SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness

• URL: http://arxiv.org/abs/2607.02886v1
• Date: Fri, 03 Jul 2026 02:34:50 GMT
• Title: SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness
• Abstract summary: We introduce a training-free detector that operates on patch tokens from a frozen vision encoder to detect both fully generated and partially edited videos.<n>SPLIT computes two complementary signals: Two-step Temporal Roughness (TTR) and Local Spatial Motion Incoherence (LSMI)<n>We propose a service-aligned evaluation protocol based on Fake Recall at fixed FPR with real-only threshold calibration and cross-real threshold transfer.
• Score: 4.774658730084455
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Deploying AI-generated video detectors in real-world services demands an ultra-low false positive rate (FPR) on real videos to avoid falsely rejecting authentic content, a regime where standard metrics such as AUROC fail to reflect actual operating behavior. We introduce Spatial Patch-Level Incoherence and Temporal Roughness (SPLIT), a training-free detector that operates on patch tokens from a frozen vision encoder to detect both fully generated and partially edited videos. SPLIT computes two complementary signals: Two-step Temporal Roughness (TTR), capturing non-smooth patch trajectories via one-step and two-step feature variation contrast, and Local Spatial Motion Incoherence (LSMI), measuring spatially inconsistent temporal changes through gradients of a feature-space motion field. The two are fused multiplicatively with gamma correction to sharpen real-fake separation at strict thresholds. We further propose a service-aligned evaluation protocol based on Fake Recall at fixed FPR with real-only threshold calibration and cross-real threshold transfer. Across three benchmarks (FakeParts, GenVideo, and ViF-Bench), SPLIT achieves the highest Fake Recall at FPR = $0.1\%$, substantially outperforming supervised and training-free baselines while remaining robust to post-processing with negligible overhead. The code is publicly available at https://github.com/mldljyh/SPLIT .

Related papers

• Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection [0.27998963147546135]
  We introduce a lightweight federated MIL-VLM cascade in which only a compact MIL scorer is trained across clients, while a frozen VLM verifies high-scoring suspect segments post hoc.<n>We study two VLM feedback interfaces: parsed text-generation decisions and a logit-based interface that extracts a continuous anomaly score from next-token Yes/No probabilities.<n>In contrast, the logit interface provides a fixed-free signal that improves both frame-level AUC and frame-level AP over the MIL baseline across both VLMs.
  arXiv  Detail & Related papers  (2026-09-07T13:04:00Z)
• PERSIST: Persistent-State Discrimination for Shot Boundary Detection [2.2822910284300355]
  Shot boundary detection (SBD) is widely treated as the localisation of local visual discontinuities.<n>We reformulate SBD as boundary semantic discrimination.<n>PerSIST turns every decision into an inspectable one.
  arXiv  Detail & Related papers  (2026-08-29T14:23:00Z)
• LeVJEPA: Efficient & Scalable Video Pretraining without the Heuristics [50.45297537821907]
  We introduce LeVJEPA, the first video encoder trained under LeJEPA's collapse-free objective.<n>A single encoder is trained with an invariance loss over global and local views of a clip.<n>LeVJEPA matches or surpasses V-JEPA 2 across ViT-S/B/L at 5.6 to 20.8x less pretraining compute.
  arXiv  Detail & Related papers  (2026-08-27T17:26:24Z)
• Addressing Detail Bottlenecks in Latent Diffusion for RGB-to-SWIR Image Translation [3.8750462550584044]
  Latent diffusion models (LDMs) enable efficient image-to-image translation but discard fine details during compression.<n>We identify two bottlenecks: the autoencoder, which loses information, and the conditioning pathway, which further degrades the source signal through naive downsampling.<n>We propose two lightweight, backbone-agnostic fixes: a Source-Conditioned Autoencoder (SCAE) that injects high-resolution source features into the decoder via skip connections, and a Learnable Guidance (LGE) that replaces naive downsampling with a learned conditioning signal.
  arXiv  Detail & Related papers  (2026-06-18T08:59:03Z)
• GIRL-DETR: Gradient-Isolated Reinforcement Learning for Video Moment Retrieval [10.034595422596562]
  Video Moment Retrieval (VMR) task requires accurately localizing temporal boundaries aligned with natural language queries.<n>GIRL-DETR introduces RL post-training into a lightweight temporal localization framework for the first time.
  arXiv  Detail & Related papers  (2026-05-30T15:40:00Z)
• CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL [56.969946199335716]
  We introduce a compositional constraint-based reward model for post-training embodied video generation models.<n>We propose CreFlow, a novel online RL framework with two key designs.
  arXiv  Detail & Related papers  (2026-05-14T02:18:58Z)
• PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs [57.790910044227935]
  Video LLMs suffer from temporal inconsistency: small shifts in frame timing can flip attention and suppress relevant frames.<n>We present Phase Aggregated Smoothing (PAS), a training-free mechanism that applies small opposed phase offsets across heads and then aggregates their outputs.<n>Our analysis shows that the RoPE rotated logit can be approximated as a content dot product scaled by a time kernel; smoothing this kernel yields Lipschitz stability of attention to small temporal shifts; multi phase averaging attenuates high frequency ripples while preserving per-head spectra under Nyquist-valid sampling.
  arXiv  Detail & Related papers  (2025-11-14T05:56:47Z)
• Real-Time LiDAR Super-Resolution via Frequency-Aware Multi-Scale Fusion [0.4078247440919472]
  FLASH (Frequency-aware LiDAR Adaptive Super-resolution with Hierarchical fusion) is a novel framework that overcomes limitations through dual-domain processing.<n> FLASH integrates two key innovations: (i) Frequency-Aware Window Attention that combines local spatial attention with global frequency-domain analysis via FFT, capturing both fine-grained geometry and periodic scanning patterns at log-linear complexity, and (ii) Adaptive Multi-Scale Fusion that replaces conventional skip connections with learned position-specific feature aggregation, enhanced by CBAM attention for dynamic feature selection.
  arXiv  Detail & Related papers  (2025-11-10T18:38:15Z)
• Learning to Recognize Correctly Completed Procedure Steps in Egocentric Assembly Videos through Spatio-Temporal Modeling [11.720299001244976]
  We propose a dual-stream framework for Procedure step recognition (PSR)<n>STORM-PSR is evaluated on the MECCANO and IndustReal datasets.<n>It reduces the average delay between actual and predicted assembly step completions by 11.2% and 26.1%, respectively.
  arXiv  Detail & Related papers  (2025-10-14T11:03:30Z)
• Stable Video Infinity: Infinite-Length Video Generation with Error Recycling [76.91310169118408]
  We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines.<n> SVI incorporates Error-Recycling Fine-Tuning, a new type of efficient training that recycles the Diffusion Transformer's self-generated errors into supervisory prompts.<n>We evaluate SVI on three benchmarks, including consistent, creative, and conditional settings, thoroughly verifying its versatility and state-of-the-art role.
  arXiv  Detail & Related papers  (2025-10-10T09:45:46Z)
• Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects [70.48554424894728]
  We develop a Global Context Aggregation Network (GCANet) for lightweight saliency detection of surface defects on the encoder-decoder structure. First, we introduce a novel transformer encoder on the top layer of the lightweight backbone, which captures global context information through a novel Depth-wise Self-Attention (DSA) module. The experimental results on three public defect datasets demonstrate that the proposed network achieves a better trade-off between accuracy and running efficiency compared with other 17 state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-22T06:19:11Z)
• UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection [52.91782218300844]
  We propose a novel Unsupervised Inconsistency-Aware method based on Vision Transformer, called UIA-ViT. Due to the self-attention mechanism, the attention map among patch embeddings naturally represents the consistency relation, making the vision Transformer suitable for the consistency representation learning.
  arXiv  Detail & Related papers  (2022-10-23T15:24:47Z)
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
  This paper explores a relatively less-studied methodology based on classification. We propose new techniques to push its frontier in two aspects. Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-11-19T05:42:02Z)
• Two-branch Recurrent Network for Isolating Deepfakes in Videos [17.59209853264258]
  We present a method for deepfake detection based on a two-branch network structure. One branch propagates the original information, while the other branch suppresses the face content. Our two novel components show promising results on the FaceForensics++, Celeb-DF, and Facebook's DFDC preview benchmarks.
  arXiv  Detail & Related papers  (2020-08-08T01:38:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.