PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation

Ji Wang; Shuangqing Zhang; Guo-Sen Xie; Fang Zhao

cs.CVSep 27, 2026

PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation

Authors: Ji Wang, Shuangqing Zhang, Guo-Sen Xie, Fang Zhao

Organizations: Global Institute of Future Technology Shanghai Jiao Tong University Shanghai, 200240, China · School of Intelligence Science and Technology Nanjing University Suzhou, 215163, China · School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing, 210094, China

Abstract

Training-free online video anomaly detection (VAD) with frozen multimodal language models faces two coupled challenges: extracting reliable current-window semantics under causal and computational constraints, and maintaining temporal continuity without repeatedly transmitting high-dimensional history. Encoding history through text can compress visual evidence and introduce semantic bias, whereas retaining visual history expands multimodal context. We introduce PARSEE-VAD, a two-module framework that separates semantic evidence acquisition from score-state evolution. Proposition-Aware Reasoning (PAR) extracts structured propositional evidence from the current causal window and conditionally activates more specific queries when coarse evidence warrants further refinement. By sharing a reusable causal visual prefix across queries, PAR reduces redundant computation through selective execution. Streaming Evidence Escalation (SEE) maps the acquired proposition evidence into a compact score-domain event state through current evidence escalation, then propagates only the resulting bounded state across decisions to support temporal continuity. Experiments on four benchmarks demonstrate strong training-free online performance while selective routing reduces specialist computation and score-state propagation remains sparse. These results support a current-first principle for streaming multimodal inference: resolve present semantics first, then use compact historical state only to repair residual continuity gaps.

Figures & tables

Figure 1: Motivation for PARSEE-VAD. Left: causal event-state ambiguity under no-future and online-budget constraints, including transient evidence gaps. Middle: inference-interface bottlenecks from scalar scoring and high-dimensional textual or visual memory. Right: PARSEE-VAD separates proposition-based semantic evidence acquisition from compact score-state evolution.

Figure 2: Overview of PARSEE-VAD. One causal visual-prefix state is reused across proposition queries. PA-readout yields order-balanced margins $\ell_{k}^{(t)}$ , and PA-routing selectively acquires P3/P4. SEE converts the available proposition evidence into the current-evidence state $L_{t}$ through routed escalation $f$ , then carries bounded score-derived state across decisions to emit $s_{t}$ . The stream uses a 60-frame (2-s) decision stride.

Method	Training- free	Online	UCF-Crime	XD-Violence		MSAD		UBnormal
Method	Training- free	Online	AUC (%)	AUC (%)	AP (%)	AUC (%)	AP (%)	AUC (%)
Sultani et al. (2018)	✗	✗	77.92	–	73.20	–	–	50.30
GODS Wang and Cherian (2019)	✗	✗	70.46	61.56	–	–	–	–
RTFM Tian et al. (2021)	✗	✗	83.31	–	77.81	86.70	66.30	64.94
RTFM (online) † Tian et al. (2021)	✗	✓	80.63	–	72.60	–	–	–
CLIP-TSA Joo et al. (2023)	✗	✗	87.58	–	82.19	–	–	–

Table 1: Comparison with existing video anomaly detection methods. ✓ and ✗ indicate whether each method is training-free or online. Here, online indicates that the reported inference uses only observations available by each decision time. PARSEE-VAD headline metrics use completed-interval benchmark mapping; the corresponding release-time availability view is reported in Table 12 . Provenance of the UBnormal entries is documented in Appendix E.1 .

Method	$D$ (s)	$C$ (s)	$C/D$
REWARD ( Karim et al., 2024 )	6.4	0.500	0.078
MoniTor ( Yang et al., 2025a )	0.6	5.900	9.83
Flashback ( Lee et al., 2025 )	1.0	0.713	0.713
SphereVAD (online) † ( Huang et al., 2026 )	0.167	0.067	0.40
MACD ‡ ( Ouyang et al., 2026 )	1.0	0.520	0.52
PARSEE-VAD (ours)	2.0	1.372	0.686

Table 2: Published online operating points.

