Perceptual Field Research Articles

A dynamic adaptive multi-view fusion graph convolutional network recommendation model with dilated mask convolution mechanism

Graph Convolutional Networks (GCNs) has shown promise in recommendation systems. However, a critical issue known as the over-smoothing problem has been identified in GCN models. This problem arises as the number of layers in the model increases, leading to a decrease in model performance due to node representations becoming excessively similar. Various strategies have been proposed to combat this issue, like preserving node-specific information or introducing high-order neighbors. Unfortunately, these approaches overlook a crucial factor known as Visual Overlap Strength (VOS), which plays a significant role in the over-smoothing problem. VOS measures the extent of neighborhood overlap between nodes in the graph. To address the over-smoothing problem, this paper offers a comprehensive analysis of the issue and introduces the concept of VOS between nodes. We present a novel solution in the form of the Dynamic Adaptive Multi-view fusion GCN model with dilAted maSK convolution mechanism (DAMASK-GCN). This model dynamically adjusts the perceptual field of nodes, captures high-order information, and alleviates the impact of VOS through the utilization of dilated mask convolution and an adaptive attention fusion mechanism. Extensive experiments on six popular recommendation system datasets demonstrate DAMASK-GCN's effectiveness in reducing over-smoothing and outperforming existing GCN-based recommendation models.

« Choses, assemblages, mondes : le vitalité situer au-delà d'une relation sujet-objet (Un conte de Disposition) »

"Things, Assemblages, Worlds" argues that the vibrancy of things is attributable not to an inherent quality within matter, but to the relationality of the perceptual field or world that things and bodies share. Reading Martin Heidegger's analytic of Dasein against Brian Massumi's description of things in their connectability allows for a revised description of how art sensitizes us to things through defamiliarization. Adina Bar-On's performance Disposition provides a useful example for uncovering art's ability to reveal things' character, their who-ness.

A lightweight network for improving wheat ears detection and counting based on YOLOv5s.

Recognizing wheat ears plays a crucial role in predicting wheat yield. Employing deep learning methods for wheat ears identification is the mainstream method in current research and applications. However, such methods still face challenges, such as high computational parameter volume, large model weights, and slow processing speeds, making it difficult to apply them for real-time identification tasks on limited hardware resources in the wheat field. Therefore, exploring lightweight wheat ears detection methods for real-time recognition holds significant importance. This study proposes a lightweight method for detecting and counting wheat ears based on YOLOv5s. It utilizes the ShuffleNetV2 lightweight convolutional neural network to optimize the YOLOv5s model by reducing the number of parameters and simplifying the complexity of the calculation processes. In addition, a lightweight upsampling operator content-aware reassembly of features is introduced in the feature pyramid structure to eliminate the impact of the lightweight process on the model detection performance. This approach aims to improve the spatial resolution of the feature images, enhance the effectiveness of the perceptual field, and reduce information loss. Finally, by introducing the dynamic target detection head, the shape of the detection head and the feature extraction strategy can be dynamically adjusted, and the detection accuracy can be improved when encountering wheat ears with large-scale changes, diverse shapes, or significant orientation variations. This study uses the global wheat head detection dataset and incorporates the local experimental dataset to improve the robustness and generalization of the proposed model. The weight, FLOPs and mAP of this model are 2.9 MB, 2.5 * 109 and 94.8%, respectively. The linear fitting determination coefficients R2 for the model test result and actual value of global wheat head detection dataset and local experimental Site are 0.94 and 0.97, respectively. The improved lightweight model can better meet the requirements of precision wheat ears counting and play an important role in embedded systems, mobile devices, or other hardware systems with limited computing resources.

SSIR: Spatial shuffle multi-head self-attention for Single Image Super-Resolution

Benefiting from the development of deep convolutional neural networks, CNN-based single-image super-resolution methods have achieved remarkable reconstruction results. However, the limited perceptual field of the convolutional kernel and the use of static weights in the inference process limit the performance of CNN-based methods. Recently, a few vision transformer-based image super-resolution methods have achieved excellent performance compared to CNN-based methods. These methods contain many parameters and require vast amounts of GPU memory for training. In this paper, we propose a spatial shuffle multi-head self-attention for single-image super-resolution that can significantly model long-range pixel dependencies without additional computational consumption. A local perception module is also proposed to combine convolutional neural networks’ local connectivity and translational invariance. Reconstruction results on five popular benchmarks show that the proposed method outperforms existing methods in both reconstruction accuracy and visual performance. The proposed method matches the performance of transformed-based methods but requires an inferior number of transformer blocks, which reduces the number of parameters by 40%, GPU memory by 30%, and inference time by 30% compared to transformer-based methods.

Reading recognition of pointer meters based on an improved UNet++ network

Pointer meters are widely used in modern industries, such as petrochemical applications, substations, and nuclear power plants. To overcome the reading errors and inaccurate measurements due to uneven or fluctuating illumination in practical applications, this paper proposes an improved UNet++ network for recognizing pointer meter readings. First, the scale invariant feature transform feature-matching algorithm is used to adjust the captured tilted meter images to a symmetrical and upright shape. Then, the UNet++ network is used to segment the scale and pointer regions in the dashboard to eliminate background interference. Furthermore, part of the convolution in the UNet++ network is replaced with dilated convolution with different expansion rates to expand the perceptual field during network training. In the UNet++ network jump connection, the attention mechanism module is also introduced in the path to enhance the region’s features to be segmented and suppress the parts of the non-segmented area. A hybrid loss function is used for the network model training to prevent the imbalance of the segmented region share. Finally, the distance method is used to read the gauge representation. Experiments were conducted to compare the performance of the proposed method with that of the original UNet++ network in terms of feasibility and precision. The experimental results showed that the recognition reading accuracy was significantly improved by the enhanced network, with the accuracy, sensitivity, and specificity reaching 98.65%, 84.33%, and 99.38%, respectively. Furthermore, when using the improved UNet++ network for numerical reading, the average relative error was only 0.122%, indicating its robustness in a natural environment.

Patients' experiences with early rehabilitation in intensive care units: A qualitative study about aspects that influence their participation.

To explore patients' experiences with early rehabilitation in the intensive care unit and what they perceive to influence their participation. A qualitative design anchored in phenomenological and hermeneutical traditions utilizing in-depth interviews. Thirteen patients were interviewed from 5 to 29 weeks following discharge from three units, in January-December 2022. Analysed using systematic text condensation and the pattern theory of self. Reporting adhered to consolidated criteria for reporting qualitative research. Interviews described four main categories: (1) A foreign body, how the participants experienced their dysfunctional and different looking bodies. (2) From crisis to reorientation, the transformation the participants experienced from a state of crisis to acceptance and the ability to look forwards, indicating how bodily dysfunctions are interlinked to breakdowns of the patients' selves and the reorganization process. (3) Diverse expectations regarding activity: ambiguous expectations communicated by the nurses. (4) Nurse-patient: a powerful interaction, highlighting the essential significance of positive expectations and tailored bodily and verbal interaction for rebuilding the patient's outwards orientation. Outwards orientation and reorganization of the self through a reduction in bodily dysfunctions, strengthening the patients' acceptance of the situation, providing tailored expectations and hands-on and verbal interaction appear to be fundamental aspects of patient participation in early rehabilitation. Insights into patients' perceptions show how dysfunctional bodies cloud individuals' perceptual fields, causing inwards orientation and negative thoughts concerning themselves, their capabilities, environment and future. This knowledge can improve nurses' ability to tailor care to promote optimal recovery for patients. User representative contributed to the design of the study.

Speaker diarization with variants of self-attention and joint speaker embedding extractor

The speaker diarization task pertains to the automated differentiation of speakers within an audio recording, while lacking any prior information regarding the speakers. The introduction of the self-attention mechanism in End-to-End Neural Speaker Diarization (EEND) has elegantly resolved the issue of overlapping speakers. The Transformer model equipped with self-attention mechanism has shown great potential in collecting global information, yielding remarkable outcomes in various tasks. However, the individual speaker characteristics are predominantly reflected in the contextual information, which conventional self-attention would not adequately address. In this study, we propose a hierarchical encoders model to augment the encoders’ acquisition of speaker information in two distinct ways: (1) Constraining the perceptual field of the self-attentive mechanism with left-right windows or Gaussian weights to highlight contextual information; (2) Utilizing a pre-trained time-delay neural network based speaker embedding extractor to alleviate the shortcomings of speaker feature extraction ability. We evaluate the proposed methods on a simulated dataset of two speakers and a real conversation dataset. The model with the most favorable outcomes among the proposed enhancements achieves a diarization error rate of 7.74% on the simulated dataset and 21.92% on MagicData-RAMC after adaptation. These results compellingly demonstrate the efficacy of the proposed methods.

