paper-with-me

Papers

Spectra-Guided Neural Tucker Factorization

2026-05-30 · Fusheng Wang, Yikai Hou arxiv

This paper proposes Spectra-Guided Neural Tucker Factorization (SG-NTF) for High-Dimensional and Incomplete (HDI) tensor completion. Circumventing discrete representational limits, SG-NTF maps scalar timestamps into a continuous spectral space to abstract temporal periodicities. Concurrently, a Spatio-Temporal Co-Gating (STCG) mechanism explicitly filters latent interactions via multiplicative modulation on spatiotemporal contexts. Evaluations on real-world HDI tensors verify that SG-NTF maintains competitive completion accuracy with parameter efficiency.

📄 PDF Abstract BibTeX arXiv:2606.00584

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization

2020-01-06 · Wei He, Yong Chen, Naoto Yokoya, Chao Li 외

Hyperspectral super-resolution (HSR) fuses a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) to obtain a high-resolution HSI (HR-HSI). In this paper, we propose a new model, named…

Super-Resolution

Scalable Tucker Factorization for Sparse Tensors - Algorithms and Discoveries

2018-02-25 · Oh Sejoon, Park Namyong, Sael Lee, Kang U

Given sparse multi-dimensional data (e.g., (user, movie, time; rating) for movie recommendations), how can we discover latent concepts/relations and predict missing values? Tucker factorization has been widely used to so…

Missing Values

Sparse Hierarchical Tucker Factorization and its Application to Healthcare

2016-10-25 · Ioakeim Perros, Robert Chen, Richard Vuduc, Jimeng Sun

We propose a new tensor factorization method, called the Sparse Hierarchical-Tucker (Sparse H-Tucker), for sparse and high-order data tensors. Sparse H-Tucker is inspired by its namesake, the classical Hierarchical Tucke…

Semi-NMF Regularization-Based Autoencoder Training for Hyperspectral Unmixing

2024-04-05 · 30th National Conference on Communications (NCC) 2024 4 · Divyam Goel, Saurabh Khanna

Hyperspectral Unmixing (HSU) refers to the procedure of decomposing measured pixel spectra into a set of constituent spectral signatures known as endmembers and a corresponding set of fractional mixing ratios. In this wo…

Hyperspectral Unmixing

Multi-mode Core Tensor Factorization based Low-Rankness and Its Applications to Tensor Completion

2020-12-03 · Haijin Zeng

Low-rank tensor completion has been widely used in computer vision and machine learning. This paper develops a novel multi-modal core tensor factorization (MCTF) method combined with a tensor low-rankness measure and a b…

Denoising