Spatial Inconsistency Research Articles

Experimental and numerical simulation study on the mass transfer characteristics of static flash evaporation

Due to the short duration and intense nature of static flash evaporation, and limited by the measurement methods, there is still limited understanding of the inhomogeneous characteristics of mass transfer within the waterfilm. This paper studies the spatiotemporal variation of mass transfer characteristics during static flash using experimental and numerical simulation methods. The formation and evolution mechanism of the bubble layer is analyzed, and its impact on the spatial distribution of temperature within the waterfilm is explained. Firstly, it was found that during the flash process, the temperature difference at different heights of the waterfilm first increases and then decreases. Secondly, during the flash process, there is a maximum value of the vapor generation rate within the waterfilm along the height direction of the flash chamber, and there is a spatial inconsistency between the vapor generation rate and the superheat distribution. Thirdly, reducing the initial waterfilm height can improve the consistency between the maximum superheat and the maximum volume fraction, resulting in a higher vapor generation rate per unit mass and an earlier peak appearance. This study contributes to a deeper understanding of flash mass transfer and provides ideas for the future enhancement of flash evaporation.

Prototype-wise self-knowledge distillation for few-shot segmentation

Few-shot segmentation was proposed to obtain segmentation results for a image with an unseen class by referring to a few labeled samples. However, due to the limited number of samples, many few-shot segmentation models suffer from poor generalization. Prototypical network-based few-shot segmentation still has issues with spatial inconsistency and prototype bias. Since the target class has different appearance in each image, some specific features in the prototypes generated from the support image and its mask do not accurately reflect the generalized features of the target class. To address the support prototype consistency issue, we put forward two modules: Data Augmentation Self-knowledge Distillation (DASKD) and Prototype-wise Regularization (PWR). The DASKD module focuses on enhancing spatial consistency by using data augmentation and self-knowledge distillation. Self-knowledge distillation helps the model acquire generalized features of the target class and learn hidden knowledge from the support images. The PWR module focuses on obtaining a more representative support prototype by conducting prototype-level loss to obtain support prototypes closer to the category center. Broad evaluation experiments on PASCAL-5i and COCO-20i demonstrate that our model outperforms the prior works on few-shot segmentation. Our approach surpasses the state of the art by 7.5% in PASCAL-5i and 4.2% in COCO-20i.

GazeForensics: DeepFake detection via gaze-guided spatial inconsistency learning

DeepFake detection is pivotal in personal privacy and public safety. With the iterative advancement of DeepFake techniques, high-quality forged videos and images are becoming increasingly deceptive. Prior research has seen numerous attempts by scholars to incorporate biometric features into the field of DeepFake detection. However, traditional biometric-based approaches tend to segregate biometric features from general ones and freeze the biometric feature extractor. These approaches resulted in the exclusion of valuable general features, potentially leading to a performance decline and, consequently, a failure to fully exploit the potential of biometric information in assisting DeepFake detection. Moreover, insufficient attention has been dedicated to scrutinizing gaze authenticity within the realm of DeepFake detection in recent years. In this paper, we introduce GazeForensics, an innovative DeepFake detection method that utilizes gaze representation obtained from a 3D gaze estimation model to regularize the corresponding representation within our DeepFake detection model, while concurrently integrating general features to further enhance the performance of our model. Experimental results demonstrate that our proposed GazeForensics method performs admirably in terms of performance and exhibits excellent interpretability.

Coarse‐to‐fine adjustment for multi‐platform point cloud fusion

AbstractLeveraging multi‐platform laser scanning systems offers a complete solution for 3D modelling of large‐scale urban scenes. However, the spatial inconsistency of point clouds collected by heterogeneous platforms with different viewpoints presents challenges in achieving seamless fusion. To tackle this challenge, this paper proposes a coarse‐to‐fine adjustment for multi‐platform point cloud fusion. First, in the preprocessing stage, the bounding box of each point cloud block is employed to identify potential constraint association. Second, the proposed local optimisation facilitates preliminary pairwise alignment with these potential constraint relationships, and obtaining initial guess for a comprehensive global optimisation. At last, the proposed global optimisation incorporates all the local constraints for tightly coupled optimisation with raw point correspondences. We choose two study areas to conduct experiments. Study area 1 represents a fast road scene with a significant amount of vegetation, while study area 2 represents an urban scene with many buildings. Extensive experimental evaluations indicate the proposed method has increased the accuracy of study area 1 by 50.6% and the accuracy of study area 2 by 44.7%.