Psychedelic Aesthetics and the Body without Organs at the Limits of Perception

This article focuses on the aesthetics of the psychedelic experience. Aldous Huxley’s Doors of Perception remains one of the few studies that investigates the aesthetic dimension of the psychedelic experience as profoundly meaningful as such, because it gives direct attention to the nonhuman otherness of the universe that is hard to describe in words, but that can be felt and sensed. Similarly, Deleuze and Guattari have investigated psychedelics as a perceptual, aesthetic, phenomenon. They argue that psychedelic aesthetics offers an experience at the limits of perception to the point of ultimate abstraction of geometric figures and grains. Drawing upon the works of two experimental filmmakers from two different generations and backgrounds, Philippe Garrel’s enigmatic Le Révélateur ( The Revealer, 1968 ) and Morgan Quaintance’s thought-provoking Surviving You, Always (2021), the borders of the perceptual field by cinematographic means will be investigated. These works are exemplary of how the nonhuman perception of the camera, its ‘bodies without organs’, and its affective intensity evoke a psychedelic, mind-revealing, experience and an ethics of – in Deleuze’s words – ‘becoming not unworthy of the event’.

Micro-Expression Spotting Based on VoVNet, Driven by Multi-Scale Features

Micro-expressions are a type of real emotional expression, which are unconscious and difficult to hide. Identifying these expressions has great potential applications in areas such as civil aviation security, criminal interrogation, and clinical medicine. However, because of their characteristics such as short duration, low intensity, and sparse action units, this makes micro-expression spotting difficult. To address this problem and inspired by object detection methods, we propose a VoVNet-based micro-expression spotting model, driven by multi-scale features. Firstly, VoVNet is used to achieve the extraction and reuse of different scale perceptual field features to improve the feature extraction capability. Secondly, multi-scale features are extracted and fused using the Feature Pyramid Network module, incorporating optical flow features, and by realizing the interactive fusion of fine-grained feature information and semantic feature information. Finally, the model is trained and optimized on CAS(ME)2 and SAMM Long Video. The experimental results show that the F1 score of the proposed model is improved by 0.1963 and 0.2441 on the two datasets compared with the baseline method, which outperforms the most popular spotting methods.

Deep Learning-Based Understanding of Defects in Continuous Casting Product

A novel YOLOv5 network is presented in this paper to quantify the degree of defects in continuously cast billets. The proposed network addresses the challenges posed by noise or dirty spots and different defect sizes in the images of these billets. The CBAM-YOLOv5 network integrates the channel and spatial attention of the Convolutional Block Attention Module (CBAM) with the C3 layer of the YOLOv5 network structure to better fuse channel and spatial information, with focus on the defect target, and improve the network’s detection capability, particularly for different levels of segregation. As a result, the feature pyramid is improved. The feature map obtained after the fourth down-sampling of the backbone network is fed into the feature pyramid through CBAM to improve the perceptual field of the target and reduce information loss during the fusion process. Finally, a self-built dataset of continuously cast billets collected from different sources is used, and several experiments are conducted using this database. The experimental results show that the average accuracy (mAP) of the network is 93.7%, which can achieve intelligent rating.

A Forest Wildlife Detection Algorithm Based on Improved YOLOv5s.

