Fingerprint
Dive into the research topics of 'Real-time Architecture for Audio-Visual Active Speaker Detection'. Together they form a unique fingerprint.- Sort by
- Weight
- Alphabetically
Real-time Architecture for Audio-Visual Active Speaker Detection
Min Huang, Wen Wang, Zheyuan Lin, Fiseha B. Tesema, Shanshan Ji, Jason Gu, Minhong Wan, Wei Song, Te Li, Shiqiang Zhu
Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review