Configuration	PA-routing	Score state	Spec. q/w	UCF AUC	MSAD AUC	MSAD AP
Generated (no PA-readout)	–	–	0.000	80.115	88.211	78.071
Q2 only	–	Q2	0.000	84.872	90.275	79.073
+ Q3 (no specialists)	–	$L_{t}$	0.000	84.825	90.273	79.978
+ P3/P4 (non-routed)	$\times$	$L_{t}$	2.000	–	90.245	81.155
+ P3/P4 (PA-routed)	✓	$L_{t}$	0.565	85.071	90.518	81.970
Full PARSEE-VAD	✓	$s_{t}$	0.565	85.146	90.551	82.024

Table 3: Stage-wise ablation of PARSEE-VAD at 512sq.

Figure 3: Efficiency analysis on MSAD. Left: visual-budget accuracy–compute trade-off. Right: latency decomposition for generated scoring, Q2-only, non-routed all-probe, and routed PARSEE inference.

Figure 4: Mechanistic analysis. (a) Representative suppression and reinforcement cases with routed P3/P4 evidence and PARSEE-VAD scores. (b) Distributions of nonzero score-state adjustments. Active is the fraction of decisions with a nonzero adjustment, $n$ counts active adjustments, and Aligned is the fraction of active adjustments whose sign moves the score in the local ground-truth-consistent direction.

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Inference strategy	Model s/window $\downarrow$	Total s/window $\downarrow$	Model speedup $\uparrow$	Mean headwise logit MSE $\downarrow$
Independent full forward	2.494	4.006	1.00 $\times$	0.0000
Native prefix reuse (ours)	0.839	2.383	2.97 $\times$	0.0214

Appendix

Table 4: Shared-prefix reuse: efficiency, routing fidelity, and score impact on MSAD.

Variant	Specialists / win.	Model mean	Total mean	Total med.	Total P95
		(s)	(s)	(s)	(s)
Q2 only	0.000	0.802	1.271	1.190	1.687
Dense all-probe	2.000	1.073	1.581	1.499	1.988
PARSEE routed	0.565	0.884	1.372	1.378	1.741

Appendix

Table 5: Full-set MSAD runtime at 512sq.

Dataset	Operating point	AUC (%) $\uparrow$	AP (%) $\uparrow$	Mean E2E (s) $\downarrow$	P95 E2E (s) $\downarrow$
MSAD	9F / 60F stride	90.551	82.024	1.372	1.741
MSAD	4F / 30F stride	90.423	83.059	0.753	0.931
UCF-Crime	9F / 60F stride	85.146	–	–	–
UCF-Crime	4F / 30F stride	84.567	–	0.485	0.658

Appendix

Table 6: Canonical and low-latency PARSEE-VAD operating points. The 4F/30F rows use the same model, 512sq budget, PA-routing, and SEE rules as the main system. Matching full-set UCF-Crime timing for the canonical 9F/60F setting was not retained, so those timing cells are left blank.

(a) Current-escalation strength $\alpha$
$\alpha$	UCF AUC	MSAD AUC	MSAD AP	Comment
0.25	85.052	90.557	81.266	weaker local update
0.50	85.132	90.632	82.085
0.625	85.144	90.602	82.101
0.75 (used)	85.146	90.551	82.024	deployed
0.875	85.134	90.457	81.851

Appendix

Table 7: Sensitivity of PAR acquisition and SEE current escalation.

		Q2 only		PARSEE-VAD		$\Delta$
Backbone	Size	AUC $\uparrow$	AP $\uparrow$	AUC $\uparrow$	AP $\uparrow$	AUC	AP
Qwen3.5-2B	2B	88.499	77.869	87.514	78.881	-0.985	+1.012
VideoLLaMA3-7B	7B	88.986	79.071	89.311	81.162	+0.325	+2.090
Qwen3.5-9B	9B	90.275	79.073	90.551	82.024	+0.276	+2.951

Appendix

Table 8: Backbone robustness on MSAD at 512sq.

