Search
Search Results
-
Performance of Different Methods
In this chapter, we will conduct comparative experimental demonstrations of all the proposed methods. It consists of four parts: experimental setup,... -
Learning the external and internal priors for multispectral and hyperspectral image fusion
Recently, multispectral image (MSI) and hyperspectral image (HSI) fusion has been a popular topic in high-resolution HSI acquisition. This fusion...
-
Quality Assessment of Light-Field Image
Light-field (LF) imaging technology is widely applied to the fields like 3D reconstruction, virtual reality and image rendering, and has attracted... -
On Gaussian Sampling, Smoothing Parameter and Application to Signatures
We present a general framework for polynomial-time lattice Gaussian sampling. It revolves around a systematic study of the discrete Gaussian measure... -
LGHAE: Local and Global Hyper-relation Aggregation Embedding for Link Prediction
The Knowledge Graph (KGs) have profoundly impacted many research fields. However, there is a problem of low data integrity in KGs. The... -
Batch Bootstrap** I:
In this series of work, we aim at improving the bootstrap** paradigm for fully homomorphic encryption (FHE). Our main goal is to show that the... -
Efficient low-rank multi-component fusion with component-specific factors in image-recipe retrieval
Image-Recipe retrieval is the task of retrieving closely related recipes from a collection given a food image and vice versa. The modality gap...
-
Numerical Simulation Model Construction of Swept Frequency Dielectric Logging Response Based on Wireless Communication
The current method is faced with the interference of logging signals caused by mud invasion, which cannot meet the real-time requirements. In order... -
An autonomous and intelligent hybrid CNN-RNN-LSTM based approach for the detection and classification of abnormalities in brain
This article shows the identification and classification of abnormalities present in the brain. MRI test is typically conducted to detect...
-
Dynamic relation learning for link prediction in knowledge hypergraphs
Link prediction for knowledge graphs (KGs), which aims to predict missing facts, has been broadly studied in binary relational KGs. However, real...
-
Generating One-Hot Maps Under Encryption
One-hot maps are commonly used in the AI domain. Unsurprisingly, they can also bring great benefits to ML-based algorithms such as decision trees... -
Multi-hop Multi-key Homomorphic Encryption with Less Noise Under CRS Model
The application of information technologies such as big data, artificial intelligence, and cloud computing in the Internet environment makes... -
-
Batch Bootstrap** II:
This work continues the exploration of the batch framework proposed in Batch Bootstrap** I (Liu and Wang, Eurocrypt 2023). By further designing... -
Generalized Visual Information Analysis Via Tensorial Algebra
High-order data are modeled using matrices whose entries are numerical arrays of a fixed size. These arrays, called t-scalars, form a commutative...
-
Partial Shape Similarity by Multi-metric Hamiltonian Spectra Matching
Estimating the similarity of non-rigid shapes and parts thereof plays an important role in numerous geometry analysis applications. We propose a... -
Full Domain Functional Bootstrap** with Least Significant Bit Encoding
Functional bootstrap** (FBS) is a powerful technique that evaluates a look-up table (LUT) while refreshing an LWE ciphertext in FHEW and TFHE... -
A review of hashing based image authentication techniques
In the recent digitization era, image hashing is a key technology, including image recognition, authentication and manipulation detection, among many...
-
Efficient Visual Recognition: A Survey on Recent Advances and Brain-inspired Methodologies
Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general...
-
Towards Practical Multi-key TFHE: Parallelizable, Key-Compatible, Quasi-linear Complexity
Multi-key homomorphic encryption is a generalized notion of homomorphic encryption supporting arbitrary computation on ciphertexts, possibly...