Mandarin Audio-Visual Speech Recognition Challenge
MAVSR 2025 aims to advance visual speech analysis technology through two tracks, specifically designed to address the challenges encountered in real-world applications. Specifically, the two tracks are: Track 1 – Visual Speech Recognition under Low-Quality Conditions, and Track 2 – Chinese Visual Keyword Spotting. Through this competition, we hope to inspire the research community to push the boundaries of VSR technology, fostering the development of more robust and practical solutions that can be deployed effectively in diverse real-world environments.
Website: https://vipl.ict.ac.cn/en/resources/challen/202412/t20241203_252138.html
Entry submission deadline: March 12th
AI Innovation Competition
Website: https://sites.google.com/view/ai-innovation-competition-fg25/home
Entry submission deadline: