AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision

Peng Wu, Jing Liu, Yujia Shi, Yujia Sun, Fangtao Shao, Zhaoyang Wu, Zhiwei Yang

ECCV 2020 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 579 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add audio (VGGish) to RGB input (ablation)HL-Net · XD-ViolenceAP (%): +3.2%Improved
add audio (VGGish) to Flow input (ablation)HL-Net · XD-ViolenceAP (%): +3.5%Improved
add localized and score branches to holistic branch (ablation)HL-Net · XD-ViolenceAP (%): 75.44 -> 78.64Improved
add holistic and score branches to localized branch (ablation)HL-Net · XD-ViolenceAP (%): 76.60 -> 78.64Improved
add score branch to holistic and localized branches (ablation)HL-Net · XD-ViolenceAP (%): 77.23 -> 78.64Improved
use offline detection instead of online (HLC approximator)HL-Net · XD-ViolenceAP (%): 73.67 -> 78.64Improved
use I3D RGB features instead of C3DHL-Net · XD-ViolenceAP (%): 67.19 -> 78.64Improved
use similarity Version 2 with learnable weights instead of Version 1 (ablation)HL-Net · XD-ViolenceAP (%): 78.64 -> 79.04No clear effect
increase sampling length threshold Gamma from 100 to 200 (ablation)HL-Net · XD-ViolenceAP (%): 78.30 -> 78.64No clear effect
add audio to RGB for Abuse class (ablation)HL-Net · XD-Violence AbuseAP (%): 90.10 -> 83.43Hurt
add audio to RGB for Shooting class (ablation)HL-Net · XD-Violence ShootingAP (%): 83.51 -> 90.30Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy