The paper investigates how vision‑language models (VLMs) can be used for training‑free video anomaly detection (VAD) by answering questions about video segments. It shows that the way a VLM’s output is converted into an anomaly score—either by taking only the most likely answer (generated readout) or by using the full probability distribution (probability readout)—has a significant impact on ranking performance. Across four large VLMs, the probability readout consistently outperforms the generated readout, achieving 5–13 point gains in AUROC or AP, because the generated readout compresses the rank order into only a few distinct scores.
arXiv:2608.21244v2 Announce Type: replace Abstract: Anomaly detection aims to identify observations that deviate from normal patterns. Recent work uses pretrained vision-language models (VLMs) for tr...
The paper proposes a lightweight federated multiple‑instance learning (MIL) framework that trains only a compact MIL scorer across distributed clients while using a frozen vision‑language model (VLM) to verify high‑scoring video segments post‑hoc. Two VLM feedback interfaces are explored: a parsed text‑generation interface and a logit‑based interface that derives a continuous anomaly score from next‑token Yes/No probabilities. Experiments on UCF‑Crime with InternVL3.5‑2B and Qwen3‑VL‑2B‑Instruct show that the logit interface consistently improves frame‑level AUC and AP over the MIL baseline without requiring temporal post‑processing, whereas the text‑generation interface is more sensitive to prompts, parsers, and model choice.
arXiv:2607. 13305v1 Announce Type: cross Abstract: Benchmark accuracy in video large language models (LLMs) is often treated as evidence of visual understanding.
arXiv:2606. 22437v2 Announce Type: replace-cross Abstract: We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effectively measure multimodal understanding; 2) many items are already close to performance saturation for current LVLMs, which limits their discriminative power; 3) a small number of anomalous items affect the reliability of evaluation results.
arXiv:2606. 00435v1 Announce Type: cross Abstract: Vision-language models (VLMs) can produce confident visual answers even when the required visual evidence is missing, blank, or unrelated to the question.
The paper investigates how weakly supervised video anomaly detectors, trained with only video‑level labels, are evaluated using frame‑level metrics such as Micro‑AUROC and AP. It shows that these metrics largely measure a detector’s ability to separate different videos rather than correctly ordering anomalous moments within a single video, a phenomenon termed temporal dilution. Experiments demonstrate that a detector can achieve high pooled scores even when it assigns the same score to every frame in a video, indicating that current evaluation practices may overstate temporal localization performance.
arXiv:2603. 18373v4 Announce Type: replace-cross Abstract: When VLMs answer correctly, do they genuinely rely on visual information?
arXiv:2607. 12304v1 Announce Type: cross Abstract: A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions.
A score on a temporal video question answering benchmark is meant to measure that a model has temporal understanding, but it conflates two questions. 1.
arXiv:2607. 18850v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning.
arXiv:2607. 23924v1 Announce Type: cross Abstract: Vision foundation models have enabled strong training-free anomaly detection (AD).
Token-Budget Distillation (TBD) is a parameter‑efficient fine‑tuning framework that adapts video vision‑language models to a fixed token budget. It freezes the pretrained backbone, updates only LoRA adapters, and incorporates FlashVID visual token compression. TBD uses a dual‑path teacher‑student design with full‑token supervision and compressed student optimization, enabling the student to recover full‑token semantics while remaining efficient under aggressive token reduction.