SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere | Paper Citation Record

Observation 8fc334e2-902f-472e-8049-7a4aa881f354 · outbound

This paper cites Princeton University Press.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Princeton University Press

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.969789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9f08b2d7-a00a-4235-9723-419c4ab8db73 · outbound

This paper cites Ubnormal: New benchmark for supervised open-set video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Ubnormal: New benchmark for supervised open-set video anomaly detection

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.966267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8dac8c80-07ab-4590-a266-f2910e1d38fd · outbound

This paper cites Llava-onevision-1.5: Fully open framework for democratized multimodal training.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Llava-onevision-1.5: Fully open framework for democratized multimodal training

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.973266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 948e9cc2-df6b-4439-ad27-5cd7d1f14d2d · outbound

This paper cites Qwen3-VL Technical Report.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Qwen3-VL Technical Report

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-11T03:05:54.373124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 393c76e3-84ed-4c63-91f2-2ccaba79951f · outbound

This paper cites Clustering on the unit hypersphere using von mises-fisher distributions.Journal of Machine Learning Research, 6(9).

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Clustering on the unit hypersphere using von mises-fisher distributions.Journal of Machine Learning Research, 6(9)

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.971546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2e744847-429d-4c2c-9d78-652d64f5fbfa · outbound

This paper cites Steering and rectifying latent representa- tion manifolds in frozen multi-modal llms for video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Steering and rectifying latent representa- tion manifolds in frozen multi-modal llms for video anomaly detection

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:54.414353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6789bf88-1f76-44a7-ade4-8553a04d6c50 · outbound

This paper cites Hiprobe-vad: Video anomaly detection via hidden states probing in tuning-free multimodal llms.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Hiprobe-vad: Video anomaly detection via hidden states probing in tuning-free multimodal llms

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.964256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 415ca4ff-dd0a-49c0-b14c-c13cbc27e274 · outbound

This paper cites Prompt-enhanced multiple instance learning for weakly supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Prompt-enhanced multiple instance learning for weakly supervised video anomaly detection

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.968054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dc9aa736-0145-451d-9f04-2f143c1ce809 · outbound

This paper cites Mgfn: Magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Mgfn: Magnitude-contrastive glance-and-focus network for weakly-supervised video anomaly detection

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.975205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 40769f79-6408-482d-a202-d1b15115f65c · outbound

This paper cites No need for real anomaly: Mllm empowered zero-shot video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere No need for real anomaly: Mllm empowered zero-shot video anomaly detection

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:54.387167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 262ef05e-b377-4098-8abc-b6c92c5e9a84 · outbound

This paper cites Mcanet: Multimodal caption aware training-free video anomaly detection via large language model.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Mcanet: Multimodal caption aware training-free video anomaly detection via large language model

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.021820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d7e0ee8a-a3c0-4ba3-9639-ae675c26279d · outbound

This paper cites Concept decompositions for large sparse text data using clustering.Machine learning, 42(1):143–175.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Concept decompositions for large sparse text data using clustering.Machine learning, 42(1):143–175

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.057812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 42b15f8b-58c4-4e55-b105-66d20b1088dd · outbound

This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:48:27.616218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ec1bd183-4fdd-4827-b026-8d98dd95ccfe · outbound

This paper cites Clip-tsa: Clip-assisted temporal self- attention for weakly-supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Clip-tsa: Clip-assisted temporal self- attention for weakly-supervised video anomaly detection

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.991845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3f41cf13-0796-471e-b7b1-987ece6f11d4 · outbound

This paper cites Refinevad: Semantic-guided feature recalibration for weakly supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Refinevad: Semantic-guided feature recalibration for weakly supervised video anomaly detection

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.034302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6677d502-f6e5-4038-a5d3-25c6df59fb85 · outbound

This paper cites Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median.Journal of experimental social psychology, 49(4):764–766.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median.Journal of experimental social psychology, 49(4):764–766

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.066756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9d336898-4403-4e85-b313-d64eceec4ecf · outbound

This paper cites Cutpaste: Self-supervised learning for anomaly detection and localization.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Cutpaste: Self-supervised learning for anomaly detection and localization

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.063183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ecfce604-66b6-4ec0-91f6-b7eb9d09721b · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.080680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1915fbe5-df01-478e-9211-61662d4007ec · outbound

This paper cites Vadtree: Explainable training-free video anomaly detection via hierarchical granularity-aware tree.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Vadtree: Explainable training-free video anomaly detection via hierarchical granularity-aware tree

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:54.428921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 961f4137-bd7b-436d-9bf4-614ae436e88e · outbound

