Zhi-Yi Lin — accepted AI-conference papers

2026

PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction

Zhi-Yi Lin, Thomas Markhorst, Jouh Yeong Chew, Xucong Zhang

CVPR 2026

Human-like multimodal reaction generation is essential for natural group interactions between humans and intelligent embodied AI. However, existing approaches are often limited to single-modality or speaking-only responses in dyadic interactions, making them unsuitable for realistic social scenarios

Cited by 0 Source ↗code ↗Scholar ↗

2018

A 203 FPS VLSI Architecture of Improved Dense Trajectories for Real-Time Human Action Recognition

Zhi-Yi Lin, Jia-Lin Chen, Liang-Gee Chen

ICASSP 2018accepted

This paper introduces architecture with high throughput, low on-chip memory, and efficient data access for Improved Dense Trajectories (iDT) as video representations for realtime action recognition. The iDT feature can capture longterm motion cues better than any existing deep feature, which makes i…

Cited by 0 Source ↗Scholar ↗