Short-Window Sliding Learning for Real-Time Violence Detection via LLM-based Auto-Labeling

The paper introduces a Short-Window Sliding Learning framework for real‑time violence detection in CCTV footage. It splits videos into 1–2 second clips and uses LLM‑based auto‑caption labeling to build fine‑grained datasets, preserving temporal continuity for accurate recognition of rapid violent events. The method achieves 95.25% accuracy on RWF‑2000 and 83.25% on UCF‑Crime, demonstrating strong generalization and real‑time applicability in intelligent surveillance systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms