The effective utilization of multimodal information is crucial for the task of fake news detection. The primary challenge lies in reducing the semantic distance between the news evidences of different modalities and accurately aligning them in the latent space. It has been observed that the relevance of news image content varies across coarse-to-fine scales, depending on the object and its class label. For instance, the visual evidence to justify a news item sometimes may be a very local detail such as the tiny changes of facial expression and limb position while sometimes may be the global composition. Consequently, how to align news text with image at the most discriminative scale significantly impacts detection performance. However, very few studies have addressed this issue in fake news detection. In this paper, we delve deeper into this issue and propose a simple yet effective Multi-scale Semantic Alignment and Cross-modal Attention (MSACA) network. Specifically, we construct hierarchical multi-scale images for each news data, enhance the semantic consistency between text and images in the latent space, and employ an attention module to select the deterministic embeddings in an end-to-end manner. Extensive experiments on two real-world benchmarks demonstrate the superior performance of our proposed MSACA network.

In industrial enterprises, effective retrieval and reuse of three-dimensional (3-D) computer-aided design (CAD) models could greatly save time and cost in new product development and manufacturing. Consequently, this article proposes a novel view-based approach for 3-D CAD model retrieval enabled by deep learning. This article constructs a multiview model dataset in industrial domain that collects solid and line views of database models. Since views contain rich information for differentiating these models, the problem of model retrieval is defined as a view recognition problem. Then, the extended deep residual networks (ResNets) are successfully trained to facilitate the model retrieval. With the learned networks, engineers could take a group of views, an engineering drawing, or even a hand-drawn sketch that represents their query intents as input and acquire the relevant 3-D CAD models and embedded knowledge for product lifecycle reuse. The experimental results demonstrate the effectiveness and efficiency of the approach.