Search Results for author:
Found 8 papers, 2 papers with code
PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection
Comprising two modules - a pre-processing module and an ego-neighbor matching module - PREM eliminates the necessity for message-passing propagation during training, and employs a simple contrastive loss, leading to considerable reductions in training time and memory usage.
Separable Quaternion Matrix Factorization for Polarization Images
To determine the source factor matrix in quaternion space, we propose a heuristic algorithm called quaternion successive projection algorithm (QSPA) inspired by the successive projection algorithm.
Diverse Dance Synthesis via Keyframes with Transformer Controllers
The video and qualitative experimental results demonstrate that the complex motion sequences generated by our algorithm can achieve diverse and smooth motion transitions between keyframes, even for long-term synthesis.
Co-Separable Nonnegative Matrix Factorization
It aims to find a low rank approximation for nonnegative data M by a product of two nonnegative matrices W and H. In general, NMF is NP-hard to solve while it can be solved efficiently under separability assumption, which requires the columns of factor matrix are equal to columns of the input matrix.
Nonnegative Low Rank Tensor Approximation and its Application to Multi-dimensional Images
The main aim of this paper is to develop a new algorithm for computing nonnegative low rank tensor approximation for nonnegative tensors that arise in many multi-dimensional imaging applications.
Orthogonal Nonnegative Tucker Decomposition
In this paper, we study the nonnegative tensor data and propose an orthogonal nonnegative Tucker decomposition (ONTD).
Generalized Separable Nonnegative Matrix Factorization
Given a data matrix $M$ and a factorization rank $r$, NMF looks for a nonnegative matrix $W$ with $r$ columns and a nonnegative matrix $H$ with $r$ rows such that $M \approx WH$.
Tucker Decomposition Network: Expressive Power and Comparison
Deep neural networks have achieved a great success in solving many machine learning and computer vision problems.
