Yangxi Li
YOU?
Author Swipe
View article: Deep Graph Neural Point Process For Learning Temporal Interactive Networks
Deep Graph Neural Point Process For Learning Temporal Interactive Networks Open
Learning temporal interaction networks(TIN) is previously regarded as a coarse-grained multi-sequence prediction problem, ignoring the network topology structure influence. This paper addresses this limitation and a Deep Graph Neural Point…
View article: Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction
Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction Open
The rapid advancement of large language models has raised significant concerns regarding their potential misuse by malicious actors. As a result, developing effective detectors to mitigate these risks has become a critical priority. Howeve…
View article: SelfMedHPM: Self Pre-training With Hard Patches Mining Masked Autoencoders For Medical Image Segmentation
SelfMedHPM: Self Pre-training With Hard Patches Mining Masked Autoencoders For Medical Image Segmentation Open
In recent years, deep learning methods such as convolutional neural network (CNN) and transformers have made significant progress in CT multi-organ segmentation. However, CT multi-organ segmentation methods based on masked image modeling (…
View article: LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning
LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning Open
Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and effec…
View article: Micro–Nano Water Film Enabled High-Performance Interfacial Solar Evaporation
Micro–Nano Water Film Enabled High-Performance Interfacial Solar Evaporation Open
Interfacial solar evaporation holds great promise to address the freshwater shortage. However, most interfacial solar evaporators are always filled with water throughout the evaporation process, thus bringing unavoidable heat loss. Herein,…
View article: Hydrogel for the Treatment of Osteoarthritis
Hydrogel for the Treatment of Osteoarthritis Open
Worldwide, the prevalence of osteoarthritis has grown significantly in recent years, and the rate of growth is accelerating. In recent years, the number of people with osteoarthritis has increased rapidly worldwide, and the rate of increas…
View article: Self-supervised speckle noise reduction of optical coherence tomography without clean data
Self-supervised speckle noise reduction of optical coherence tomography without clean data Open
Optical coherence tomography (OCT) is widely used in clinical diagnosis due to its non-invasive, real-time, and high-resolution characteristics. However, the inherent speckle noise seriously degrades the image quality, which might damage t…
View article: Noise Reduction of OCT Images Based on the External Patch Prior Guided Internal Clustering and Morphological Analysis
Noise Reduction of OCT Images Based on the External Patch Prior Guided Internal Clustering and Morphological Analysis Open
Optical coherence tomography (OCT) is widely used in biomedical imaging. However, noise severely affects diagnosing and identifying diseased tissues on OCT images. Here, a noise reduction method based on the external patch prior guided int…
View article: Long-Short Term Cross-Transformer in Compressed Domain for Few-Shot Video Classification
Long-Short Term Cross-Transformer in Compressed Domain for Few-Shot Video Classification Open
Compared with image few-shot learning, most of the existing few-shot video classification methods perform worse on feature matching, because they fail to sufficiently exploit the temporal information and relation. Specifically, frames are …
View article: RLINK: Deep reinforcement learning for user identity linkage
RLINK: Deep reinforcement learning for user identity linkage Open
User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predictin…
View article: Semi-Supervised Recognition under a Noisy and Fine-grained Dataset
Semi-Supervised Recognition under a Noisy and Fine-grained Dataset Open
Simi-Supervised Recognition Challenge-FGVC7 is a challenging fine-grained recognition competition. One of the difficulties of this competition is how to use unlabeled data. We adopted pseudo-tag data mining to increase the amount of traini…
View article: Learning from Easy to Complex: Adaptive Multi-Curricula Learning for Neural Dialogue Generation
Learning from Easy to Complex: Adaptive Multi-Curricula Learning for Neural Dialogue Generation Open
Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varie…
View article: Type-Aware Anchor Link Prediction across Heterogeneous Networks Based on Graph Attention Network
Type-Aware Anchor Link Prediction across Heterogeneous Networks Based on Graph Attention Network Open
Anchor Link Prediction (ALP) across heterogeneous networks plays a pivotal role in inter-network applications. The difficulty of anchor link prediction in heterogeneous networks lies in how to consider the factors affecting nodes alignment…
View article: Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation Open
Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varie…
View article: Control Strategies and Economic Analysis of an LTO Battery Energy Storage System for AGC Ancillary Service
Control Strategies and Economic Analysis of an LTO Battery Energy Storage System for AGC Ancillary Service Open
With the rapid growth of renewable energy and the DC fast charge pile of the electric vehicle, their inherent volatility and randomness increase a power system’s unbalance of instantaneous power. The need for power grid frequency regulatio…
View article: RLINK: Deep Reinforcement Learning for User Identity Linkage
RLINK: Deep Reinforcement Learning for User Identity Linkage Open
User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predictin…
View article: Research on SOC Estimation Based on Room-temperature SOC-OCV Curve and Capacity Normalization for Li-ion Batteries
Research on SOC Estimation Based on Room-temperature SOC-OCV Curve and Capacity Normalization for Li-ion Batteries Open
The Open Circuit Voltage (OCV) is a measure of the electromotive force of the battery, which has a monotonic relationship with the State of Charge (SOC). This relationship is widely used inSOCestimation. However, Li-ionbatteries have diffe…
View article: Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification Open
Local features at neighboring spatial positions in feature maps have high correlation since their receptive fields are often overlapped. Self-attention usually uses the weighted sum (or other functions) with internal elements of each local…