Knowledge-Based visual question answering (KBVQA) separates image interpretation and knowledge retrieval into separate processes, motivated in part by the fact that they are very different tasks. In this paper, we transform the KB-VQA into linguistic question-answering tasks so that we can leverage the rich world knowledge and strong reasoning abilities of Large Language Models (LLMs). The caption-then-question approach to KBVQA has been effective, but relies on the captioning method to describe the detail required to answer every possible question. We propose instead a Question-Aware Captioner (QACap), which uses the question as guidance to extract correlated visual information from the image and generate a question-related caption. To train such a model, we utilize GPT-4 to build a corresponding high-quality question-aware caption dataset on top of existing KBVQA datasets. Extensive experiments demonstrate that our QACap model and dataset significantly improve KBVQA performance. Our method, QA-Cap, achieves 68.2% accuracy on the OKVQA validation set, 73.4% on the direct-answer part of the A-OKVQA validation set, and 74.8% on the multiple-choice part, all setting new SOTA benchmarks.

Recently, with wide use of internet and rapid growth of computer networks, the problem of intrusion detection in network security has become an import issue of concern. In this paper, a new intrusion detection algorithm DB-Kmeans has been introduced which combines K-means with DBSCAN. DB-Kmeans uses a new selection method of initial cluster center in K-means and set the neighborhood radius in DBSCAN to dynamic. Compared to K-means algorithm, it overcomes the shortage of sensitivity to initial centers and reduces the impact of noise points. Compared to DBSCAN algorithm, it reduces the influence of fixed neighborhood radius. The experiments on the NSL-KDD data set indicate that the proposed method is more efficient than that based on MinMax K-means algorithm. Also, the method has higher detection accuracy and lower false alarm rate.