cs.CVMar 16, 2026
SaveTraining-free Detection of Generated Videos via Spatial-Temporal Likelihoods
Organizations: Technion – Israel Institute of Technology, Haifa, Israel
Abstract
Following major advances in text and image generation, the video domain has surged, producing highly realistic and controllable sequences. Along with this progress, these models also raise serious concerns about misinformation, making reliable detection of synthetic videos increasingly crucial. Image-based detectors are fundamentally limited because they operate per frame and ignore temporal dynamics, while supervised video detectors generalize poorly to unseen generators, a critical drawback given the rapid emergence of new models. These challenges motivate zero-shot approaches, which avoid synthetic data and instead score content against real-data statistics, enabling training-free, model-agnostic detection. We introduce STALL, a simple, training-free, theoretically justified detector that provides likelihood-based scoring for videos, jointly modeling spatial and temporal evidence within a probabilistic framework. We evaluate STALL on two public benchmarks and introduce ComGenVid, a new benchmark with state-of-the-art generative models. STALL consistently outperforms prior image- and video-based baselines. Code and data are available at https://omerbenhayun.github.io/stall-video.
Figures & tables
Figure 2: Qualitative comparison of ZED, D3, and our method (STALL). Each row shows a video clip with natural or unnatural spatial and temporal behavior, together with the corresponding predictions. ZED (spatial-only) misses in cases dominated by temporal inconsistency; D3 (temporal-only) fails when spatial realism is misleading. STALL fuses spatial and temporal likelihoods, yielding robust detection when either modality alone is insufficient. Additional examples with more details are given in Supp. D.7.
Figure 3: Method overview. A video is split into frames and encoded into embeddings. The spatial branch scores the likelihood of each frame embedding; the temporal branch normalizes inter-frame differences and scores their likelihood analogously. The two scores are then fused into a unified measure that separates AI-generated from real videos.
Figure 4: Correlations among spatial and temporal aggregation methods. Values computed on VATEX [ 82 ] , which is not used in our evaluations. When all individual likelihood detectors perform reasonably well on the evaluated benchmarks (see Supp. Section D.2), lower correlations are desirable.
Figure 5: Temporal embedding coordinates. Raw coordinates of temporal embeddings (frame differences) are not Gaussian; after normalization, each coordinate is approximately Gaussian (full histogram comparison in Supp. B.2.1).
Figure 6: Comparison of detectors and calibration data. We compare our method against six detectors: three image-based [ 68 , 42 , 28 ] and three video-based [ 93 , 1 , 5 ] , for performance and efficiency. (a) Inference latency per video. (b) Average AUC across all three benchmarks; our method is both high-performing and efficient. (c) GenVideo [ 24 ] results using different datasets as the calibration set, showing that same-distribution calibration is only slightly better, indicating robustness to the calibration choice (see Supp. D.6.6).
Figure 7: Robustness to calibration set size and image perturbations. (a) Varying calibration-set size between 1k to 34k; each size is resampled 5 times and we report mean AUC standard deviation. (b) Robustness to four common image perturbations applied randomly to frames at five severity levels; our method maintains high separation across perturbation type and intensity. Both experiments are performed on GenVideo [ 24 ] .
Figure 8: Temporal ablations. Our method remains robust under all temporal variations: (a) temporal step size for likelihood computation; (b) video length; (c) frame rate (FPS).
| Representation | Test | Avg Score | Threshold | Normal Features | approximately gaussian? |
| Raw embeddings | AD | 0.4750 | 96.3% | ✓ | |
| DP | 0.3931 | 99.2% | ✓ | ||
| Whitened embeddings | AD | 0.5034 | 98.2% | ✓ | |
| DP | 0.3207 | 99.3% | ✓ | ||
| Transition vector | AD | 3.3992 | 0.0% | ✗ | |
| DP | 0.0093 | 0.0% | ✗ |
Table 4: Normality tests. Results of Anderson Darling (AD) and D’Agostino Pearson (DP) normality tests for different representations on the VATEX [ 82 ] calibration set. “Avg Score” is the mean test statistic across embedding coordinates and groups, “Threshold” specifies the acceptance condition for normality, and “Normal Features” is the percentage of coordinates satisfying that condition.
Figure 9: Raw vs. Normalized Temporal Difference Histograms. Histogram comparison of raw temporal differences (Raw , left) versus normalized temporal differences (Normalized , right) for the first four dimensions of DINOv3 [ 71 ] embeddings, computed from all adjacent frame pairs in the VATEX [ 82 ] calibration set. Red curves show Gaussian distributions fitted using the empirical mean and variance of the data (i.e., a moment-matched Gaussian). Even under this moment-matched fit, raw differences exhibit clear deviations from Gaussianity, while normalized differences closely match Gaussian distributions across all dimensions.
