Deploying Vision-Language Models for video anomaly detection confronts a fundamental constraint. Their semantic reasoning demands computational budgets incompatible with the scale of real-world video streams. We present Signal-Aware Adaptive Fusion (SAAF), a framework that achieves efficient zero-shot anomaly detection through three key innovations. First, we introduce a dual-signal adaptive sampler operating in semantic embedding space: a delta signal captures sudden events via frame-to-frame cosine distance, while a drift signal detects static and gradual anomalies through deviation from rolling temporal context. Their OR-gated combination with adaptive EMA-based thresholding provides comprehensive anomaly coverage without training data. Second, we propose a threshold-gated cascaded architecture where lightweight frame-level scoring precedes expensive video-level temporal analysis, invoking it only when confidence warrants additional context. Third, we design a signal-aware weighted fusion mechanism that dynamically adapts score combination based on which signal triggered frame selection. Across four benchmarks, SAAF delivers competitive accuracy at substantially lower cost. Among training-free zero-shot methods, SAAF sets a new state of the art on XD-Violence (92.07%), MSAD (86.70%), and ShanghaiTech (80.54%) AUC-ROC, with XD-Violence and MSAD also surpassing supervised baselines. SAAF sustains 44.95, 48.61, and 41.06 FPS on XD-Violence, UCF-Crime, and MSAD, a 2.43×, 2.63×, and 2.22× throughput improvement over the prior best zero-shot method. Code: https://github.com/kdawoud91/SAAF
Figures & tables
Figure 1: Comparison of sampling strategies. (a) Dense sampling. (b) Uniform sampling selects at fixed intervals. (c) SAAF adaptively selects within the same uniform stride pool, concentrating frames around anomalous regions (pink), avoiding redundant frames. SAAF achieves efficient coverage of anomalous content while significantly reducing the number of processed frames.
Figure 2: Overview of the SAAF pipeline. Stage 1 extracts delta (frame-to-frame change) and drift (context deviation) signals from CLIP embeddings via adaptive EMA-based thresholding. Stage 2 generates frame-level anomaly scores through VLM captioning and LLM reasoning. Stage 3 conditionally invokes video-level temporal analysis for high-scoring frames, combining frame and video scores via signal-aware weighted fusion. Stage 4 propagates and refines sparse anchor scores to produce dense frame-level predictions.
Method
Sampling Strategy
AnyAnomaly [ 2 ]
Segment length 24, 4 frames per segment
EventVAD [ 24 ]
Stride 16 per event (MLLM)
Holmes-VAU [ 41 ]
Stride 16, then 16 frames via ATS
VERA [ 37 ]
8 frames per 10 s window
STPrompt [ 32 ]
Stride 16 (UCF), stride 4 (Shang)
LAVAD [ 38 ]
Stride 16
Table 1: Sampling strategies adopted by ZS & WS VAD methods.
Figure 3: Per-category AUC-ROC across SAAF pipeline stages. Stage 2 (blue): frame-level scoring. Stage 3 (red): λ -weighted video-level gating. Stage 4 (green): refinement. All categories benefit from multi-stage fusion.
Method
Zero-shot
Training-free
XD [ 30 ]
UCF [ 26 ]
MSAD [ 43 ]
Shang [ 17 ]
AUC(%)
AUC(%)
AUC(%)
AUC(%)
Sultani et al. [ 26 ]
✗
✗
–
77.92
–
–
FusedVision [ 7 ]
✗
✗
–
–
–
83.58
RTFM [ 27 ]
✗
✗
61.56
–
85.67
–
GODS [ 29 ]
✗
✗
–
70.46
–
–
MGFN [ 6 ]
✗
✗
–
86.98
85.0
–
Table 2: VAD Performance comparison across XD, UCF, MSAD and Shang. ✓ / ✗ indicate whether a method is zero-shot and training-free in terms of model parameters. Our SAAF results are mean ± std over 3 runs.
Figure 4: Shows Qualitative results. Each column shows: (a) signal activation patterns with ground-truth anomaly regions shaded in pink, blue vertical lines indicate delta-only activations, green lines indicate drift-only activations, and orange lines indicate frames where both signals are activated; (b) frame-level anomaly scores; and (c) video-level scores after threshold-gated fusion.
Figure 5: Distribution of per-video VLM call reduction relative to uniform stride-16 sampling across benchmark datasets. Higher reduction indicates fewer VLM calls within the stride-16 candidate pool. Adaptive frame selection achieves 20–60% reduction for the majority of videos while preserving detection accuracy.
Component
B
T(s)
# Frames processed
XD
UCF
MSAD
Shang
Stage 1: Signal Extraction (candidate frames)
CLIP ViT-B/32
24
0.14
146,449
69,634
14,360
2,550
Stage 2–3: Frame-Level Scoring (selected frames)
VLM (Qwen3-VL-8B)
24
8.19
102,066
53,283
9,353
1,898
LLM (Qwen2.5-7B)
24
0.64
102,066
53,283
9,353
1,898
Table 3: Per-component computational cost across benchmarks.
XD
UCF
MSAD
Method
FPS
AUC
FPS
AUC
FPS
AUC
LAVAD † [ 38 ]
13.0
85.36
13.0
80.28
–
–
Unified [ 14 ]
18.5
91.34
18.5
84.28
18.5
85.90
SAAF (Ours)
44.95
92.07
48.61
82.59
41.06
86.70
Table 4: Throughput and accuracy across XD, UCF, and MSAD. Measured under identical settings. † LAVAD does not report MSAD.
Figure 6: Signal distribution (%) among selected stride-16 frames.
Backbone
AUC-ROC (%)
CLIP ViT-B/32
92.07
DINOv3 ViT-B/14
91.65
DINOv2 ViT-B/14
91.78
SigLIP2 ViT-B/16
91.61
Table 5: Backbone ablation for signal extraction on XD. All encoders achieve comparable performance. Drift window W=20
Window Size ( W )
AUC-ROC (%)
5
91.77
10
91.79
15
91.80
20
92.07
Table 6: Ablation on rolling window size W for drift signal.
Stage
XD
UCF
MSAD
Shang
2. Frame-level
78.30
64.70
72.13
71.38
3. + λ -gating
88.53
76.27
82.36
75.50
4. + Refinement
92.07
82.59
86.70
80.54
Table 7: Stage-wise ablation across benchmarks. AUC-ROC (%).
Configuration
XD-Viol.
UCF
MSAD
Shang
Stage 2 (no smoothing)
78.30
64.70
72.13
71.38
Stage 2 + smoothing
89.35
73.30
81.78
77.19
Stage 3 + smoothing (Stage 3)
92.07
82.59
86.70
80.54
Table 8: Ablation of refinement components.
Appendix figures & tables9 assets
Supplementary material from the paper’s appendix.
Appendix
Dataset
Events
Recall (%)
Miss
Unhittable
SAAF miss
MSAD
240
98.3
4
1
3
UCF
156
92.3
12
0
12
XD
1210
88.9
134
0
134
Shang
194
77.8
43
22
21
Appendix
Table 9: Event-level recall of Stage 1 selection. Unhittable events contain no stride-16 candidate; SAAF miss events had a candidate but no signal crossed threshold.
Table 11: Selection threshold ablation. Stage 1 AUC-ROC (%) with selection rate relative to uniform stride-16 sampling. Lower N yields higher selection rates but diminished efficiency gains.
sd
XD-Viol.
UCF
MSAD
Shang
0
64.90
55.44
67.50
63.35
0.1
76.26
61.52
72.74
68.15
0.2
78.98
64.90
72.13
71.38
0.3
78.30
64.70
72.13
71.38
Appendix
Table 12: Default fill value ( sd ) ablation. Stage 1 AUC-ROC (%).
XD-Violence
UCF-Crime
MSAD
ShanghaiTech
τf
AUC
Inv.%
AUC
Inv.%
AUC
Inv.%
AUC
Inv.%
0.4
88.53
10.90
76.27
4.7
82.36
16.2
75.50
22.5
0.5
88.00
10.5
75.86
3.4
82.08
16.2
75.35
22.5
0.6
88.00
10.5
75.86
3.4
82.07
16.1
75.35
22.5
0.7
87.87
8.5
75.80
1.8
82.01
15.2
75.61
19.5
0.8
87.81
7.6
75.85
1.5
81.88
12.1
75.47
0.1
Appendix
Table 13: Effect of fusion threshold τf on AUC-ROC (%) and invocation rate (%). Higher τf reduces VLM calls with minimal performance degradation.
