7 papers
Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization
Feng-Qi Cui, Jinyang Huang, Anyang Tong +6
Micro-action Recognition is vital for psychological assessment and human-computer interaction. However, existing methods often fail in real-world scenarios because inter-person var…
STAR: A Benchmark for Astronomical Star Fields Super-Resolution
Kuo-Cheng Wu, Guohang Zhuang, Jinyang Huang +3
Super-resolution (SR) advances astronomical imaging by enabling cost-effective high-resolution capture, crucial for detecting faraway celestial objects and precise structural analy…
Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization
Feng-Qi Cui, Anyang Tong, Jinyang Huang +4
Dynamic Facial Expression Recognition (DFER) plays a critical role in affective computing and human-computer interaction. Although existing methods achieve comparable performance,…
High Performance Space Debris Tracking in Complex Skylight Backgrounds with a Large-Scale Dataset
Guohang Zhuang, Weixi Song, Jinyang Huang +3
With the rapid development of space exploration, space debris has attracted more attention due to its potential extreme threat, leading to the need for real-time and accurate debri…
Empowering Iterative Graph Alignment Using Heat Diffusion
Boyan Wang, Weijie Feng, Jinyang Huang +2
Unsupervised plain graph alignment (UPGA) aims to align corresponding nodes across two graphs without any auxiliary information. Existing UPGA methods rely on structural consistenc…
Optimizing Federated Graph Learning with Inherent Structural Knowledge and Dual-Densely Connected GNNs
Longwen Wang, Jianchun Liu, Zhi Liu +1
Federated Graph Learning (FGL) is an emerging technology that enables clients to collaboratively train powerful Graph Neural Networks (GNNs) in a distributed manner without exposin…