Xujian Zhao

ASTRM: Adaptive spatio-temporal reasoning for audio-visual question answering

Mingxiang Wen, Y C Wang, Xujian Zhao, Peiquan Jin et autres

cn (code pays fourni par la source)

BiMaskSum: Bidirectional Vision-Language Masking for Multimodal Summarization

Chunfan Lu, Xujian Zhao, Peiquan Jin, Hongyou Chen et autres

cn (code pays fourni par la source)

A survey on music emotion recognition using learning models

Yixin Wang, Xujian Zhao, Yao Xiao, Haoxin Ruan et autres

cn (code pays fourni par la source)

Fair Causal Decision Tree

Wenkai Chen, Hui Zhang, Chunming Yang, Bo Li et autres

The decision tree algorithm is an effective machine learning technique, but it cannot uncover causal relationships within data. To overcome this limitation, the causal decision tree was proposed, which combines causal discovery with decision tree principles. This method is particularly effective at …

cn (code pays fourni par la source)

Audio-Visual Adaptive Fusion Network for Question Answering Based on Contrastive Learning

Xujian Zhao, Yixin Wang, Peiquan Jin

The Audio-Visual Question Answering (AVQA) task involves extracting question-related audio-visual clues from both temporal and spatial perspectives to answer questions accurately. Despite the promising performance of existing multi-modal AVQA models, thanks to large-scale pre-trained models, challenges remain in the field. Firstly, aligning …

cn (code pays fourni par la source)

Fair Laplace: A unified framework for fair spectral clustering

Zhijing Yang, Hui Zhang, Chunming Yang, Bo Li et autres

cn (code pays fourni par la source)

Multivariate Time-Series Data Anomaly Detection via Dimension Independence and Reconstruction

Jianqiu Xu, Xujian Zhao

Time-series data anomaly detection has received widespread attention from academia and industry, with crucial applications in service monitor, IoT surveillance, and network security. Existing anomaly detection methods for multivariate time-series data (MTS) typically (1) focus solely on low-accuracy anomalies, neglecting explicit errors, …

cn (code pays fourni par la source)

FlyTsViz: A Flight Time Series Data Visual Analytics System Based on Reduction Method

Duosi Jin, Jianqiu Xu, Xujian Zhao

The rapid development of unmanned aerial vehicles (UAVs) and other low-altitude aircraft technologies has dramatically increased the volume of generated flight time series data. These data contain important operational and performance information which is crucial for further analysis and mining, providing valuable …

cn (code pays fourni par la source)

DTI-MPFM: A multi-perspective fusion model for predicting potential drug–target interactions

Chunlin He, Chunming Yang, Hui Zhang, Yin Long et autres

cn (code pays fourni par la source)

CPM: Knowledge Graph Tensor Factorisation Model for Discovering Drug Targets

Chunlin He, Chunming Yang, Bo Li, Hui Zhang et autres

The discovery of novel therapeutic applications for drugs is crucial for drug development. Representation learning methods can uncover unknown relationships between drugs and targets within drug knowledge graphs. However, existing methods often suffer from information loss and insufficient representation of entities and …

cn (code pays fourni par la source)

Scale Fairness on Spectral Clustering

Zhijing Yang, Hui Zhang, Chunming Yang, Bo Li et autres

The fairness and bias of spectral clustering algorithms have attracted considerable research interest in recent years. Currently fair spectral clustering algorithms are based on the notions of group fairness and individual fairness, which effectively reduce decision bias for similar individuals and sensitive …

cn (code pays fourni par la source)

Multi-view subspace clustering based on multi-order neighbor diffusion

Yin Long, Hongbin Xu, Yang Xiang, Chrisy Xiyu Du et autres

Abstract Multi-view subspace clustering (MVC) intends to separate out samples via integrating the complementary information from diverse views. In MVC, since the structural information in the graph is crucial to the graph learning, most of the existing algorithms construct the superficial graph …

cn (code pays fourni par la source)