A forest wildlife detection algorithm based on an improved YOLOv5s network model is proposed to advance forest wildlife monitoring and improve detection accuracy in complex forest environments. This research utilizes a data set from the Hunan Hupingshan National Nature Reserve in China, to which data augmentation and expansion methods are applied to extensively train the proposed model. To enhance the feature extraction ability of the proposed model, a weighted channel stitching method based on channel attention is introduced. The Swin Transformer module is combined with a CNN network to add a Self-Attention mechanism, thus improving the perceptual field for feature extraction. Furthermore, a new loss function (DIOU_Loss) and an adaptive class suppression loss (L_BCE) are adopted to accelerate the model's convergence speed, reduce false detections in confusing categories, and increase its accuracy. When comparing our improved algorithm with the original YOLOv5s network model under the same experimental conditions and data set, significant improvements are observed, in particular, the mean average precision (mAP) is increased from 72.6% to 89.4%, comprising an accuracy improvement of 16.8%. Our improved algorithm also outperforms popular target detection algorithms, including YOLOv5s, YOLOv3, RetinaNet, and Faster-RCNN. Our proposed improvement measures can well address the challenges posed by the low contrast between background and targets, as well as occlusion and overlap, in forest wildlife images captured by trap cameras. These measures provide practical solutions for enhanced forest wildlife protection and facilitate efficient data acquisition.

Photovoltaic arrays fault diagnosis based on an improved dilated convolutional neural network with feature-enhancement

Photovoltaic (PV) arrays are installed outdoors and prone to abnormalities and various faults under harsh natural conditions, reducing power conversion efficiency and the life of the PV modules, and even causing electric shock and fire. Current fault diagnosis methods are unable to accurately identify and locate faults in PV arrays in PV power systems, leading to increased operation and maintenance costs. Therefore, the feature-enhancement improved dilated convolutional neural network (CNN) is proposed for fault diagnosis of PV arrays in this paper. Firstly, aim at the problem of information loss due to data structure and spatial hierarchy within the traditional CNN, and the loss of data after down-sampling, which leads to the inability to reconstruct information, a dilated convolution is introduced to obtain a larger perceptual field while reducing the computational effort. Meanwhile, the adaptive dual domain soft threshold group convolution attention module is proposed to enhance the essential features of faults and reduce the information redundancy given the ambiguity and blindness of the feature data in PV array fault extraction. Finally, the model performance of the proposed model is validated and the operability and effectiveness of the proposed method are verified experimentally. The diagnostic results show that the average diagnostic accuracy of the proposed model is 98.95% compared with other diagnostic models, with better diagnostic accuracy and more stable diagnostic performance.

Multi-level perception fusion dehazing network.

Image dehazing models are critical in improving the recognition and classification capabilities of image-related artificial intelligence systems. However, existing methods often ignore the limitations of receptive field size during feature extraction and the loss of important information during network sampling, resulting in incomplete or structurally flawed dehazing outcomes. To address these challenges, we propose a multi-level perception fusion dehazing network (MPFDN) that effectively integrates feature information across different scales, expands the perceptual field of the network, and fully extracts the spatial background information of the image. Moreover, we employ an error feedback mechanism and a feature compensator to address the loss of features during the image dehazing process. Finally, we subtract the original hazy image from the generated residual image to obtain a high-quality dehazed image. Based on extensive experimentation, our proposed method has demonstrated outstanding performance not only on synthesizing dehazing datasets, but also on non-homogeneous haze datasets.

Autonomous Parking Space Detection for Electric Vehicles Based on Improved YOLOV5-OBB Algorithm

Currently, in the process of autonomous parking, the algorithm detection accuracy and rate of parking spaces are low due to the diversity of parking scenes, changes in lighting conditions, and other unfavorable factors. An improved algorithm based on YOLOv5-OBB is proposed to reduce the computational effort of the model and increase the speed of model detection. Firstly, the backbone module is optimized, the Focus module and SSP (Selective Spatial Perception) module are replaced with the general convolution and SSPF (Selective Search Proposals Fusion) modules, and the GELU activation function is introduced to reduce the number of model parameters and enhance model learning. Secondly, the RFB (Receptive Field Block) module is added to fuse different feature modules and increase the perceptual field to optimize the small target detection. After that, the CA (coordinate attention) mechanism is introduced to enhance the feature representation capability. Finally, the post-processing is optimized using spatial location correlation to improve the accuracy of the vehicle position and bank angle detection. The implementation results show that by using the improved method proposed in this paper, the FPS of the model is improved by 2.87, algorithm size is reduced by 1 M, and the mAP is improved by 8.4% on the homemade dataset compared with the original algorithm. The improved model meets the requirements of perceived accuracy and speed of parking spaces in autonomous parking.