Dataset	Current update (%)	Temporal maintenance (%)	Final valley gate (%)
UCF-Crime	23.8	1.1	0.32
MSAD	43.8	2.9	0.69
XD-Violence	40.7	2.9	0.56

Appendix

Table 9: SEE intervention density across datasets.

(a) Compute gating versus evidence selection; final score $s_{t}$
Configuration	Specialists / win.	Total s / win.	AUC	AP
PA-routed acquisition	0.565	1.372	90.551	82.024
Always compute + routed mask	2.000	1.581	90.551	82.024
Always compute + dense evidence	2.000	1.581	90.280	81.233
(b) Budget-matched acquisition; current-evidence state $L_{t}$
Uniform random, 1,000 seeds	0.565	–	$90.147\pm 0.116$	$80.312\pm 0.508$

Appendix

Table 10: MSAD routing audit on a shared 512sq proposition bank.

Policy	Specialists / win.	AUC	AP
Dense all specialists	2.000	67.537	25.476
Uniform random	0.527	$68.213\pm 0.224$	$28.952\pm 0.654$
Generic uncertainty	0.527	68.090	31.488
PAR semantic routing	0.527	68.779	34.418

Appendix

Table 11: Cross-dataset routing diagnostic on UCF-Crime.

	UCF AUC	XD-Violence		MSAD
Stage	C / A	AUC C / A	AP C / A	AUC C / A	AP C / A
Q2	84.872 / 83.953	92.640 / 90.774	76.047 / 71.465	90.275 / 88.118	79.073 / 76.257
$L_{t}$ (current)	85.071 / 84.148	92.940 / 91.041	78.876 / 74.015	90.518 / 88.242	81.970 / 78.697
$s_{t}$ (final)	85.146 / 84.208	92.999 / 91.082	79.016 / 74.104	90.551 / 88.236	82.024 / 78.669

Appendix

Table 12: Completed-interval and anchor-aligned score availability.

Dataset	Contrast	$\Delta$ AUC (95% CI)	$\Delta$ AP (95% CI)
UCF-Crime	Q2 $\rightarrow L_{t}$	+0.199 [ $-0.098$ , +0.536]	–
	$L_{t}\rightarrow s_{t}$	+0.075 [+0.031, +0.129]	–
XD-Violence	Q2 $\rightarrow L_{t}$	+0.300 [ $-0.099$ , +0.738]	+2.828 [+0.734, +5.155]
	$L_{t}\rightarrow s_{t}$	+0.060 [+0.034, +0.088]	+0.140 [+0.074, +0.210]
MSAD	Q2 $\rightarrow L_{t}$	+0.243 [ $-0.505$ , +1.446]	+2.897 [ $-1.204$ , +7.466]
	$L_{t}\rightarrow s_{t}$	+0.032 [ $-0.008$ , +0.079]	+0.054 [ $-0.046$ , +0.168]

Appendix

Table 13: Paired video-level bootstrap of score-state increments.

	Q2 only		PARSEE-VAD		$\Delta$
Dataset	AUC	AP	AUC	AP	AUC	AP
UCF-Crime	84.43	34.52	84.69	38.67	+0.25	+4.14
XD-Violence	92.24	74.74	92.73	78.35	+0.49	+3.61
MSAD	89.63	78.92	90.11	82.47	+0.48	+3.54

Appendix

Table 14: Decision-anchor stage decomposition.

	Forward only		Reverse only		Balanced		Flip (%)
Dataset	AUC	AP	AUC	AP	AUC	AP
UCF-Crime	84.33	33.28	84.06	34.98	84.43	34.52	10.5
XD-Violence	92.06	73.98	91.85	73.93	92.24	74.74	24.1
MSAD	89.92	78.79	89.01	78.83	89.63	78.92	7.9

Appendix

Table 15: Option-order sensitivity of the Q2 proposition readout.