Figure 10: Real and AI-generated videos embeddings. Histograms of selected embedding dimensions from DINOv3 [ 71 ] features extracted from randomly sampled frames in the GenVideo [ 24 ] dataset. The left column corresponds to real videos, and the right column corresponds to generated videos. Red curves show Gaussian distributions fitted using the empirical mean and variance of each feature dimension.
Figure 11: Uniformity on the sphere and Gaussian distribution. Histograms of the first coordinate of , where is uniformly distributed on the -dimensional unit sphere , shown for several values of and overlaid with the density.
Figure 12: Uniformity on the sphere. Cosine similarity distributions over all unordered pairs of randomly sampled normalized temporal differences from the VATEX [ 82 ] calibration set and points drawn uniformly from the unit sphere.
Figure 13: Ablations on temporal derivative order. STALL performance for different temporal derivative orders : (a) AUC across orders, (b) Pearson correlation between scores from different orders, and (c) Spearman correlation between scores from different orders.
Figure 14: Components ablation. Bar plots of spatial-only, temporal-only, and combined detectors, using both raw scores and percentile-ranked scores. Spatial and Temporal denote single-branch detectors, and Combined refers to the fused Spatial and Temporal detector. Configurations labeled with “P” use percentile-ranked scores, where “P” stands for percentile. “Avg” stands for average of the two scores and “Prod” stands for the product of the two scores.
Figure 15: Frame-level aggregation ablation. Heatmaps of AP and AUC, for different combinations of spatial and temporal frame-level aggregation operators. Rows correspond to the spatial aggregation and columns to the temporal aggregation, while all other parts of the pipeline follow the default configuration described in the main paper.
Figure 16: Temporal scores under temporal perturbations. Each condition applies a different perturbation to 400 real MSR-VTT videos: Original (no perturbation), Reversed (frames in reverse order), Shuffle (consecutive frames shuffled), Black flash (one black frame inserted mid-video), and White flash (one white frame inserted mid-video). The temporal likelihood is largely unaffected by reversal and shuffling, since adjacent-frame difference statistics are preserved; however, abrupt flash frames cause a strong drop in the score, with white flashes producing a larger degradation than black flashes.
| Perturbation | Implementation | Severity levels (1 5) |
| Gaussian blur | TF.gaussian_blur | |
| JPEG compression | PIL.save(..., | JPEG quality |
| format="JPEG", quality) |
Table 10: Image perturbation details. These perturbations are used in the robustness ablation (Sec. D.5). Levels 1–5 span the full range of corruption strength for each type; level 0 corresponds to no perturbation.
Figure 17: Perturbations example. mandrill.
Figure 18: Perturbations example. Sailboat on lake.
Figure 19: Qualitative examples. Each row shows sampled frames from a video clip, with indicators marking whether its spatial and temporal behavior appears natural or unnatural.
Figure 20: Qualitative examples. Each row shows sampled frames from a video clip, with indicators marking whether its spatial and temporal behavior appears natural or unnatural.
| Domain | Method | Mean [sec] | Std [sec] |
| Zero shot images | AEROBLADE [ 68 ] | 2.5266 | 0.0243 |
| ZED [ 28 ] | 1.1394 | 0.0067 | |
| RIGID [ 42 ] | 0.4363 | 0.0024 | |
| Supervised video | T2VE [ 1 ] | 1.9950 | 0.0102 |
| AIGVdet [ 5 ] | 5.4216 | 0.0787 | |
| Zero-shot video | D3 cos [ 93 ] | 0.2157 | 0.0043 |
Table 12: Inference time comparison for all methods.
| domain | method | model loading cpu (MB) | model loading gpu (MB) | inference cpu peak (MB) | inference gpu peak (MB) |
| zero shot images | AEROBLADE [ 68 ] | 7875.93 | 141.02 | 9711.18 | 2624.43 |
| ZED [ 28 ] | 101.11 | 16.06 | 1707.72 | 310.08 | |
| RIGID [ 42 ] | 142.41 | 327.30 | 1373.67 | 567.57 | |
| supervised video | T2VE [ 1 ] | 1852.16 | 1271.43 | 2795.96 | 140.96 |
| AIGVdet [ 5 ] | 488.77 | 182.59 | 1849.03 | 673.18 | |
| zero-shot video | D3 cos [ 93 ] | 315.64 | 1157.72 | 1470.08 | 160.30 |
Table 13: Memory usage comparison for all methods