This paper cites A unified reasoning framework for holistic zero-shot video anomaly analysis.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere A unified reasoning framework for holistic zero-shot video anomaly analysis

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:54.444349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eb95ee86-b439-4b53-9873-7a4d3efe0fef · outbound

This paper cites Improved baselines with visual instruction tuning.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Improved baselines with visual instruction tuning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.030751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b9868235-fd23-48e5-8de7-dde4571375d1 · outbound

This paper cites Few-shot scene-adaptive anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Few-shot scene-adaptive anomaly detection

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.001484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e9e70761-252b-4030-8c43-df8b81d70e0a · outbound

This paper cites Sherlock: Towards multi-scene video abnormal event extraction and localization via a global-local spatial-sensitive llm.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Sherlock: Towards multi-scene video abnormal event extraction and localization via a global-local spatial-sensitive llm

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.007144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d721b6f5-41b3-4f2a-b615-69c68b96fbbc · outbound

This paper cites Just dance with pi! a poly-modal inductor for weakly- supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Just dance with pi! a poly-modal inductor for weakly- supervised video anomaly detection

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.027096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 17cd1893-a5e5-4080-8b3b-0824c66d3b19 · outbound

This paper cites John Wiley & Sons.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere John Wiley & Sons

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.003036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae2a34f5-fbdc-4182-bb41-aef782efd693 · outbound

This paper cites Self-trained deep ordinal regression for end-to-end video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Self-trained deep ordinal regression for end-to-end video anomaly detection

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.056055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f1a951ec-c6ca-4d30-8bed-7e041883b4c5 · outbound

This paper cites Intrinsic statistics on riemannian manifolds: Basic tools for geometric measurements.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Intrinsic statistics on riemannian manifolds: Basic tools for geometric measurements

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.014456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1708cda4-bc6c-4e65-8c5e-95cdb53e8773 · outbound

This paper cites Learning transferable visual models from natural language supervision.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Learning transferable visual models from natural language supervision

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.997501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b68e1f6a-eaf1-40d7-806e-8dc06e41d270 · outbound

This paper cites A survey of single-scene video anomaly detection.IEEE transactions on pattern analysis and machine intelligence, 44(5):2293–2312.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere A survey of single-scene video anomaly detection.IEEE transactions on pattern analysis and machine intelligence, 44(5):2293–2312

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.984448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fd360dbf-572e-474e-8de6-392a22597709 · outbound

This paper cites Eventvad: Training-free event-aware video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Eventvad: Training-free event-aware video anomaly detection

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.979031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9332883b-4fd8-4f8a-bf0b-02815322657a · outbound

This paper cites Animating rotation with quaternion curves.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Animating rotation with quaternion curves

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.995599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 98ab1d39-82b2-4b8a-9c09-c5bb3b08b461 · outbound

This paper cites Real-world anomaly detection in surveillance videos.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Real-world anomaly detection in surveillance videos

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.049518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 44303ab9-caad-413f-adae-06ce27a59681 · outbound

This paper cites Qwen3.5: Accelerating productivity with native multimodal agents, February 2026.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Qwen3.5: Accelerating productivity with native multimodal agents, February 2026

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.019910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 80a62e46-aacf-4846-aca7-66bbb2d9c344 · outbound

This paper cites Dyannet: A scene dynamicity guided self-trained video anomaly detection network.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Dyannet: A scene dynamicity guided self-trained video anomaly detection network

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.078807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4bc2e341-33aa-4b95-b9bd-de15deeb8f98 · outbound

This paper cites Weakly-supervised video anomaly detection with robust temporal feature magnitude learning.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Weakly-supervised video anomaly detection with robust temporal feature magnitude learning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.988134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fef88032-776c-4a43-9204-e15e64b65ed4 · outbound

This paper cites Not only look, but also listen: Learning multimodal violence detection under weak supervision.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Not only look, but also listen: Learning multimodal violence detection under weak supervision

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.980770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 04447a31-7443-40e4-aff7-ff6a61881022 · outbound

This paper cites Open- vocabulary video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Open- vocabulary video anomaly detection

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.016251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 577113fb-1057-4775-bb08-b8aae0f2dba2 · outbound

This paper cites Weakly supervised video anomaly detection and localization with spatio-temporal prompts.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Weakly supervised video anomaly detection and localization with spatio-temporal prompts

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.025358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b7fa4b35-f038-4bea-8470-d026e9b6a51a · outbound

This paper cites Vadclip: Adapting vision-language models for weakly supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Vadclip: Adapting vision-language models for weakly supervised video anomaly detection

