This paper investigates LVLMs’ behavior in VAD from a visual-textual co-occurrence perspective, and proposes VAD-DPO, a direct preference optimization method supervised with counter-example pairs that enhances both anomaly detection and reasoning performance, particularly in scene-dependent scenarios.
This work proposes a novel Text-Driven Video Anomaly Detection (TD-VAD) approach, which utilizes video-like text descriptions with temporal characteristics generated by LLM to train a VAD model, without any reliance on target-domain anomaly data.
The effectiveness of large language models in transportation mode detection (TMD) remains underexplored, creating a significant research gap in understanding how these models process trajectory data, and which trajectory formats and prompting strategies best support LLM-based inference in human mobility.
This work proposes REcognition-based Zero-shot Extraction (REZE), a simple training-free method that splits the video into short clips, asks the model for a clip-level confidence score for the query, and uses a deterministic algorithm to convert the resulting score curve into the output required by the task.
The presented framework can detect and classify GNSS spoofing attacks in real-time while requiring relatively low computational and memory resources, and is therefore suitable for deployment on resource-constrained vehicular computing platforms.
A novel test-time evidence calibration framework that improves both reasoning details and prediction reliability by introducing a tree search mechanism to progressively acquire localized, fine-grained visual evidence, coupled with a test-time calibration module to mitigate score biases.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
