6 papers
Patch as Node: Human-Centric Graph Representation Learning for Multimodal Action Recognition
Zeyu Liang, Hailun Xia, Naichuan Zheng
While human action recognition has witnessed notable achievements, multimodal methods fusing RGB and skeleton modalities still suffer from their inherent heterogeneity and fail to…
LLM Collaboration With Multi-Agent Reinforcement Learning
Shuo Liu, Tianle Chen, Zeyu Liang +2
A large amount of work has been done in Multi-Agent Systems (MAS) for modeling and solving problems with multiple interacting agents. However, most LLMs are pretrained independentl…
Empowering Global Voices: A Data-Efficient, Phoneme-Tone Adaptive Approach to High-Fidelity Speech Synthesis
Yizhong Geng, Jizhuo Xu, Zeyu Liang +3
Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic com…
SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion
Naichuan Zheng, Hailun Xia, Zeyu Liang +1
Multimodal human action recognition based on RGB and skeleton data fusion, while effective, is constrained by significant limitations such as high computational complexity, excessi…
Occamy: A Preemptive Buffer Management for On-chip Shared-memory Switches
Danfeng Shan, Yunguang Li, Jinchao Ma +7
Today's high-speed switches employ an on-chip shared packet buffer. The buffer is becoming increasingly insufficient as it cannot scale with the growing switching capacity. Nonethe…
Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition
Zeyu Liang, Hailun Xia, Naichuan Zheng +1
Skeleton-based action recognition has achieved remarkable performance with the development of graph convolutional networks (GCNs). However, most of these methods tend to construct…