Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies
Answering questions about long videos often requires connecting events involving the same objects across hours or days. Chronological descriptions and text-derived entities can leave physical identity unresolved: different objects may share a description, while observations of the same object remain disconnected across events. Retrieving relevant events therefore does not necessarily recover the…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
