Skip to main content
Search

# Identity-Aware Video Captioning

1 related articles

Subscribe to updates
  1. arXiv

    BAC pairs identity-linked boxes with LoRA tuning to reach 93.20% person-centric QA at 8B scale

    Using LSMDC v2 movie clips, the work builds an automatic character-identification and identity-linked spatial grounding pipeline, manually verifies a benchmark of 750 clips and 3,000 person-centric questions, and compares five identity-grounding representations; visual face boxes combined with textual coordinates prove most consistent across scales, and LoRA fine-tuning of Qwen yields BAC, with BAC-8B reaching 93.20% overall person-centric QA accuracy.

You’re all caught up