This article presents an intrafusion network (IFN) for hyperspectral image (HSI) super-resolution (SR). Given that the HSI is a 3-D data cube with both the spatial information and the spectral information, the key challenge to construct HSI SR is how to efficiently exploit the spectral information among consecutive low-resolution (LR) bands, besides the spatial information. The proposed IFN consists of three modules, including the spectral difference module, the parallel convolution module, and the intrafusion module, which directly utilizes both the spatial information and the spectral information for reconstructing the high-resolution HSI. Different from most of the existed methods that tackle the spatial and spectral information separately, the proposed spatial-spectral utilization is achieved in one integrated network, which opens up a new way for HSI SR. Meanwhile, applications of this three modules strategy (first spectral difference, then parallel convolution, and finally, intrafusion) on both the conventional convolutional neural network and the residual network with deeper depth have shown the generalization capacity of this proposal. Experimental results and data analysis demonstrate the effectiveness of the proposed method using three hyperspectral data sets.

Theoretically, hyperspectral images (HSIs) are capable of providing subtle spectral differences between different materials, but in fact, it is difficult to distinguish between background and anomalies because the samples of anomalous pixels in HSIs are limited and susceptible to background and noise. To explore the discriminant features, a spectral adversarial feature learning (SAFL) architecture is specially designed for hyperspectral anomaly detection in this article. In addition to reconstruction loss, SAFL also introduces spectral constraint loss and adversarial loss in the network with batch normalization to extract the intrinsic spectral features in deep latent space. To further reduce the false alarm rate, we present an iterative optimization approach by a weighted suppression function that depends on the contribution rate of each feature to the detection. In particular, the structure tensor matrix is adopted to adaptively calculate the contribution rate of each feature. Benefiting from these improvements, the proposed method is superior to the typical and state-of-the-art methods either in detection probability or false alarm rate.

Integrating deep learning techniques into the video coding framework gains significant improvement compared to the standard compression techniques, especially applying super-resolution (up-sampling) to down-sampling based video coding as post-processing. However, besides up-sampling degradation, the various artifacts brought from compression make super-resolution problem more difficult to solve. The straightforward solution is to integrate the artifact removal techniques before super-resolution. However, some helpful features may be removed together, degrading the super-resolution performance. To address this problem, we proposed an end-to-end restoration-reconstruction deep neural network (RR-DnCNN) using the degradation-aware technique, which entirely solves degradation from compression and sub-sampling. Besides, we proved that the compression degradation produced by Random Access configuration is rich enough to cover other degradation types, such as Low Delay P and All Intra, for training. Since the straightforward network RR-DnCNN with many layers as a chain has poor learning capability suffering from the gradient vanishing problem, we redesign the network architecture to let reconstruction leverages the captured features from restoration using up-sampling skip connections. Our novel architecture is called restoration-reconstruction u-shaped deep neural network (RR-DnCNN v2.0). As a result, our RR-DnCNN v2.0 outperforms the previous works and can attain 17.02% BD-rate reduction on UHD resolution for all-intra anchored by the standard H.265/HEVC. The source code is available at https://minhmanho.github.io/rrdncnn/.

Transformer-based tracking methods have been widely studied in the field of visual object tracking. The long-range information capturing ability of the transformer improves the performance of the tracking network. However, the self-attention learning procedure in the transformer module neglects the local information, the target and the background around it, which can be beneficial for trackers to handle background clutter and deformation. In this paper, the local-global self-attention (LGSA) learning is proposed for the object tracking task, which obtains the local and global information simultaneously in one attention learning block. Based on the LGSA, the encoder and the decoder are designed to fuse the features corresponding to the template and search images. Additionally, two tracking networks, LGSAT-T and LGSAT-B instantiated with the proposed encoder and decoder are introduced. Exclusive experiments on the commonly used datasets, including OTB100, GOT-10K, LaSOT, and TrackingNet, demonstrate the effectiveness of LGSA, and indicate the state-of-the-art performance of the proposed tracking network. The code will be released at https://github.com/lgao001/LGSAT.

Multiple object tracking (MOT) plays an important role in intelligent video-processing tasks, which aims to detect and track all moving objects in a scene. Joint-detection-and-tracking (JDT) methods are thriving in MOT tasks, because they accomplish the detection and data association in a single stage. However, the slow training convergence and insufficient data association limit the performance of JDT methods. In this paper, the anchor-based query (ABQ) is proposed to improve the design of the JDT methods for faster training convergence. By augmenting the coordinates of the anchor boxes into the learnable queries of the decoder, the ABQ introduces explicit prior spatial knowledge into the queries to focus the query-to-feature learning of the JDT methods on the local region, which leads to faster training speed and better performance. Moreover, a new template matching (TM) module is designed for the JDT methods, which enables the JDT methods to associate the detection results and trajectories with historical features. Finally, a new transformer-based MOT method, ABQ-Track, is proposed. Extensive experiments verify the effectiveness of the two modules, and the ABQ-Track surpasses the performance of the baseline JDT methods, TransTrack. Specifically, the ABQ-Track only needs to train for 50 epochs to achieve convergence, while that for TransTrack is 150 epochs.

Hyperspectral (HS) imaging is conducive to better describing and understanding the subtle differences in spectral characteristics of different materials due to sufficient spectral information compared with traditional imaging systems. However, it is still challenging to obtain high resolution (HR) HS images in both the spectral and spatial domains. Different from previous methods, we first propose spectral constrained adversarial autoencoder (SCAAE) to extract deep features of HS images and combine with the panchromatic (PAN) image to competently represent the spatial information of HR HS images, which is more comprehensive and representative. In particular, based on the adversarial autoencoder (AAE) network, the SCAAE network is built with the added spectral constraint in the loss function so that spectral consistency and a higher quality of spatial information enhancement can be ensured. Then, an adaptive fusion approach with a simple feature selection rule is induced to make full use of the spatial information contained in both the HS image and PAN image. Specifically, the spatial information from two different sensors is introduced into a convex optimization equation to obtain the fusion proportion of the two parts and estimate the generated HR HS image. By analyzing the results from the experiments executed on the tested data sets through different methods, it can be found that, in CC, SAM, and RMSE, the performance of the proposed algorithm is improved by about 1.42%, 13.12%, and 29.26% respectively on average which is preferable to the well-performed method HySure. Compared to the MRA-based method, the improvement of the proposed method in in the above three indexes is 17.63%, 0.83%, and 11.02%, respectively. Moreover, the results are 0.87%, 22.11%, and 20.66%, respectively, better than the PCA-based method, which fully illustrated the superiority of the proposed method in spatial information preservation. All the experimental results demonstrate that the proposed method is superior to the state-of-the-art fusion methods in terms of subjective and objective evaluations.