Multi-modal hashing focuses on fusing different modalities and exploring the complementarity of heterogeneous multi-modal data for compact hash learning. However, existing multi-modal hashing methods still suffer from several problems, including: 1) Almost all existing methods generate unexplainable hash codes. They roughly assume that the contribution of each hash code bit to the retrieval results is the same, ignoring the discriminative information embedded in hash learning and semantic similarity in hash retrieval. Moreover, the length of hash code is empirically set, which will cause bit redundancy and affect retrieval accuracy. 2) Most existing methods exploit shallow models which fail to fully capture higher-level correlation of multi-modal data. 3) Most existing methods adopt online hashing strategy based on immutable direct projection, which generates query codes for new samples without considering the differences of semantic categories. In this paper, we propose a Semantic-driven Interpretable Deep Multi-modal Hashing (SIDMH) method to generate interpretable hash codes driven by semantic categories within a deep hashing architecture, which can solve all these three problems in an integrated model. The main contributions are: 1) A novel deep multi-modal hashing network is developed to progressively extract hidden representations of heterogeneous modality features and deeply exploit the complementarity of multi-modal data. 2) Learning interpretable hash codes, with discriminant information of different categories distinctively embedded into hash codes and their different impacts on hash retrieval intuitively explained. Besides, the code length depends on the number of categories in the dataset, which can reduce the bit redundancy and improve the retrieval accuracy. 3) The semantic-driven online hashing strategy encodes the significant branches and discards the negligible branches of each query sample according to the semantics contained in it, therefore it could capture different semantics in dynamic queries. Finally, we consider both the nearest neighbor similarity and semantic similarity of hash codes. Experiments on several public multimedia retrieval datasets validate the superiority of the proposed method.

In recent years, object detection algorithms have achieved great success in the field of machine vision. To pursue the detection accuracy of the model, the scale of the network is constantly increasing, which leads to the continuous increase in computational cost and a large requirement for memory. The larger network scale allows their execution to take a longer time, facing the balance between the detection accuracy and the speed of execution. Therefore, the developed algorithm is not suitable for real-time applications. To improve the detection performance of small targets, we propose a new method, the real-time object detection algorithm based on transfer learning. Based on the baseline Yolov3 model, pruning is done to reduce the scale of the model, and then migration learning is used to ensure the detection accuracy of the model. The object detection method using transfer learning achieves a good balance between detection accuracy and inference speed and is more conducive to the real-time processing of images. Through the evaluation of the dataset voc2007 + 2012, the experimental results show that the parameters of the Yolov3-Pruning(transfer): model are reduced by 3X compared with the baseline Yolov3 model, and the detection accuracy is improved, realizes real-time processing, and improves the detection accuracy.