Current-evidence update rule	UCF-Crime		XD-Violence		MSAD
Current-evidence update rule	AUC	AP	AUC	AP	AUC	AP
Signed specialist correction (main)	84.69	38.67	92.73	78.35	90.11	82.47
Positive-only specialist reinforcement	84.54	36.09	93.01	78.46	90.10	82.49

Appendix

Table 16: Specialist evidence semantics at decision anchors.

Temporal rule	UCF AUC	XD AUC	XD AP	MSAD AUC	MSAD AP
Current-evidence state $L_{t}$	85.071	92.940	78.876	90.518	81.970
Causal MA3	85.630	92.651	77.606	89.405	79.504
Causal EMA ( $\beta=0.5$ )	85.987	93.348	79.620	89.752	80.290
Causal Max-3	85.560	92.221	75.230	89.891	79.325
Final score $s_{t}$	85.146	92.999	79.016	90.551	82.024

Appendix

Table 17: Temporal maintenance and parameter sensitivity.

Explore similar work

Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection
Sep 15, 2026Jiawei Gu, Qilin Zhao, Tengkuo Guo +6Training-Free Video Anomaly Detection Anomaly Score
School of Intelligence Science and Technology, Nanjing University, Suzhou 215163, China · Faculty of Life Science and Medicine, School of Medicine and Health, Harbin Institute of Technology, Harbin 150001, China · School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150001, China +2
CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection
May 22, 2026Hyeongmuk Lim, Youngbum HurTraining-Free Video Anomaly Detection Fine-Grained Video Understanding
Department of Industrial Engineering, Inha University, Incheon, Republic of Korea
Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding
Oct 1, 2026Mohd Ubaid Wani, Sara Atito, Josef Kittler +1Training-Free Video Anomaly Detection Fine-Grained Video Understanding
Centre for Vision, Speech and Signal Processing (CVSSP) University of Surrey, UK · Surrey Institute for People-Centred AI (PAI) University of Surrey, UK

Sep 15, 2026, cs.CVJ/K move · Enter open · S save

Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection

Jiawei Gu, Qilin Zhao, Tengkuo Guo, Zhiming Zhong+5

School of Intelligence Science and Technology, Nanjing University, Suzhou 215163, China · Faculty of Life Science and Medicine, School of Medicine and Health, Harbin Institute of Technology, Harbin 150001, China · School of Instrumentation Science and Engineering, Harbin Institute of Technology, Harbin 150001, China+2

Training-Free Video Anomaly Detection Anomaly Score Visual Evidence

Open paper AskPDF arXiv

Video anomaly detection (VAD) aims to localize anomalous events in untrimmed videos. Vision-language models (VLMs) provide rich visual understanding for training-free VAD, but existing approaches impose restrictive interfaces between visual understanding and anomaly scoring. Caption-based pipelines compress visual evidence into text, potentially discarding subtle cues, while direct numerical generation forces the model to express its judgment through a small set of predefined scores. Such interfaces can obscure subtle differences in anomaly severity, causing visually distinct clips to receive similar representations or scores and thereby limiting the resolution of anomaly ranking. We propose \textbf{Probe-VAD}, an ordinal binary-probing framework that directly probes severity preferences from a frozen VLM. Given raw video clips, Probe-VAD queries ten ordered severity thresholds and extracts constrained \textit{YES}/\textit{NO} continuation likelihoods. Their normalized preferences form a cumulative severity profile, from which tail evidence is aggregated into a continuous anomaly score, with isotonic projection enforcing ordinal consistency. Experiments on public VAD benchmarks demonstrate superior performance with low computational cost. Probe-VAD provides a simple interface for translating frozen VLM visual understanding into continuous, rank-sensitive anomaly scores without task-specific training or caption-based compression. Code is available at: https://github.com/yvestine/COVAS-VAD.

Abstract

Explore similar work

Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection

CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection

Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding