Nearest neighbor search aims at obtaining the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining. Hashing is one of the most widely used methods for its computational and storage efficiency. With the development of deep learning, deep hashing methods show more advantages than traditional methods. In this survey, we detailedly investigate current deep hashing algorithms including deep supervised hashing and deep unsupervised hashing. Specifically, we categorize deep supervised hashing methods into pairwise methods, ranking-based methods, pointwise methods as well as quantization according to how measuring the similarities of the learned hash codes. Moreover, deep unsupervised hashing is categorized into similarity reconstruction-based methods, pseudo-label-based methods, and prediction-free self-supervised learning-based methods based on their semantic learning manners. We also introduce three related important topics including semi-supervised deep hashing, domain adaption deep hashing, and multi-modal deep hashing. Meanwhile, we present some commonly used public datasets and the scheme to measure the performance of deep hashing algorithms. Finally, we discuss some potential research directions in conclusion.

Image super‐resolution reconstruction refers to a technique of recovering a high‐resolution (HR) image (or multiple images) from a low‐resolution (LR) degraded image (or multiple images). Due to the breakthrough progress in deep learning in other computer vision tasks, people try to introduce deep neural network and solve the problem of image super‐resolution reconstruction by constructing a deep‐level network for end‐to‐end training. The currently used deep learning models can divide the SISR model into four types: interpolation‐based preprocessing‐based model, original image processing based model, hierarchical feature‐based model, and high‐frequency detail‐based model, or shared the network model. The current challenges for super‐resolution reconstruction are mainly reflected in the actual application process, such as encountering an unknown scaling factor, losing paired LR–HR images, and so on.

Forecasting future traffic flows from previous ones is a challenging problem because of their complex and dynamic nature of spatio-temporal structures. Most existing graph-based CNNs attempt to capture the static relations while largely neglecting the dynamics underlying sequential data. In this paper, we present dynamic spatio-temporal graph-based CNNs (DST-GCNNs) by learning expressive features to represent spatiotemporal structures and predict future traffic flows from surveillance video data. In particular, DST-GCNN is a two stream network. In the flow prediction stream, we present a novel graph-based spatio-temporal convolutional layer to extract features from a graph representation of traffic flows. Then several such layers are stacked together to predict future flows over time. Meanwhile, the relations between traffic flows in the graph are often time variant as the traffic condition changes over time. To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream. Experiments on real datasets demonstrate that the proposed model achieves competitive performances compared with the other state-of-the-art methods.

Vision and language understanding is one of the most fundamental and difficult tasks in Multimedia Intelligence. Simultaneously Visual Question Answering (VQA) is even more challenging since it requires complex reasoning steps to the correct answer. To achieve this, Neural Module Network (NMN) and its variants rely on parsing the natural language question into a module (layout i.e., a problem-solving program). In particular, this process follows a feedforward encoder-decoder pipeline: the encoder embeds the question into a static vector and the decoder generates the layout. However, we argue that such conventional encoder-decoder neglects the dynamic nature of question comprehension (i.e., we should attend to different words from step to step) and per-module intermediate results (i.e., we should discard module performing badly) in the reasoning steps. In this paper, we present a novel NMN, called Self-Adaptive Neural Module Transformer (SANMT), which adaptively adjusts both of the question feature encoding and the layout decoding by considering intermediate Q&A results. Specifically, we encode the intermediate results with the given question features by a novel transformer module to generate dynamic question feature embedding which evolves over reasoning steps. Besides, the transformer utilizes the intermediate results from each reasoning step to guide subsequent layout arrangement. Extensive experimental evaluations demonstrate the superiority of the proposed SANMT over NMN and its variants on four challenging benchmarks, including CLEVR, CLEVR-CoGenT, VQAv1.0, and VQAv2.0 (on average the relative improvement over NMN are 1.5, 2.3, 0.7 and 0.5 points with respect to accuracy).

With the rise of deep learning methods, person Re-Identification (ReID) performance has been improved tremendously in many public datasets. However, most public ReID datasets are collected in a short time window in which persons' appearance rarely changes. In real-world applications such as in a shopping mall, the same person may change their wearings, and different persons may wear similar apparel. It reveals a critical problem that current ReID models heavily rely on a person's apparel, resulting in an inconsistent ReID performance. Therefore, it is crucial to learn an apparel-invariant person representation under clothes changing or several persons wearing similar clothes cases. In this work, we tackle this problem from the viewpoint of invariant feature representation learning. The main contributions of this work are as follows. (1) We propose the semi-supervised Apparel-invariant Feature Learning (AIFL) framework to learn an apparel-invariant pedestrian representation using images of the same person wearing different clothes. (2) To obtain images of the same person wearing different clothes, we propose an unsupervised apparel-simulation GAN (AS-GAN) to synthesize cloth-changing images according to the target cloth embedding. It is worth noting that the images used in ReID tasks were cropped from real-world low-quality CCTV videos, making it more challenging to synthesize cloth-changing images. Extensive experiments demonstrate that our proposal can improve the ReID performance of the baseline models.