> 10.87 | Improved |
| Use Reshuffled-TD instead of LSB, 1 bit/chn | Image steganography · FIVEK cover + FIVEK secret | SIR (cover): 23.02 -> 21.86 | Hurt |
| Use Reshuffled-TD instead of DPS | Image steganography · FIVEK cover + FIVEK secret | SIR (secret): 8.96 -> 6.67 | Hurt |
| Use Reshuffled-TD instead of DWT, 2 bits/chn | Image steganography · FVC cover + FIVEK secret | SIR (cover): 24.47 -> 20.25 | Hurt |
| Use Reshuffled-TD instead of DPS | Image steganography · FVC cover + FIVEK secret | SIR (secret): 8.90 -> 12.80 | Improved |
| Use Reshuffled-TD instead of LSB, 1 bit/chn | Image steganography · LIVE cover + FIVEK secret | SIR (cover): 24.50 -> 24.71 | Improved |
| Use Reshuffled-TD instead of DPS | Image steganography · LIVE cover + FIVEK secret | SIR (secret): 9.50 -> 11.49 | Improved |
Closest papers by meaning
- Handling The Non-Smooth Challenge in Tensor SVD: A Multi-Objective Tensor Recovery Framework (ECCV 2024 · similarity 0.88)
- Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms (CVPR 2019 · similarity 0.88)
- Deep Rank-One Tensor Functional Factorization for Multi-Dimensional Data Recovery (AAAI 2025 · similarity 0.86)
- Non-Convex Tensor Recovery from Local Measurements (AAAI 2025 · similarity 0.86)
- Towards Multi-Mode Outlier Robust Tensor Ring Decomposition (AAAI 2024 · similarity 0.86)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · 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.