High familiar faces have both eye recognition and holistic processing advantages.

People recognize familiar faces better than unfamiliar faces. However, it remains unknown whether familiarity affects part-based and/or holistic processing. Wang et al., Frontiers in Psychology, 6, 559 (2015), Vision Research, 157, 89-96 (2019) found both enhanced part-based and holistic processing in eye relative to mouth regions (i.e., in a region-selective manner) for own-race and own-species faces, i.e., faces with more experience. Here, we examined the role of face familiarity in eyes (part-based, region-selective) and holistic processing. Face familiarity was tested at three levels: high-familiar (faces of students from the same department and the same class who attended almost all courses together), low-familiar (faces of students from the same department but different classes who attended some courses together), and unfamiliar (faces of schoolmates from different departments who seldom attended the same courses). Using the old/new task in Experiment 1, we found that participants recognized eyes of high-familiar faces better than low-familiar and unfamiliar ones, while similar performance was observed for mouths, indicating a region-selective, eyes familiarity effect. Using the "Perceptual field" paradigm in Experiment 2, we observed a stronger inversion effect for high-familiar faces, a weaker inversion effect for low-familiar faces, but a non-significant inversion effect for unfamiliar faces, indicating that face familiarity plays a role in holistic processing. Taken together, our results suggest that familiarity, like other experience-based variables (e.g., race and species), can improve both eye processing and holistic processing.

SW-UNet: a U-Net fusing sliding window transformer block with CNN for segmentation of lung nodules.

Medical images are information carriers that visually reflect and record the anatomical structure of the human body, and play an important role in clinical diagnosis, teaching and research, etc. Modern medicine has become increasingly inseparable from the intelligent processing of medical images. In recent years, there have been more and more attempts to apply deep learning theory to medical image segmentation tasks, and it is imperative to explore a simple and efficient deep learning algorithm for medical image segmentation. In this paper, we investigate the segmentation of lung nodule images. We address the above-mentioned problems of medical image segmentation algorithms and conduct research on medical image fusion algorithms based on a hybrid channel-space attention mechanism and medical image segmentation algorithms with a hybrid architecture of Convolutional Neural Networks (CNN) and Visual Transformer. To the problem that medical image segmentation algorithms are difficult to capture long-range feature dependencies, this paper proposes a medical image segmentation model SW-UNet based on a hybrid CNN and Vision Transformer (ViT) framework. Self-attention mechanism and sliding window design of Visual Transformer are used to capture global feature associations and break the perceptual field limitation of convolutional operations due to inductive bias. At the same time, a widened self-attentive vector is used to streamline the number of modules and compress the model size so as to fit the characteristics of a small amount of medical data, which makes the model easy to be overfitted. Experiments on the LUNA16 lung nodule image dataset validate the algorithm and show that the proposed network can achieve efficient medical image segmentation on a lightweight scale. In addition, to validate the migratability of the model, we performed additional validation on other tumor datasets with desirable results. Our research addresses the crucial need for improved medical image segmentation algorithms. By introducing the SW-UNet model, which combines CNN and ViT, we successfully capture long-range feature dependencies and break the perceptual field limitations of traditional convolutional operations. This approach not only enhances the efficiency of medical image segmentation but also maintains model scalability and adaptability to small medical datasets. The positive outcomes on various tumor datasets emphasize the potential migratability and broad applicability of our proposed model in the field of medical image analysis.

The use of graphic design elements in commercial architectural design in the context of intelligence

Abstract In this paper, firstly, in the context of intelligence, using techniques such as hierarchical features, local perceptual field, weight sharing, and spatial subsampling make the convolutional neural network with representational learning ability, certain translation, scaling, and deformation invariance, which can accurately extract the features of target objects in graphic design elements. Next, the network structure, loss function, and optimization methods of MaskR-CNN are analyzed, and the MaskR-CNN convolutional neural network is implemented based on the TensorFlow framework, and the network is applied to the extraction of buildings from graphic design elements. Then the borrowed landscape technique in graphic design is used to enrich the combination form of elements of architectural design through the mirror effect of water landscape. The selected IALD dataset is composed of 180 data images and 180 corresponding labeled images, and the effect of high-resolution building extraction of graphic design elements based on the MaskR-CNN model is verified by simulation experiments. The simulation results show that Mask R-CNN improves the accuracy of building extraction from graphic design elements by 5.11%, mAP also improves by about 10.09%, and the inference time is less than 1 second; Mask R-CNN has good robustness and accuracy for building extraction from graphic design elements. This study has important research significance for the depth and development of the commercial architectural design.

Basic behavior recognition of yaks based on improved SlowFast network

The yak is a symbol of the Tibetan Plateau and an indispensable livestock resource at high altitudes, with important ecological, economic, and cultural values. When yaks are sick, their excrement can cause serious damage to the highland ecosystem, so real-time monitoring of their health status is essential for ecological conservation. The daily behaviors of yaks, such as eating, lying, standing, and walking, contains a wealth of health information. By recognizing the behavior of yaks using computer vision technology, real-time monitoring of yak health status can be achieved, thus, effectively protecting the ecological environment while maintaining the economic benefits of yak breeding. This study proposes a non-contact yak behavior recognition method based on the SlowFast model. The method uses two paths with different sampling rates (i.e., Slow and Fast) to extract spatial and action features from the input video. The 3D Resnet50 network is selected as the backbone network of the SlowFast dual path after comparative analysis. The size of the 3D convolutional kernel is increased to improve the perceptual field of feature extraction, which in turn effectively improves the recognition accuracy of the algorithm. A total of 318 videos of yaks in different scenes and poses were captured for testing. Six different networks were selected to verify the performance of the proposed method: SlowFast-3DResnet50, SlowFast-3DResnet101, SlowFast-3DResnet152, 3DResnet50, C3D, and I3D. The experimental results show that the method achieves 96.6% recognition accuracy, 91.3% recall, and 90.5% precision in classifying the basic behaviors of yaks in natural scenes, and 97.3%, 99.1%, 95.9% and 94.1% for the four basic behaviors, respectively. These results are comprehensively better than the other six methods. In addition, compared with other 3D convolutional neural networks used for video classification, the method proposed in this paper can classify the target behavior from each video frame, which has a broader implications and application. The algorithm meets the needs for basic behavior recognition of yaks and lays the foundation for real-time monitoring of yak health status.

Full-Reference Image Quality Assessment via Low-Level and High-Level Feature Fusion

We propose a full-reference image quality assessment (FR-IQA) method by incorporating low-level and high-level image features. First, in contrast to the preexisting deep IQA methods, which only use the features extracted by the deep network, we not only use the image gradient to replace the low-level features in the first two stages of the deep network, but also combine them with the middle-stage features of the deep network to construct the new low-level features. The deep features of shallow layers contain some unwanted noise and further result in a decline in IQA performance. Second, we combine the global features extracted by the self-attention-based model with the semantic features extracted by the convolutional neural network to form the high-level features. Instead of directly using the self-attention-based model trained on the classification task, we first train a no-reference (NR) IQA regression model on a larger dataset and then use the global features of this NR-IQA model. The self-attention-based model can capture the internal connections of the image and is more effective in extracting global information due to its larger perceptual field. In the final pooling stage, we combine the average pooling and the standard deviation pooling to obtain the dispersion and concentration of the similarity maps for a more comprehensive description of quality. Experiments show that our FR-IQA method is able to obtain competitive results on three standard IQA datasets.

Into the glidescape: an outline of gliding sports from the perspective of applied phenomenology

ABSTRACT There is an absence in the literature on sports of a conceptualization of what in French are labeled sports de glisse: sports that imply gliding on water, through air, and on snow and ice, such as surfing, paragliding, skiing, and skating. Inspired by Ingold’s (1993) concept of the taskscape, we introduce the idea of the glidescape: a perceptual field in which gliding sports practitioners inhabit, create, and transform their environment while at the same time being recreated and transformed themselves. Using an applied phenomenological approach, we describe the main experiential qualities and structure of the glidescape. In the quest for extended phases of effortless movement, gliders engage in a clearly accentuated rhythm with sharp contrasts between forceful effort and smooth effortlessness based on a fine-tuned proprioceptive sense for material and ecological resonance, which opens fleeting and emplaced moments of freedom and authenticity.