236 Result(s)
-
Article
Part-pixel transformer with smooth alignment fusion for domain adaptation person re-identification
The method of generating pseudo-labels by clustering is proved to be effective in unsupervised domain adaptation (UDA) person re-identification (re-ID). However, the pseudo-labels contain a lot of noise, which...
-
Article
Tracking treatment effect heterogeneity in evolving environments
Heterogeneous treatment effect (HTE) estimation plays a crucial role in develo** personalized treatment plans across various applications. Conventional approaches assume that the observed data are independen...
-
Article
Margin distribution and structural diversity guided ensemble pruning
Ensemble methods that train and combine multiple learners have always been among the state-of-the-art learning methods, and ensemble pruning aims at generating a smaller-sized ensemble with even better general...
-
Article
An image reranking algorithm based on discrete-time quantum walk
In order to further improve the performance of image retrieval, a novel image reranking algorithm based on discrete-time quantum walk is proposed. In this algorithm, a discrete-time quantum walk model based on...
-
Article
Towards enabling learnware to handle heterogeneous feature spaces
The learnware paradigm was recently proposed by Zhou (2016) with the wish of develo** the learnware market to help users build models more efficiently by reusing existing well-performed models rather than start...
-
Article
A visually secure image encryption algorithm based on block compressive sensing and deep neural networks
A novel visually secure image encryption algorithm is proposed by combining compressive sensing and deep neural networks. To achieve a tradeoff between the visual quality and the reconstruction quality in diff...
-
Chapter and Conference Paper
Mining the Potential Temporal Features Based on Wearable EEG Signals for Driving State Analysis
Fatigue driving is considered to be one of the main factors causing traffic accidents, so fatigue driving detection technology has an important role in road safety. Currently, EEG-based detection is one of the...
-
Chapter and Conference Paper
Stress Expression Identification Model for Emotion-Driven Association Calculation over Social Network Blogs
Emotion and stress expression are deeply intertwined. Analyzing blog data from social network platforms reveals that specific emotions often appear simultaneously with expressions indicating stress, and emotio...
-
Chapter and Conference Paper
Distributed Backdoor Attacks in Federated Learning Generated by DynamicTriggers
The emergence of federated learning has alleviated the dual challenges of data silos and data privacy and security in machine learning. However, this distributed learning approach makes it more susceptible to ...
-
Article
A new visually meaningful double-image encryption algorithm combining 2D compressive sensing with fractional-order chaotic system
A visually meaningful double-image image encryption algorithm is proposed based on a fractional-order chaotic system combined with 2D compressive sensing (CS). Specifically, in the pre-encryption phase, a 2D d...
-
Article
Geometrically Preserved Dual Projections Learning for Multi-label Classification
Multi-label classification encounters great challenges in processing high dimensional input feature and output label spaces. In this paper, we propose a geometrically preserved dual projections learning of bot...
-
Article
Learnware: small models do big
There are complaints about current machine learning techniques such as the requirement of a huge amount of training data and proficient training skills, the difficulty of continual learning, the risk of catast...
-
Article
A visually meaningful image encryption algorithm based on adaptive 2D compressive sensing and chaotic system
A novel visually meaningful image encryption algorithm is proposed based on adaptive 2D compressive sensing and chaotic system. The plain image is first compressed and encrypted simultaneously by adaptive 2D c...
-
Article
Dual projection learning with adaptive graph smoothing for multi-label classification
In multi-label learning, the high dimensions of both label and feature spaces pose great challenges to multi-label classification. In this paper, we propose dual projection learning with adaptive graph smoothi...
-
Article
Efficient color image encryption by color-grayscale conversion based on steganography
Traditional image encryption algorithms usually aim to encrypt the RGB channels of color plain images separately. In this paper, a novel dimension reduction method is proposed for color image encryption, where...
-
Chapter and Conference Paper
Leg Mass Influences the Jum** Performance of Compliant One-legged Robots
Compliant leg behavior and the spring-loaded inverted pendulum (SLIP) model help understand the dynamics of legged locomotion while few works could be found discussing the effects of leg mass, which is an intr...
-
Article
Rehearsal: learning from prediction to decision
-
Chapter and Conference Paper
Study on Reference Materials of Polymerase Chain Reaction Analyzer
This paper introduces the principle, structure and development process of a verification device for polymerase standard analyzer. The absorbance reference material is developed and fixed on the special test st...
-
Chapter and Conference Paper
Multi-objective Evolutionary Ensemble Pruning Guided by Margin Distribution
Ensemble learning trains and combines multiple base learners for a single learning task, and has been among the state-of-the-art learning techniques. Ensemble pruning tries to select a subset of base learners ...
-
Article
Intelligent circulation system modeling using bilateral matching theory under Internet of Things technology
The purpose is to promote the supply–demand market circulation of agricultural products and agricultural informationization. First, Artificial Intelligence (AI) and Internet of Things (IoT) applications in the...