EUVIMEDEUVIMED entdecken
Crossref

SafeLens: Segment-Level Hate Speech Detection in Online Videos

Zhuoran Wang, Dylan Raharja, Yujia Hu, Roy Ka-Wei Lee

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41712-41714

DOI: 10.1609/aaai.v40i48.42390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhuoran Wang und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present SafeLens, a lightweight segment-level video moderation system that fuses speech, text, and visual frames to produce hateful content detection for each segment. For every segment, SafeLens returns a structured prediction: label, prediction confidence, reasons for flag, harm categories. The structured predictions are optimized for triage, appeals, and downstream enforcement. The system is modular (pluggable speech, text, and visual processing modules back-ends and a mid-size policy Language Language Model (LLM) agent with parameter-efficient tuning). In the live demo, attendees can upload or select clips, scrub the timeline to flag hateful segments, inspect rationales, and vary the policy LLM agent to benchmark the hateful content moderation performance.

Zitieren

APA

Wang, Z., Raharja, D., Hu, Y., & Lee, R. K. (2026). SafeLens: Segment-Level Hate Speech Detection in Online Videos. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41712-41714. https://doi.org/10.1609/aaai.v40i48.42390

Vancouver

Wang Z, Raharja D, Hu Y, Lee RK. SafeLens: Segment-Level Hate Speech Detection in Online Videos. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41712-41714. doi:10.1609/aaai.v40i48.42390

BibTeX
@article{Wang2026,
  author = {Wang, Zhuoran and Raharja, Dylan and Hu, Yujia and Lee, Roy Ka-Wei},
  title = {SafeLens: Segment-Level Hate Speech Detection in Online Videos},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41712--41714},
  doi = {10.1609/aaai.v40i48.42390}
}
Kostenlos starten →