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.009100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 51df2852-7226-4c61-bed9-06d9ca3742bb · outbound

This paper cites Panda: Towards generalist video anomaly detection via agentic ai engineer.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Panda: Towards generalist video anomaly detection via agentic ai engineer

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:54.351346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b408c8d2-e73a-415a-9368-eec01660c3c6 · outbound

This paper cites Text prompt with normality guidance for weakly supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Text prompt with normality guidance for weakly supervised video anomaly detection

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.023614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 13fabfdb-49b5-4424-98e9-4a3678f12de1 · outbound

This paper cites Vera: Explainable video anomaly detection via verbalized learning of vision-language models.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Vera: Explainable video anomaly detection via verbalized learning of vision-language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.005160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c90c86f3-b140-466e-8443-8b15f5ddde8b · outbound

This paper cites Harnessing large language models for training-free video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Harnessing large language models for training-free video anomaly detection

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.028923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a370ffc7-42b6-4f0b-8e9b-73c34c5b2515 · outbound

This paper cites Draem-a discriminatively trained reconstruction embedding for surface anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Draem-a discriminatively trained reconstruction embedding for surface anomaly detection

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.046235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b686c060-7397-4d20-baa9-f2514b9a0fd4 · outbound

This paper cites Holmes-vau: Towards long-term video anomaly understanding at any granularity.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Holmes-vau: Towards long-term video anomaly understanding at any granularity

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.993592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 57b2abf3-d5f6-45a5-9a70-3a5e8de34007 · outbound

This paper cites Dual memory units with uncertainty regulation for weakly supervised video anomaly detection.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Dual memory units with uncertainty regulation for weakly supervised video anomaly detection

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.037939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5d890701-ebe1-4864-b77f-bbf89ab781ca · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-05-11T03:05:54.493350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 32bf8c08-72be-4e94-bbda-4d0dc24f3b8b · outbound

This paper cites This provides a consistent starting point in the vicinity of the true Fréchet mean.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere This provides a consistent starting point in the vicinity of the true Fréchet mean

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.032436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bcd8715a-8ba0-4223-accf-478ff19efdbe · outbound

This paper cites Update the estimate via the exponential map: µ(t+1) = Expµ(t) ηg (t) ,(11) whereη >0is the step size.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Update the estimate via the exponential map: µ(t+1) = Expµ(t) ηg (t) ,(11) whereη >0is the step size

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.999768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 43620198-88d4-4135-9c2d-5189072929db · outbound

This paper cites At convergence, g∗ =0, which is the necessary and sufficient first-order condition for the Fréchet mean.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere At convergence, g∗ =0, which is the necessary and sufficient first-order condition for the Fréchet mean

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.990061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1baf7289-d2c1-4f27-9046-cd855257f4cd · outbound

This paper cites Personal Emergency.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Personal Emergency

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.012744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 66e5da31-0dc6-47fa-a0e7-0097700ee95c · outbound

This paper cites Vandalism.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Vandalism

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.059567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fc16d7ed-26e8-4545-9ed6-5b24d29b54fe · outbound

This paper cites Stealing.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Stealing

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.084107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 582c1fb2-6b2f-4171-9a5e-9600feb6d344 · outbound

This paper cites They are completely stripped from the data before any feature extraction or prototype estimation occurs.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere They are completely stripped from the data before any feature extraction or prototype estimation occurs

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.077101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a54a2baf-0fd7-49bb-8dcf-d60111ca184b · outbound

This paper cites an unresolved cited work.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-05-14T11:19:34.082494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cef4ca52-36a5-4e2a-b6e8-c8deee1f60cd · outbound

This paper cites If No, output: None].

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere If No, output: None]

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.072039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 649cf2b4-86eb-452a-980a-938424bea61e · outbound

This paper cites an unresolved cited work.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-14T11:19:34.075410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 23fbd491-0125-44e5-97c4-aa92bd255924 · outbound

This paper cites If category is ‘None’, output: None].

