A large receptive field is crucial for the video frame interpolation (VFI) task. Existing video frame interpolation methods struggle with large motions due to their limited receptive fields. However, simply expanding the receptive field brings two challenges: a substantial computational burden and potential loss of texture details. In this paper, we first propose a novel spatial-temporal global window self-attention mechanism with an enlarged receptive field to enhance motion capture. Furthermore, to reduce the computational complexity introduced by the global window, we design a simple and effective separable fence window decomposition. Meanwhile, to better synthesize high-quality intermediate frames, we propose two complementary frame synthesis strategies. First, from the perspective of receptive field design, we introduce a progressive receptive field focusing module, enabling a smooth transition from global motion modeling to local detail preservation. Second, based on the VFI-specific property and the high structural similarity shared by the adjacent frames, we propose a structure-aware synthesis strategy, which incorporates structural priors to guide the generation of fine details. Subjective and objective experimental results demonstrate that our method effectively captures large motions while synthesizing texture details, outperforming state-of-the-art techniques on various datasets.

MOTIVATION: Crohn's disease (CD) exhibits substantial variability in response to biological therapies such as ustekinumab (UST), a monoclonal antibody targeting interleukin-12/23. However, predicting individual treatment responses remains difficult due to the lack of reliable histopathological biomarkers and the morphological complexity of tissue. While recent deep learning methods have leveraged whole-slide images (WSIs), most lack effective mechanisms for selecting relevant regions and integrating patch-level evidence into robust patient-level predictions. Therefore, a framework that captures local histological cues and global tissue context is needed to improve prediction performance. RESULTS: We propose a novel clustering-enhanced weakly supervised learning framework to predict UST treatment response from pre-treatment WSIs of CD patients. First, patches from WSIs were encoded using a pre-trained vision foundation model, and k-means clustering was applied to identify representative morphological patterns. Discriminative patches associated with treatment outcomes were selected via a DenseNet-based classifier, with Grad-CAM used to enhance interpretability. To aggregate patch-level predictions, we adopted a multi-instance learning approach, from which whole-slide features were extracted using both patch likelihood histograms and bag-of-words representations. These features were subsequently used to train a classifier for final response prediction. Experimental results on an independent test set demonstrated that our WSI-level model achieved superior predictive performance with an AUC of 0.938 (95% CI: 0.879-0.996), sensitivity of 0.951, and specificity of 0.825, outperforming baseline patch-level models. These findings suggest that our method enables accurate, interpretable, and scalable prediction of biological therapy response in CD, potentially supporting personalized treatment strategies in clinical settings. AVAILABILITY AND IMPLEMENTATION: https://github.com/caicai2526/USTAIM.

A light field image records rich information of a scene from multiple views, thereby providing complementary information for occlusion removal. However, current occlusion removal methods have several issues: 1) inefficient exploitation of spatial and angular complementary information among views; 2) indistinguishable treatment of pixels from foreground occlusion and background; and 3) insufficient exploration of spatial detail supplementation. Therefore, in this article, we propose a mask-aware de-occlusion network (MANet). Specifically, MANet is a joint training network that integrates the occlusion mask predictor (OMP) and the occlusion remover (OR). First, OMP is proposed to provide the location of occluded regions for OR, as the occlusion removal task is ill-posed without occluded region localization. In OR, we introduce gated spatial-angular feature aggregation, which uses a soft gating mechanism to focus on spatial-angular interaction features in non-occluded regions, extracting effective aggregated features specific to the de-occlusion. Then, we design a complementary strategy to fully utilize spatial-angular information among views. Finally, we propose texture-semantic attention to improve the performance of detail generation. Experimental results demonstrate the superiority of MANet, with substantial improvements in both PSNR and SSIM metrics. Moreover, MANet stands out with an efficient parameter count of 2.4 M, making it a promising solution for real-world applications in public safety and security surveillance.

The performance of existing de-occlusion methods is limited mainly due to inaccurate foreground mask prediction, interference from occlusion information in feature extractors, and insufficient utilization of sub-pixel information between views. Therefore, in this paper, we propose an efficient light field image de-occlusion method to improve the performance of occlusion localization and occlusion removal. First, we design an adaptive threshold mask prediction branch, which fully utilizes the spatial and angular information of light field images and incorporates mask binarization into the network for joint optimization. Then, we propose Occlusion-aware Convolution, which can more efficiently extract the joint spatial-angular features of the occluded light field image. Additionally, we design a sub-pixel complement strategy. This strategy fully utilizes the sub-pixel information between the views and supplements it into the view to be deoccluded. Experimental results demonstrate that our method achieves superior performance on both real-world and synthetic light field datasets.

Three-dimensional perception in intelligent virtual and augmented reality (VR/AR) and autonomous vehicles (AV) applications is critical and attracting significant attention. The self-supervised monocular depth and ego-motion estimation serves as a more intelligent learning approach that provides the required scene depth and location for 3D perception. However, the existing self-supervised learning methods suffer from scale ambiguity, boundary blur, and imbalanced depth distribution, limiting the practical applications of VR/AR and AV. In this article, we propose a new self-supervised learning framework based on superpixel and normal constraints to address these problems. Specifically, we formulate a novel 3D edge structure consistency loss to alleviate the boundary blur of depth estimation. To address the scale ambiguity of estimated depth and ego-motion, we propose a novel surface normal network for efficient camera height estimation. The surface normal network is composed of a deep fusion module and a full-scale hierarchical feature aggregation module. Meanwhile, to realize the global smoothing and boundary discriminability of the predicted normal map, we introduce a novel fusion loss which is based on the consistency constraints of the normal in edge domains and superpixel regions. Experiments are conducted on several benchmarks, and the results illustrate that the proposed approach outperforms the state-of-the-art methods in depth, ego-motion, and surface normal estimation.

Metaphors are ubiquitous in natural language, and detecting them requires contextual reasoning about whether a semantic incongruence actually exists.Most existing work addresses this problem using pre-trained contextualized models.Despite their success, these models require a large amount of labeled data and are not linguistically-based.In this paper, we proposed a ContrAstive pre-Trained modEl (CATE) for metaphor detection with semi-supervised learning.Our model first uses a pre-trained model to obtain a contextual representation of target words and employs a contrastive objective to promote an increased distance between target words' literal and metaphorical senses based on linguistic theories.Furthermore, we propose a simple strategy to collect large-scale candidate instances from the general corpus and generalize the model via self-training.Extensive experiments show that CATE achieves better performance against state-of-the-art baselines on several benchmark datasets.

Industrial Internet of Things (IIoT) has been widely applied in smart home, smart city, smart traffic, etc. It is a big challenge to recognize facial expression of IIoT systems more effectively. Current facial recognition methods only utilize singular facial images, so accurate features that are highly correlated with facial changes can hardly be extracted. In order to overcome this difficulty and improve facial expression recognition, in this article, we propose a parallel neural network combining texture features, which can be applied in facial expression recognition. This parallel neural network is constructed by convolution neural network, residual network, and capsule network. Additionally, texture analysis is conducted on facial expression images to extract abundant features. Eight texture features are extracted by gray-level co-occurrence matrix and integrated with features of original images. Finally, these integrated features extracted by three kinds of networks are used to classify facial images. Experimental results prove that the proposed approach has a high recognition rate and strong robustness compared to competitive algorithms. Remarkably, our accuracy reaches 98.14%, with an increase of 3.71% in comparison with ResNet, and the F1-score of 0.9801. It is thus verified from this result that the proposed algorithm has many outstanding advantages. The idea in combination with texture features also provides a new solution for image classification.

With the proliferation of embedded ubiquitous systems in all aspects of human life, the development of embedded systems has been facing more and more challenges (e.g., quality, time to market, etc.). Meanwhile, lots of software processes have been reported to be applied in Embedded Systems Development (ESD) with various advantages and disadvantages. Therefore, it’s important to portrait a big picture of the state-of-the-practice of the adoption of the software processes in ESD, which may benefit both practitioners and researchers in this area. This paper presents our investigation on this topic using systematic review that is intended to: 1) identify typical challenging factors and how software processes and practices address them; and 2) discover improvement opportunities from both academic and industrial perspectives.