Prototype as query for few shot semantic segmentation

Few-shot Semantic Segmentation (FSS) was proposed to segment unseen classes in a query image, referring to only a few annotated examples named support images. One of the characteristics of FSS is spatial inconsistency between query and support targets, e.g., texture or appearance. This greatly challenges the generalization ability of methods for FSS, which requires to effectively exploit the dependency of the query image and the support examples. Most existing methods abstracted support features into prototype vectors and implemented the interaction with query features using cosine similarity or feature concatenation. However, this simple interaction may not capture spatial details in query features. To address this limitation, some methods utilized pixel-level support information by computing pixel-level correlations between paired query and support features implemented with the attention mechanism of Transformer. Nevertheless, these approaches suffer from heavy computation due to dot-product attention between all pixels of support and query features. In this paper, we propose a novel framework, termed ProtoFormer, built upon the Transformer architecture, to fully capture spatial details in query features. ProtoFormer treats the abstracted prototype of the target class in support features as the Query and the query features as Key and Value embeddings, which are input to the Transformer decoder. This approach enables better capture of spatial details and focuses on the semantic features of the target class in the query image. The output of the Transformer-based module can be interpreted as semantic-aware dynamic kernels that filter the segmentation mask from the enriched query features. Extensive experiments conducted on PASCAL-5i\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$5^{i}$$\\end{document} and COCO-20i\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$20^{i}$$\\end{document} datasets demonstrate that ProtoFormer significantly outperforms the state-of-the-art methods in FSS.

Improvement of the YOLOv8 Model in the Optimization of the Weed Recognition Algorithm in Cotton Field.

Due to the existence of cotton weeds in a complex cotton field environment with many different species, dense distribution, partial occlusion, and small target phenomena, the use of the YOLO algorithm is prone to problems such as low detection accuracy, serious misdetection, etc. In this study, we propose a YOLOv8-DMAS model for the detection of cotton weeds in complex environments based on the YOLOv8 detection algorithm. To enhance the ability of the model to capture multi-scale features of different weeds, all the BottleNeck are replaced by the Dilation-wise Residual Module (DWR) in the C2f network, and the Multi-Scale module (MSBlock) is added in the last layer of the backbone. Additionally, a small-target detection layer is added to the head structure to avoid the omission of small-target weed detection, and the Adaptively Spatial Feature Fusion mechanism (ASFF) is used to improve the detection head to solve the spatial inconsistency problem of feature fusion. Finally, the original Non-maximum suppression (NMS) method is replaced with SoftNMS to improve the accuracy under dense weed detection. In comparison to YOLO v8s, the experimental results show that the improved YOLOv8-DMAS improves accuracy, recall, mAP0.5, and mAP0.5:0.95 by 1.7%, 3.8%, 2.1%, and 3.7%, respectively. Furthermore, compared to the mature target detection algorithms YOLOv5s, YOLOv7, and SSD, it improves 4.8%, 4.5%, and 5.9% on mAP0.5:0.95, respectively. The results show that the improved model could accurately detect cotton weeds in complex field environments in real time and provide technical support for intelligent weeding research.

Spatiotemporal Inconsistency Learning and Interactive Fusion for Deepfake Video Detection

With the rise of the metaverse, the rapid advancement of Deepfakes technology has become closely intertwined. Within the metaverse, individuals exist in digital form and engage in interactions, transactions, and communications through virtual avatars. However, the development of Deepfakes technology has led to the proliferation of forged information disseminated under the guise of users’ virtual identities, posing significant security risks to the metaverse. Hence, there is an urgent need to research and develop more robust methods for detecting deep forgeries to address these challenges. This paper explores deepfake video detection by leveraging the spatiotemporal inconsistencies generated by deepfake generation techniques, and thereby proposing the interactive spatioTemporal inconsistency learning and interactive fusion (ST-ILIF) detection method, which consists of phase-aware and sequence streams. The spatial inconsistencies exhibited in frames of deepfake videos are primarily attributed to variations in the structural information contained within the phase component of the Fourier domain. To mitigate the issue of overfitting the content information, a phase-aware stream is introduced to learn the spatial inconsistencies from the phase-based reconstructed frames. Additionally, considering that deepfake videos are generated frame-by-frame and lack temporal consistency between frames, a sequence stream is proposed to extract temporal inconsistency features from the spatiotemporal difference information between consecutive frames. Finally, through feature interaction and fusion of the two streams, the representation ability of intermediate and classification features is further enhanced. The proposed method, which was evaluated on four mainstream datasets, outperformed most existing methods, and extensive experimental results demonstrated its effectiveness in identifying deepfake videos. Our source code is available at https://github.com/qff98/Deepfake-Video-Detection

