Publications (7)
SoLAR: Error-Resilient Streamable Long-Horizon Free-Viewpoint Video Reconstruction with Anchor Activation and Latent Recalibration
Haotian Zhang, Xu Mo, Yixin Yu +7
Free-Viewpoint Video (FVV) has emerged as a cornerstone of next-generation immersive media systems and attracted widespread attention. Previous methods primarily focus on short vid…
Personalized Clustering via Targeted Representation Learning
Xiwen Geng, Suyun Zhao, Yixin Yu +5
Clustering traditionally aims to reveal a natural grouping structure within unlabeled data. However, this structure may not always align with users' preferences. In this paper, we…
Conch: Competitive Debate Analysis via Visualizing Clash Points and Hierarchical Strategies
Qianhe Chen, Yong Wang, Yixin Yu +3
In-depth analysis of competitive debates is essential for participants to develop argumentative skills and refine strategies, and further improve their debating performance. Howeve…
Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression
Haotian Zhang, Feiyue Long, Yixin Yu +7
Multi-view image compression (MIC) aims to achieve high compression efficiency by exploiting inter-image correlations, playing a crucial role in 3D applications. As a subfield of M…
RecruitScope: A Visual Analytics System for Multidimensional Recruitment Data Analysis
Xiyuan Zhu, Wenhan Lyu, Chaochao Fu +6
Online recruitment platforms have become the dominant channel for modern hiring, yet most platforms offer only basic filtering capabilities, such as job title, keyword, and salary…
Multi-timescale Event Detection in Nonintrusive Load Monitoring based on MDL Principle
Bo Liu, Jianfeng Zhang, Wenpeng Luan +2
Load event detection is the fundamental step for the event-based non-intrusive load monitoring (NILM). However, existing event detection methods with fixed parameters may fail in c…
Non-intrusive Load Monitoring based on Self-supervised Learning
Shuyi Chen, Bochao Zhao, Mingjun Zhong +2
Deep learning models for non-intrusive load monitoring (NILM) tend to require a large amount of labeled data for training. However, it is difficult to generalize the trained models…