Config
λδ
λρ
XD
UCF
MSAD
Shang
firm
0.8
0.2
88.07
75.98
82.08
75.35
moderate
0.7
0.3
88.38
76.19
82.30
75.31
default
0.6
0.4
88.53
76.27
82.36
75.50
reversed
0.2
0.8
88.14
76.08
81.73
76.43
Appendix
Table 14: Signal-aware fusion weight ablation. Stage 2 AUC-ROC (%) under different (λδ,λρ) configurations.
Figure 7: MSAD (11 anomaly categories)
Figure 8: Representative success cases demonstrating SAAF’s detection accuracy and computational efficiency across anomalous (a, b) and normal (c, d) videos.
The collection and detection of video anomaly data has long been a challenging problem due to its rare occurrence and spatio-temporal scarcity. Existing video anomaly detection (VAD) methods under perform in open-world scenarios. Key contributing factors include limited dataset diversity, and inadequate understanding of context-dependent anomalous semantics. To address these issues, i) we propose LAVIDA, an end-to-end zero-shot video anomaly detection framework. ii) LAVIDA employs an Anomaly Exposure Sampler that transforms segmented objects into pseudo-anomalies to enhance model adaptability to unseen anomaly categories. It further integrates a Multimodal Large Language Model (MLLM) to bolster semantic comprehension capabilities. Additionally, iii) we design a token compression approach based on reverse attention to handle the spatio-temporal scarcity of anomalous patterns and decrease computational cost. The training process is conducted solely on pseudo anomalies without any VAD data. Evaluations across four benchmark VAD datasets demonstrate that LAVIDA achieves SOTA performance in both frame-level and pixel-level anomaly detection under the zero-shot setting. Our code is available in https://github.com/VitaminCreed/LAVIDA.
Zunkai Dai, Ke Li, Jiajia Liu +2
Beijing University of Posts and Telecommunications · Northwestern Polytechnical University
Training-free zero-shot video anomaly detection (ZS-VAD) leverages vision-language models (VLMs) to localize anomaly instances from a predefined anomaly vocabulary, without providing any video. Existing CLIP-based methods often emphasize anomaly-side semantics, while the competing normality side remains less carefully formulated. We identify two key limitations in existing solutions: (i) blurred decision boundary: normal prompts may contain ambiguous verbs, such as running, that are semantically close to anomalies, reducing normal and abnormal separation in the VLM embedding space; and (ii) modality gap: poor alignment between features of textual normal anchors and visual frames. We propose NOVA, a training-free ZS-VAD framework that strengthens the normal side at both linguistic and visual levels. NOVA introduces Normality-Aware Prompt Construction (NA), which excludes anomaly-adjacent verbs and biases normal descriptions toward static, low-motion scenes. To overcome the text-vision modality gap, NOVA constructs a Visual Normality Anchor (VNA), which creates a weighted visual normal anchor from the initial frames of each test video, providing a video-specific normal reference without task-specific training or annotations. NOVA achieves 89.86 percent AUC on UCF-Crime and 95.07 percent AUC and 84.82 percent AP on XD-Violence, reaching state-of-the-art performance among comparable training-free zero-shot methods.
Wei-Chih Yin, Yun-Ching Kao, Cheng-Kuan Lin +1
Department of Computer Science, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and curated annotations, limiting generalization in open-set scenarios. Recent zero-shot methods based on Large Vision- Language Models (LVLMs) alleviate this dependency but often lack temporal continuity and structured reasoning. We propose Cog-VADU, a fully training-free framework that reformulates VAD as a sequential cognitive reasoning task. Cog-VADU introduces Chain-of- Anomaly Detection Thought Prompting (CoADTP), which unrolls an LVLM into a recurrent reasoning chain across video segments. By propagating structured rationales over time, the model maintains implicit temporal memory, enabling robust discrimination between com- plex anomalies and high-motion normal activities. To improve reliability, we further design a cross-modal re-ranking stage that aligns textual rationales with visual embeddings, enforcing semantic consistency and temporal coherence for refined and stable predictions. Extensive experiments on multiple public VAD benchmarks demonstrate that Cog-VADU achieves competitive zero-shot performance. Moreover, cross-model evaluations show that CoADTP consistently enhances reasoning-based anomaly detection in a model-agnostic manner, pro- viding interpretable and generalizable anomaly understanding for real-world applications.
Mohd Ubaid Wani, Sara Atito, Josef Kittler +1
Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK · Surrey Institute for People-Centred AI (PAI) University of Surrey, UK