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere If category is ‘None’, output: None]

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.073787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ce236b96-3968-4f51-9c67-a718358cd637 · outbound

This paper cites The whitelist serves as asemantic anchorthat activates latent anomaly-discriminative directions in the intermediate layers, without leaking benchmark-specific category information.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere The whitelist serves as asemantic anchorthat activates latent anomaly-discriminative directions in the intermediate layers, without leaking benchmark-specific category information

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.085954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 284db8ad-e75d-4226-b6a2-235050ee2f44 · outbound

This paper cites four consecutive video frames record the temporal evolution of the same scene.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere four consecutive video frames record the temporal evolution of the same scene

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.061275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1525d3cc-fe91-4a0b-b133-f51a7c4cb844 · outbound

This paper cites an unresolved cited work.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-05-14T11:19:34.064823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 023ab582-f4f7-4155-a226-0ff3c1c5f5fe · outbound

This paper cites visual-last.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere visual-last

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.052762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cf97368b-eb05-4769-af0d-299e691d4d9c · outbound

This paper cites For K=4 sub-images, the code identifies the first K such pairs and marks all tokens between each pair as vision tokens.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere For K=4 sub-images, the code identifies the first K such pairs and marks all tokens between each pair as vision tokens

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.068464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b8605bc4-7ef0-4fb7-accc-81ea9f42261c · outbound

This paper cites If neither method succeeds (an edge case that did not occur in our experiments), f v falls back to f l (the last-token feature).

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere If neither method succeeds (an edge case that did not occur in our experiments), f v falls back to f l (the last-token feature)

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.070388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 13394348-c818-4b2a-99d4-be49a640ae6c · outbound

This paper cites All features areℓ 2-normalised ontoS D−1.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere All features areℓ 2-normalised ontoS D−1

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.054321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation efab0b8c-a9a4-43cc-9e40-41da33308c33 · outbound

This paper cites • Log Density Ratio (LDR):quantifies the separation of per-class density estimates in the feature space.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere • Log Density Ratio (LDR):quantifies the separation of per-class density estimates in the feature space

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.018207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 844703a6-51d1-4b53-9288-40de0488b52d · outbound

This paper cites A higher composite score indicates that features at layer ℓ exhibit stronger anomaly discriminability across all three criteria.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere A higher composite score indicates that features at layer ℓ exhibit stronger anomaly discriminability across all three criteria

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:05:54.474337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 81326941-86be-4ec0-be73-0a3c7dfff1db · outbound

This paper cites As argued in Section C.2, under causal attention the last token has the maximal receptive field, attending to the task instruction, all vision tokens, and the output format.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere As argued in Section C.2, under causal attention the last token has the maximal receptive field, attending to the task instruction, all vision tokens, and the output format

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.977074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4f50a163-6ed2-4423-8138-c587ba301590 · outbound

This paper cites do these two clips depict visually similar scenes?.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere do these two clips depict visually similar scenes?

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.982631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3fb60268-d662-4925-abec-d6654f6cf683 · outbound

This paper cites This removes connections between visually dissimilar clips (e.g., different camera angles or scene transitions within the same video).

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere This removes connections between visually dissimilar clips (e.g., different camera angles or scene transitions within the same video)

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.036204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 12af04bf-1c84-416a-99bd-9f70097deda5 · outbound

This paper cites LLM/VLM Calls.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere LLM/VLM Calls

Reference 71

Resolution: malformed identifier; raw_fallback, observed 2026-05-14T11:19:34.044426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a4552918-88cd-4c0a-afeb-e4c1f8772a14 · outbound

This paper cites This eliminates the need to accumulate statistics over the test set before inference begins—the spherical reference frame is fixeda priori.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere This eliminates the need to accumulate statistics over the test set before inference begins—the spherical reference frame is fixeda priori

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:33.986326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 54a0f213-a7e0-41cc-a691-0bf234f345ba · outbound

This paper cites No test-set statistics are required.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere No test-set statistics are required

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.051074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d2c4c867-69f8-4c0b-93a6-c778044d06e0 · outbound

This paper cites Before Sunrise.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Before Sunrise

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.042799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0917ea2c-480d-4ff6-aa29-d265591461e9 · outbound

This paper cites A single centering operation can absorb this offset.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere A single centering operation can absorb this offset

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.047907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 29b5f45c-cf6b-40fb-a94c-c5fa302eb979 · outbound

This paper cites an unresolved cited work.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-05-14T11:19:34.039623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a9e16836-6ce9-4a94-9743-11ce98edb417 · outbound

This paper cites middle-of-the-plateau.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere middle-of-the-plateau

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.041211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9e4356a5-a336-4b54-8c17-ff499c717bb4 · outbound

This paper cites All remaining operations (Fréchet mean, spherical centering, HSA, vMF scoring, SGP, Gaussian smoothing) are closed-form deterministic computations.

SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere All remaining operations (Fréchet mean, spherical centering, HSA, vMF scoring, SGP, Gaussian smoothing) are closed-form deterministic computations

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T11:19:34.010847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers