The goal of multi-modality image fusion is to integrate complementary information from different modal images to create high-quality, informative fused images. In recent years, significant advances have been made in deep learning for image fusion tasks. Nevertheless, current fusion techniques are still unable to capture more intricate details from the source images. For instance, many existing methods used for tasks such as infrared and visible image fusion are susceptible to adverse lighting conditions. To enhance the ability of fusion networks to preserve detailed information in complex scenes, we propose RefineFuse, a multi-scale interaction network for multi-modal image fusion tasks. To balance and exploit local detailed features and global semantic information during the fusion process, we utilize specific modules to model cross-modal feature coupling in both the pixel and semantic domains. Specifically, a dual attention-based feature interaction module is introduced to integrate detailed information from both modalities for extracting shallow features. To obtain deep semantic information, we adopt a global attention mechanism for cross-modal feature interaction. Additionally, to bridge the gap between deep semantic information and shallow detailed information, we gradually incorporate deep semantic information to shallow detailed information via specific feature interaction modules. Extensive comparative and generalization experiments demonstrate that RefineFuse achieves high-quality fusions of infrared, visible, and medical images, while also facilitating advanced visual tasks, such as object detection.

Discriminative correlation filters (DCF) with powerful feature descriptors have proven to be very effective for advanced visual object tracking approaches. However, due to the fixed capacity in achieving discriminative learning, existing DCF trackers perform the filter training on a single template extracted by convolutional neural networks (CNN) or hand-crafted descriptors. Such single template learning cannot provide powerful discriminative filters with guaranteed validity under appearance variation. To pinpoint the structural relevance of spatio-temporal appearance to the filtering system, we propose a new tracking algorithm that incorporates the construction of the Grassmannian manifold learning in the DCF formulation. Our method constructs the model appearance within an online updated affine subspace. It enables joint discriminative learning in the origin and basis of the subspace, achieving enhanced discrimination and interpretability of the learned filters. In addition, to improve tracking efficiency, we adaptively integrate online incremental learning to update the obtained manifold. To this end, specific spatio-temporal appearance patterns are dynamically learned during tracking, highlighting relevant variations and alleviating the performance degrading impact of less discriminative representations from a single template. The experimental results obtained on several well-known datasets, i.e., OTB2013, OTB2015, UAV123, and VOT2018, demonstrate the merits of the proposed method and its superiority over the state-of-the-art trackers.

This paper investigated the problem of multiview subspace clustering, focusing on feature learning with submanifold structure and exploring the invariant representations of multiple views. A novel approach was proposed in this study, termed deep Grassmannian multiview subspace clustering with contrastive learning (DGMVCL). The proposed algorithm initially utilized a feature extraction module (FEM) to map the original input samples into a feature subspace. Subsequently, the manifold modeling module (MMM) was employed to map the aforementioned subspace features onto a Grassmannian manifold. Afterward, the designed Grassmannian manifold network was utilized for deep subspace learning. Finally, discriminative cluster assignments were achieved utilizing a contrastive learning mechanism. Extensive experiments conducted on five benchmarking datasets demonstrate the effectiveness of the proposed method. The source code is available at https://github.com/Zoo-LLi/DGMVCL.

This paper proposes a comprehensive experiment scheme that uses PredRNN technology to design a cyanobacterial spatio-temporal sequence prediction system. This experiment can provide effective reference for the treatment of cyanobacteria in lakes. The experiment uses Python language to build a cyanobacterial spatiotemporal sequence prediction system based on the PredRNN algorithm. The whole experimental program includes five modules: Pre-processing of cyanobacterial NDVI (normalized difference vegetation index) image data, segmentation of cyanobacterial dataset, training of spatial-temporal prediction model, testing of prediction model and colorized display. Through comparative experiments, the feasibility and practicality of using the PredRNN algorithm for cyanobacterial spatio-temporal sequence prediction are demonstrated. The experimental scheme is designed to help students master Python programming skills, help improve students’ comprehensive application of image processing and computer vision knowledge, realize the extension of teaching theory to practice in computer vision courses, strengthen the organic combination of teaching and research, enhance students’ research literacy, and promote the development of computer vision courses.