Aidong Lu
YOU?
Author Swipe
View article: Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition Open
Zero-shot skeleton-based action recognition aims to develop models capable of identifying actions beyond the categories encountered during training. Previous approaches have primarily focused on aligning visual and semantic representations…
View article: FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition Open
Transformer-based human skeleton action recognition has been developed for years. However, the complexity and high parameter count demands of these models hinder their practical applications, especially in resource-constrained environments…
View article: Effect of thumbtack needle therapy at ST36 on postoperative ileus: A pragmatic randomized controlled trial
Effect of thumbtack needle therapy at ST36 on postoperative ileus: A pragmatic randomized controlled trial Open
Objective This study aims to evaluate the efficacy of thumbtack needle (TN) therapy at the ST36 acupoint in reducing postoperative ileus (POI) duration following elective abdominal surgery. Background Postoperative ileus (POI) is a frequen…
View article: Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer Open
Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based appro…
View article: What User Behaviors Make the Differences During the Process of Visual Analytics?
What User Behaviors Make the Differences During the Process of Visual Analytics? Open
The understanding of visual analytics process can benefit visualization researchers from multiple aspects, including improving visual designs and developing advanced interaction functions. However, the log files of user behaviors are still…
View article: Part Aware Contrastive Learning for Self-Supervised Action Recognition
Part Aware Contrastive Learning for Self-Supervised Action Recognition Open
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represent…
View article: Part Aware Contrastive Learning for Self-Supervised Action Recognition
Part Aware Contrastive Learning for Self-Supervised Action Recognition Open
In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represent…
View article: [Ultrasound-guided stellate ganglion block improves sleep quality in elderly patients early after thoracoscopic surgery for lung cancer: a randomized controlled study].
[Ultrasound-guided stellate ganglion block improves sleep quality in elderly patients early after thoracoscopic surgery for lung cancer: a randomized controlled study]. Open
Ultrasound-guided SGB improves objective and subjective sleep quality in elderly patients early after thoracoscopic surgery for lung cancer to alleviate stress responses and sleep disorders, reduce postoperative hospital stay, and accelera…
View article: SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition
SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition Open
Fully supervised skeleton-based action recognition has achieved great progress with the blooming of deep learning techniques. However, these methods require sufficient labeled data which is not easy to obtain. In contrast, self-supervised …
View article: A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose
A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose Open
Existing deep learning-based human mesh reconstruction approaches have a tendency to build larger networks in order to achieve higher accuracy. Computational complexity and model size are often neglected, despite being key characteristics …
View article: Poisoning Attacks on Fair Machine Learning
Poisoning Attacks on Fair Machine Learning Open
Both fair machine learning and adversarial learning have been extensively studied. However, attacking fair machine learning models has received less attention. In this paper, we present a framework that seeks to effectively generate poison…
View article: Nucleotide sequence of a 5S ribosomal RNA gene in the sea urchin Lytechinus variegatus
Nucleotide sequence of a 5S ribosomal RNA gene in the sea urchin Lytechinus variegatus Open
The nucleotide sequence of a cloned DNA fragment corresponding to a gene for 5S ribosomal RNA from the sea urchin
View article: One-Class Adversarial Nets for Fraud Detection
One-Class Adversarial Nets for Fraud Detection Open
Many online applications, such as online social networks or knowledge bases, are often attacked by malicious users who commit different types of actions such as vandalism on Wikipedia or fraudulent reviews on eBay. Currently, most of the f…
View article: ImWeb
ImWeb Open
Web services have become one major way for people to obtain and explore information nowadays. However, web browsers currently only offer limited data analysis capabilities, especially for large-scale 3D datasets. This project presents a me…
View article: Object-based Visual Attention Quantification using Head Orientation in VR Applications
Object-based Visual Attention Quantification using Head Orientation in VR Applications Open
This paper presents a method to measure what and how deep users can perceive when exploring virtual reality environments using a head mounted display.A preliminary user study was conducted to verify that user gaze behavior has specific dif…
View article: Storytelling and Visualization: An Extended Survey
Storytelling and Visualization: An Extended Survey Open
Throughout history, storytelling has been an effective way of conveying information and knowledge. In the field of visualization, storytelling is rapidly gaining momentum and evolving cutting-edge techniques that enhance understanding. Man…
View article: One-Class Adversarial Nets for Fraud Detection
One-Class Adversarial Nets for Fraud Detection Open
Many online applications, such as online social networks or knowledge bases, are often attacked by malicious users who commit different types of actions such as vandalism on Wikipedia or fraudulent reviews on eBay. Currently, most of the f…
View article: Immersive Visualization for Abnormal Detection in Heterogeneous Data for On-site Decision Making
Immersive Visualization for Abnormal Detection in Heterogeneous Data for On-site Decision Making Open
The latest advances in mixed reality promote new capabilities that allow head-mounted displays, such as Microsoft HoloLens, to visualize various data and information in a real physical environment. While such new features have great potent…
View article: Storytelling and Visualization: A Survey
Storytelling and Visualization: A Survey Open
Throughout history, storytelling has been an effective way of conveying information and knowledge. In the field of visualization, storytelling is rapidly gaining momentum and evolving cutting-edge techniques that enhance understanding. Man…
View article: Spectrum-based deep neural networks for fraud detection
Spectrum-based deep neural networks for fraud detection Open
In this paper, we focus on fraud detection on a signed graph with only a small set of labeled training data. We propose a novel framework that combines deep neural networks and spectral graph analysis. In particular, we use the node projec…
View article: Interactive Movie Recommendation Through Latent Semantic Analysis and Storytelling
Interactive Movie Recommendation Through Latent Semantic Analysis and Storytelling Open
Recommendation has become one of the most important components of online services for improving sale records, however visualization work for online recommendation is still very limited. This paper presents an interactive recommendation app…
View article: On Spectral Analysis of Directed Signed Graphs
On Spectral Analysis of Directed Signed Graphs Open
It has been shown that the adjacency eigenspace of a network contains key information of its underlying structure. However, there has been no study on spectral analysis of the adjacency matrices of directed signed graphs. In this paper, we…
View article: TRI-Direct: Interactive Visual Analysis of TRI Data
TRI-Direct: Interactive Visual Analysis of TRI Data Open
In this work, we present TRI-DIRECT, an interactive visual analytic system with capabilities to analyze spatio-temporal data for both professional and novice users. The system is motivated by the Toxic Release Inventory (TRI) program of US…
View article: Are Environmental RegulationsWorking? A Visual Analytic Approach To Answering Their Impact on Toxic Emissions
Are Environmental RegulationsWorking? A Visual Analytic Approach To Answering Their Impact on Toxic Emissions Open
Acquisition and analysis of environmental data are essential to the quality, safety and health of human life, and typically consist of heterogeneous, multivariate, and spatio-temporal information collected from different resources. In the …