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 2025.
AI Innovation Competition
Join us at FG 2025 for a live AI Innovation Competition where you interact with an AI interviewer to define research problems, guide an AI innovator that performs research, and vote on the best results in face and gesture recognition. Speak with an AI interviewer, as you do with a research colleague or student that you are advising, who will perform research and write a draft research paper. The AI innovator performs a literature review, generates ideas, writes research proposals, filters them by significance, novelty, and feasibility, ranks them, implements the top ranking plans, runs experiments, writes the paper, reviews, and revises the paper. Vote on the quality, impact, and significance of three generated papers.
Interact, innovate, and vote – redefining scientific research.
Website: https://sites.google.com/view/ai-innovation-competition-fg25
Entry submission deadline: May 16th 2025.