Aivora

#visual-grounding

Visual Grounding

1 article

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
arXivVideo AI

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

超越時間線:利用「實體自傳」增強 AI 的長影片記憶與物體追蹤能力

This paper introduces Grounded Entity Biographies (GEB), a framework that compiles cross-clip visual observations of physical objects into retrievable biographies, significantly enhancing long-video question answering.

2 min read