cs.CVJul 16, 2026

Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection

Authors: Manni Cui, Ziheng Qin, ZiAn Wang, Ruiqi Liu, Dianyuan Zou, Jianglan Wei, Han Zhou, Yu Liu, 

Organizations: Huazhong University of Science and Technology · Institute of Automation, Chinese Academy of Sciences · Jilin University · Vast Intelligence Lab

Abstract

AI-generated videos (AIGVs) typically contain subtle temporal artifacts that arise from inter-frame inconsistencies rather than within individual frames. A detector that captures such artifacts should therefore benefit from video pretrained backbones over image only ones. In practice, however, video backbones with standard global readouts often fail to outperform strong image pretrained probes on AIGV benchmarks. We attribute this gap to excessive spatiotemporal aggregation in the readout. Video pretrained backbones tend to compress each frame into a single global descriptor. This compression suppresses local patch level temporal dynamics and discards inter patch relations, which are precisely the cues that AIGV detection most reliably depends on. Based on this, we propose Velocity Gated Patch Velocity Profiling (V-PVP), a lightweight readout that replaces only the aggregation layer with two parallel streams over the patch velocity field, adding only about 0.50.5M trainable parameters. V-PVP serves as a general plug-and-play module that consistently improves performance across diverse video backbones under both end-to-end fine-tuning and linear probing settings. Our method reaches 95.28 AUC on AIGVDBench while keeping the backbone fully frozen. The results show that simply replacing the aggregation layer reactivates the temporal potential of frozen video backbones, restoring their advantage on AIGV detection. Code is available at https://github.com/manic-cui/Rethinking-the-readout.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Temporal Slice Learning for AI-Generated Video Detection with 400×\times Fewer FLOPs

    Oct 26, 2026Wei Shang, Zhiyuan Li, Shengfeng HeFrequency-Domain AnalysisDeepfake Detection

  2. ATSS: Detecting AI-Generated Videos via Anomalous Temporal Self-Similarity

    Apr 5, 2026Hang Wang, Chao Shen, Lei Zhang +1Deepfake DetectionMultimodal Anomaly Detection

  3. CMTA: Leveraging Cross-Modal Temporal Artifacts for Generalizable AI-Generated Video Detection

    May 1, 2026Hang Wang, Chao Shen, Chenhao Lin +3Cross-Modal AlignmentDeepfake Detection