In the past decade, deep neural networks, particularly convolutional neural networks, have revolutionised computer vision. However, all deep learning models may require a large amount of data so as to achieve satisfying results. Unfortunately, the availability of sufficient amounts of data for real-world problems is not always possible, and it is well recognised that a paucity of data easily results in overfitting. This issue may be addressed through several approaches, one of which is data augmentation. In this paper, we survey the existing data augmentation techniques in computer vision tasks, including segmentation and classification, and suggest new strategies. In particular, we introduce a way of implementing data augmentation by using local information in images. We propose a parameter-free and easy to implement strategy, the random local rotation strategy, which involves randomly selecting the location and size of circular regions in the image and rotating them with random angles. It can be used as an alternative to the traditional rotation strategy, which generally suffers from irregular image boundaries. It can also complement other techniques in data augmentation. Extensive experimental results and comparisons demonstrated that the new strategy consistently outperformed its traditional counterparts in, for example, image classification.

Human action recognition (HAR) encompasses the task of monitoring human activities across various domains, including but not limited to medical, educational, entertainment, visual surveillance, video retrieval, and the identification of anomalous activities. Over the past decade, the field of HAR has witnessed substantial progress by leveraging convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to effectively extract and comprehend intricate information, thereby enhancing the overall performance of HAR systems. Recently, the domain of computer vision has witnessed the emergence of Vision Transformers (ViTs) as a potent solution. The efficacy of Transformer architecture has been validated beyond the confines of image analysis, extending their applicability to diverse video-related tasks. Notably, within this landscape, the research community has shown keen interest in HAR, acknowledging its manifold utility and widespread adoption across various domains. However, HAR remains a challenging task due to variations in human motion, occlusions, viewpoint differences, background clutter, and the need for efficient spatio-temporal feature extraction. Additionally, the trade-off between computational efficiency and recognition accuracy remains a significant obstacle, particularly with the adoption of deep learning models requiring extensive training data and resources. This article aims to present an encompassing survey that focuses on CNNs and the evolution of RNNs to ViTs given their importance in the domain of HAR. By conducting a thorough examination of existing literature and exploring emerging trends, this study undertakes a critical analysis and synthesis of the accumulated knowledge in this field. Additionally, it investigates the ongoing efforts to develop hybrid approaches. Following this direction, this article presents a novel hybrid model that seeks to integrate the inherent strengths of CNNs and ViTs.

Deep learning with its rapid development and advancement has achieved unparalleled performance in many areas like computer vision as well as cognitive radio and signal recognition. However, the performance of most deep neural networks would suffer from degradation in the data mismatch scenario, e.g., the test dataset has a related but nonidentical distribution with the training dataset. Considering the noise corruption, a classifier’s accuracy might drop sharply when it is tested on a dataset with much lower signal-to-noise ratio compared to its training dataset. To address this dilemma, in this work, we propose an efficient denoising and classification network (DNCNet) for radar signals. The DNCNet consists of denoising and classification subnetworks. First, a radar signal detection and synthetic mechanism is designed to generate pairwise clean data and noisy data for the DNCNet to train its denoising subnetwork. Then, a two-phase training procedure is proposed to train the denoising subnetwork in the first phase and strengthen the mapping between the denoising results and perceptual representation in the second. Experiments on synthetic and benchmark datasets validate the excellent performance of the proposed DNCNet against state-of-the-art methods in terms of both signal restoration quality and classification accuracy.

Bayesian model selection provides a powerful framework for objectively comparing models directly from observed data, without reference to ground truth data. However, Bayesian model selection requires the computation of the marginal likelihood (model evidence), which is computationally challenging, prohibiting its use in many high-dimensional Bayesian inverse problems. With Bayesian imaging applications in mind, in this work we present theproximal nested samplingmethodology to objectively compare alternative Bayesian imaging models for applications that use images to inform decisions under uncertainty. The methodology is based on nested sampling, a Monte Carlo approach specialised for model comparison, and exploits proximal Markov chain Monte Carlo techniques to scale efficiently to large problems and to tackle models that are log-concave and not necessarily smooth (e.g., involving $$\ell _1$$ℓ1 or total-variation priors). The proposed approach can be applied computationally to problems of dimension $${\mathcal {O}}(10^6)$$O(106) and beyond, making it suitable for high-dimensional inverse imaging problems. It is validated on large Gaussian models, for which the likelihood is available analytically, and subsequently illustrated on a range of imaging problems where it is used to analyse different choices of dictionary and measurement model.

Multimodal fake news detection often involves modelling heterogeneous data sources, such as vision and language. Existing detection methods typically rely on fusion effectiveness and cross-modal consistency to model the content, complicating understanding how each modality affects prediction accuracy. Additionally, these methods are primarily based on static feature modelling, making it difficult to adapt to the dynamic changes and relationships between different data modalities. This paper develops a significantly novel approach, GAMED, for multimodal modelling, which focuses on generating distinctive and discriminative features through modal decoupling to enhance cross-modal synergies, thereby optimizing overall performance in the detection process. GAMED leverages multiple parallel expert networks to refine features and pre-embed semantic knowledge to improve the experts' ability in information selection and viewpoint sharing. Subsequently, the feature distribution of each modality is adaptively adjusted based on the respective experts' opinions. GAMED also introduces a novel classification technique to dynamically manage contributions from different modalities, while improving the explainability of decisions. Experimental results on the Fakeddit and Yang datasets demonstrate that GAMED performs better than recently developed state-of-the-art models. The source code can be accessed at https://github.com/slz0925/GAMED.

The para-crystalline structures of prolamellar bodies (PLBs) and light-induced etioplast-to-chloroplast transformation have been investigated via electron microscopy. However, such studies suffer from chemical fixation artifacts and limited volumes of 3D reconstruction. Here, we examined Arabidopsis thaliana cotyledon cells by electron tomography (ET) to visualize etioplasts and their conversion into chloroplasts. We employed scanning transmission ET to image large volumes and high-pressure freezing to improve sample preservation. PLB tubules were arranged in a zinc blende-type lattice-like carbon atoms in diamonds. Within 2 h after illumination, the lattice collapsed from the PLB exterior and the disorganized tubules merged to form thylakoid sheets (pre-granal thylakoids), which folded and overlapped with each other to create grana stacks. Since the nascent pre-granal thylakoids contained curved membranes in their tips, we examined the expression and localization of CURT1 (CURVATURE THYLAKOID1) proteins. CURT1A transcripts were most abundant in de-etiolating cotyledon samples, and CURT1A was concentrated at the PLB periphery. In curt1a etioplasts, PLB-associated thylakoids were swollen and failed to form grana stacks. In contrast, PLBs had cracks in their lattices in curt1c etioplasts. Our data provide evidence that CURT1A is required for pre-granal thylakoid assembly from PLB tubules during de-etiolation, while CURT1C contributes to cubic crystal growth in the dark.