StrAD Benchmark
Explore score history ↗StrAD is a benchmark for long-form audio description generation on full-length videos across diverse genres, reformulating the task as streaming dense video captioning without ground-truth timestamps.
- Released
- 2026-08-12
- Institutions
- University of Bonn · Fraunhofer Institute for Intelligent Analysis and Information Systems · Hochschule Bonn-Rhein-Sieg
- Evaluates
- General AI, Vision & 3D, cs.CV
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
StrAD paper
No reported scores are on record for this benchmark yet.