What's the Catch? Evaluating Temporal Consistency in Vision-Language Models

2026-08-24

AI Summary

研究通过引入TimeCatch方法检测视觉-语言模型在视频序列中对时间一致性的敏感度，揭示了模型在帧级异常检测上的成功与时间异常检测上的不足。

Abstract

Vision-language models (VLMs) achieve strong performance on video and image-sequence benchmarks, yet it remains unclear whether they capture temporal structure. To study this question, we formulate temporal grounding as an anomaly detection problem, providing a simple and controlled evaluation that directly tests sensitivity to temporal consistency. We introduce TimeCatch, where temporal anomalies are created by swapping consecutive frames and frame-level anomalies by replacing a frame with Gaussian noise. Models are evaluated on anomaly detection and localization tasks across four synthetic and real-world datasets, alongside a human study. Our evaluation reveals a substantial gap between frame-level and temporal anomaly detection. While VLMs consistently detect frame-level anomalies and often localize them accurately, they perform near chance on temporal anomaly detection and only modestly above chance on localization. Humans, in contrast, achieve near-ceiling performance on both tasks. Additional analyses across model scales, prompting strategies, sequence lengths, and visual similarity suggest that these failures cannot be explained solely by limitations in perception or model capacity. Together, these findings indicate that current VLMs can identify anomalies within individual frames but struggle to integrate information across frames to reason about temporal consistency. TimeCatch provides a controlled benchmark for evaluating temporal grounding in vision-language models.

Problem

• Temporal Consistency
• Vision-Language Models
• Anomaly Detection

Innovation

• Temporal Consistency
• Anomaly Detection
• Vision-Language Models
• TimeCatch