GEB addresses a failure mode of chronological or text-derived video memory: descriptions can conflate distinct objects that share a name, and fragment a single object observed under different states or locations.
Grounding long-video memories in visual identity lets QA systems track objects across days
The authors' GEB framework links observations of the same physical object across clips and retrieves those linked biographies when answering questions.
Big Tech
Hui Ren · Lei Fan · Henry Pao · Han Guo · Zeeshan Zia · Ying Chen · +2 more
University of Illinois Urbana-Champaign · Amazon.com, Inc.
Research Digest··2 min read
The authors introduce Grounded Entity Biographies (GEB), a long-video memory framework that groups visually grounded observations of the same physical instance across clips into retrievable biographies.
Why this paper
From Amazon.com, Inc. and University of Illinois Urbana-Champaign
In one line
Grounded Entity Biographies link visually identified objects across video clips to answer questions about long recordings.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§