-
Article
PCMG:3D point cloud human motion generation based on self-attention and transformer
Previous methods for human motion generation have predominantly relied on skeleton representations to depict human poses and motion. These methods typically use a series of skeletons to represent the motion of...
-
Chapter and Conference Paper
SwinFusion: Channel Query-Response Based Feature Fusion for Monocular Depth Estimation
Given a single RGB image, Monocular Depth Estimation (MDE) predicts the depth of each pixel by utilizing both global and local information. Most MDE networks use simple skip connections, each skip connection o...
-
Article
Solving the cooperative scheduling problem of muck transport under time-segment restriction in an entire region
With the acceleration of urbanization, there is an urgent need to build more transportation facilities to alleviate travel pressure. However, during the construction of a subway station, a large amount of muck...
-
Chapter and Conference Paper
Long-Term and Short-Term Perception in Knowledge Tracing
Knowledge Tracing (KT) is a fundamental task in contemporary intelligent educational systems, which tracks the knowledge states of the learners based on their response sequences. KT is crucial for the effectiv...
-
Article
A novel secure DV-Hop localization algorithm against wormhole attacks
IoT era and its ubiquitous sensing raise serious security challenges such as wormhole attacks. Given that these attacks may affect the location determination of the employed sensors, security can be seriously ...
-
Article
Three-view generation based on a single front view image for car
The multi-view of an object can be used for 3D reconstruction. The method proposed in this paper generates the left and the top view of a target car through deep learning. The input of the method is only a fro...
-
Chapter and Conference Paper
GPU-Accelerated Parallel Aligning Long Reads with High Error Rate Using Enhanced Sparse Suffix Array
The read alignment (sequence alignment) is one of the most basic and time-consuming problems in Bioinformatics. In this paper, a CPU-GPU parallel long-read alignment method is studied to solve this problem. A ...
-
Chapter and Conference Paper
Soft Tissue Deformation Estimation Model Based on Spatial-Temporal Kriging for Needle Insertion Procedure
The percutaneous surgery needs to know the soft tissue deformation in real time, but the existing prediction model cannot solve the problem. As a statistical interpolation method, kriging can effectively chara...
-
Article
Decision function with probability feature weighting based on Bayesian network for multi-label classification
The multi-label classification problem involves finding a multi-valued decision function that predicts an instance to a vector of binary classes. Two methods are widely used to build multi-label classifiers: t...
-
Article
Multi-label imbalanced classification based on assessments of cost and value
Multi-label imbalanced data comprise data with a disproportionate number of samples in the classes. Traditional classifiers are more suitable for classifying balanced data because the classification performanc...
-
Chapter and Conference Paper
An Effective Gated and Attention-Based Neural Network Model for Fine-Grained Financial Target-Dependent Sentiment Analysis
In this work, we propose an effective neural network architecture GABi-LSTM to address fine-grained financial target-dependent sentiment analysis from financial microblogs and news. We first adopt a gated mech...
-
Chapter and Conference Paper
Acceptance Strategies for Maximizing Agent Profits in Online Scheduling
In the global logistics market, agents need to decide upon whether to accept jobs offered sequentially. For each offer, an agent makes an immediate selection decision with little knowledge about future jobs; t...
-
Chapter
Multi-player Multi-issue Negotiation with Complete Information
This paper presents a multi-player multi-issue negotiation model to solve a resource allocation problem. We design a multilateral negotiation protocol, by which rational players bid sequentially in consecutive...
-
Chapter and Conference Paper
Efficient Methods for Multi-agent Multi-issue Negotiation: Allocating Resources
In this paper, we present an automated multi-agent multi-issue negotiation solution to solve a resource allocation problem. We use a multilateral negotiation model, by which three agents bid sequentially in co...
-
Chapter and Conference Paper
Autonomous Scheduling with Unbounded and Bounded Agents
Autonomous scheduling deals with the problem - how to enable agents to schedule a set of interdependent tasks in such a way that whatever schedule they choose for their tasks, the individual schedules always c...