Video Content Moderation

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 12

All topics

Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
Oct 1, 2026Guangyu Yang, Jingbiao Mei, Mingsheng Sun +5Video Content Moderation RL for VLMs
University of Cambridge · Xiaohongshu Inc. · AntGroup +2
Nürnberg NLP at ChildSafeAds 2026: Structurally Dissimilar Voter Ensembles under Four Levels of Data Access
Sep 28, 2026Philipp Steigerwald, Eric Rudolph, Jens AlbrechtOnline Advertising Video Content Moderation
Technische Hochschule Nürnberg Georg Simon Ohm
Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderation
Aug 31, 2026Ruotong Wang, Zihao Zhu, Siwei Lyu +2Multimodal Large Language Models Video Content Moderation
The Chinese University of Hong Kong, Shenzhen · Kling Team, Kuaishou Technology · State University of New York at Buffalo
HALLELUAI: A Hallucination-Aware AI System for Ultra-Realistic Image-to-Video Generation at Scale
Jul 25, 2026Aniket Sakpal, Yang Jiang, Rouzbeh Davoudi +2Image-to-Video Generation Video Content Moderation
Expedia Group
Child-Oriented AIGC Video Risk Reviewing: A Benchmark and Knowledge-Supported Iterative Reasoning Framework
Jul 21, 2026Lewen Mi, Manyi Li, Yuling Sun +5Video Content Moderation
Shandong University · Weihai, Shandong, China · Jinan, Shandong, China +3
R^3: Advertisement Compliance Rectification via Group-Relative Experience Extractor and Curriculum Reinforcement
Jul 8, 2026Yuan Chen, Zhenyu Hu, Mengge Xue +5RL for Language Models Video Content Moderation
Tencent
From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
Jun 29, 2026Shuchang Ye, Jinqiang Yu, Zhujun Xiao +6Video Content Moderation Multimodal Model Evaluation
1TikTok
HarmVideoBench: Benchmarking Harmful Video Understanding in Large Multimodal Models
Jun 25, 2026Jiajun Wu, Haoyu Kang, Yining Sun +13Video Understanding Video Content Moderation
Central South University · Tsinghua University · South China Normal University +10
UNIVID: Unified Vision-Language Model for Video Moderation
Jun 4, 2026Kejuan Yang, Yizhuo Zhang, Mingyuan Du +6Unified Multimodal Models VLM Adaptation
Bytedance
SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening
May 17, 2026Shahriar Kabir Nahin, Hadi Askari, Muhao Chen +1Adaptive Inference Efficient VLM Inference
University of South Florida · University of California, Davis
Latent Space Probing for Adult Content Detection in Video Generative Models
Apr 25, 2026Alizishaan Khatri, Chiquita PrabhuVideo Content Moderation
Wrynx Inc. · Independent Researcher
FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation
Dec 21, 2025Ziyuan Tao, Chuanzhi Xu, Sandaru Jayawardana +4Federated Learning Aggregation Video Content Moderation
School of Computing, Macquarie University, Sydney, Australia · School of Computer Science, The University of Sydney, Sydney, Australia · School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia

Oct 1, 2026, cs.CLJ/K move · Enter open · S save

Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization

Guangyu Yang, Jingbiao Mei, Mingsheng Sun, Jinghong Chen+4

University of Cambridge · Xiaohongshu Inc. · AntGroup+2

Video Content Moderation RL for VLMs

Open paper AskPDF arXiv

The rapid growth of video-based social media has increased users' exposure to harmful content, creating a need for reliable automated video safety detection. Although recent Vision-Language Models (VLMs) show strong video understanding capabilities, existing harmful video detection systems face two key limitations: they typically reduce safety detection to binary classification, overlooking the inherently multi-label nature of unsafe videos, and they rely on static training objectives that do not support controllable precision-recall trade-offs, though the desired operating point may vary across moderation pipelines and unsafe categories. To address these gaps, we propose Adaptive Tversky Policy Optimization (ATPO), a reinforcement learning framework for Multi-label Video Safety Detection (Multi-VSD). ATPO introduces the Adaptive Tversky Reward (ATR), which dynamically adjusts false-positive and false-negative penalties during training to enable controllable precision-recall trade-offs. Experiments on SafeWatch-Bench and XD-Violence show that ATPO substantially improves multi-label performance, increasing the Jaccard Index from 40.66 to 75.44 on SafeWatch-Bench-Real. Moreover, ATR enables reliable steering of the precision-recall operating point, supporting deployment scenarios with heterogeneous policy requirements. Code and checkpoints are provided at https://bruceyg.github.io/ATPO-project-page/ .

Momentum

Related topics

Latest papers 12