Capsule Network is a novel and promising neural network in the field of deep learning, which has shown good performance in image classification by encoding features into capsules and constructing the part-whole relationships. However, the original Capsule Network is not suitable for the images with complex background due to its weak ability of feature extraction, a large number of training parameters, and the characteristic of explaining everything in the image. To address the above issues, we propose an advanced Capsule Network named RS-CapsNet, which uses Res2Net block to extract multi-scale features, and Squeeze-and-Excitation (SE) block to highlight useful features and suppress useless features. Meanwhile, we adopt the method of linear combination between capsules, which enhances the representation ability of capsules for detected object and reduces the number of capsules. Moreover, we propose the method of firstly constructing intermediate capsules that can represent most of the detected object, and then using the intermediate capsules and primary capsules to construct the classification capsules together. The experimental results show that proposed RS-CapsNet has better performance on CIFAR10, CIFAR100, SVHN, FashionMNIST, and AffNIST datasets, it can also provide better translation equivariance, and the number of training parameters is reduced by 65.11%.

Convolutional neural networks (CNNs) have achieved great success in visual recognition because of the availability of large-scale image datasets, such as the ImageNet. The transfer of convolutional features to challenging scene recognition remains an open problem. Multiple non-linear transforms endow the convolutional features with abundant information. On the other side, CNNs are adept at capturing the holistic appearances of scenes, whereas the lack of some critical local details may reduce the recognition accuracy. To address these problems, we propose a novel hierarchical coding algorithm to learn effective representations. To adapt the scale variations, many useful patches with various scales sampled from the whole image are considered to provide the sufficient details. Non-negative sparse decomposition model (NNSD) based on convolutional features is proposed to learn the sharable components for each scale and further produce global signatures. Based on the global signatures, inter-class linear coding (ICLC) is proposed to learn the discriminative components and ultimate image representations. Experimental results indicate that our approach significantly improves the recognition accuracy compared with general CNN models and achieves excellent performance on five standard benchmarks.

Recently, with the popularization of camera tools such as mobile phones and the rise of various short video platforms, a lot of videos are being uploaded to the Internet at all times, for which a video retrieval system with fast retrieval speed and high precision is very necessary. Therefore, content-based video retrieval (CBVR) has aroused the interest of many researchers. A typical CBVR system mainly contains the following two essential parts: video feature extraction and similarity comparison. Feature extraction of video is very challenging, previous video retrieval methods are mostly based on extracting features from single video frames, while resulting the loss of temporal information in the videos. Hashing methods are extensively used in multimedia information retrieval due to its retrieval efficiency, but most of them are currently only applied to image retrieval. In order to solve these problems in video retrieval, we build an end-to-end framework called deep supervised video hashing (DSVH), which employs a 3D convolutional neural network (CNN) to obtain spatial-temporal features of videos, then train a set of hash functions by supervised hashing to transfer the video features into binary space and get the compact binary codes of videos. Finally, we use triplet loss for network training. We conduct a lot of experiments on three public video datasets UCF-101, JHMDB and HMDB-51, and the results show that the proposed method has advantages over many state-of-the-art video retrieval methods. Compared with the DVH method, the mAP value of UCF-101 dataset is improved by 9.3%, and the minimum improvement on JHMDB dataset is also increased by 0.3%. At the same time, we also demonstrate the stability of the algorithm in the HMDB-51 dataset.