跳到正文
Google AI Developers· @googleaidevs · X·· 2026-09-02AI 评分51
AI 导读

Google AI Developers 演示 Gemini 3.7 Flash 使用新的 agentic video understanding 能力准确数出视频中每一次鼓掌。默认静态处理以固定 1 FPS 摄取视频,拍手这类瞬间动作容易被完全漏掉或与打响指、点击混淆,新能力可自动按需调整处理速度来识别快速动作。

正文 · 原文

Can Gemini count the number of claps? 👏

Accurately counting rapid movements is a notoriously tricky task for AI. Because static processing ingests video at a fixed 1 FPS by default, split-second movements like a clap easily get missed entirely or get confused with a snap or click.

Watch Gemini 3.7 Flash use the new agentic video understanding capability to accurately identify and count every single clap by automatically adapting the processing speed as needed:

来源:Google AI Developers · x.com