Emission ensemble approach to improve the development of multi-scale emission inventories

Abstract. Many studies have shown that emission inventories are one of the inputs with the most critical influences on the results of air quality modelling. Comparing emission inventories among themselves is, therefore, essential to build confidence in emission estimates. In this work, we extend the approach of Thunis et al. (2022) to compare emission inventories by building a benchmark that serves as a reference for comparisons. This benchmark is an ensemble that is based on three state-of-the-art EU-wide inventories: CAMS-REG, EMEP and EDGAR. The ensemble-based methodology screens differences between inventories and the ensemble. It excludes differences that are not relevant and identifies among the remaining ones those that need special attention. We applied the ensemble-based screening to both an EU-wide and a local (Poland) inventory. The EU-wide analysis highlighted a large number of inconsistencies. While the origin of some differences between EDGAR and the ensemble can be identified, their magnitude remains to be explained. These differences mostly occur for SO2 (sulfur oxides), PM (particulate matter) and NMVOC (non-methane volatile organic carbon) for the industrial and residential sectors and reach a factor of 10 in some instances. Spatial inconsistencies mostly occur for the industry and other sectors. At the local scale, inconsistencies relate mostly to differences in country sectorial shares that result from different sectors/activities being accounted for in the two types of inventories. This is explained by the fact that some emission sources are omitted in the local inventory due to a lack of appropriate geographically allocated activity data. We identified sectors and pollutants for which discussion between local and EU-wide emission compilers would be needed in order to reduce the magnitude of the observed differences (e.g. in the residential and industrial sectors). The ensemble-based screening proved to be a useful approach to spot inconsistencies by reducing the number of necessary inventory comparisons. With the progressive resolution of inconsistencies and associated inventory improvements, the ensemble will improve. In this sense, we see the ensemble as a useful tool to motivate the community around a single common benchmark and monitor progress towards the improvement of regionally and locally developed emission inventories.

De[formula omitted]Net: Under-display camera image restoration with feature deconvolution and kernel decomposition

While the under-display camera (UDC) system provides an effective solution for notch-free full-screen displays, it inevitably causes severe image quality degradation due to the diffraction phenomenon. Recent methods have achieved decent performance with deep neural networks, yet the characteristic of the point spread function (PSF) is less studied. In this paper, considering the large support and spatial inconsistency of PSF, we propose De2Net for UDC image restoration with feature deconvolution and kernel decomposition. In terms of feature deconvolution, we introduce Wiener deconvolution as a preliminary process, which alleviates feature entanglement caused by the large PSF support. Besides, the deconvolution kernel can be learned from training images, eliminating the tedious PSF-obtaining process. As for kernel decomposition, we observe regular patterns for PSFs at different positions. Thus, with a kernel prediction network (KPN) deployed for handling the spatial inconsistency problem, we improve it from two aspects, i.e., (i) decomposing the predicted kernels into a set of bases and weights, (ii) decomposing kernels into groups with different dilation rates. These modifications largely improve the receptive field under certain memory limits. Extensive experiments on three commonly used UDC datasets show that De2Net outperforms existing methods both quantitatively and qualitatively. Source code and pre-trained models are available at https://github.com/HyZhu39/De2Net.

EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer

Video Motion Magnification (VMM) aims to break the resolution limit of human visual perception capability and reveal the imperceptible minor motion that contains valuable information in the macroscopic domain. However, challenges arise in this task due to photon noise inevitably introduced by photographic devices and spatial inconsistency in amplification, leading to flickering artifacts in static fields and motion blur and distortion in dynamic fields in the video. Existing methods focus on explicit motion modeling without emphasizing prioritized denoising during the motion magnification process. This paper proposes a novel dynamic filtering strategy to achieve static-dynamic field adaptive denoising. Specifically, based on Eulerian theory, we separate texture and shape to extract motion representation through inter-frame shape differences, expecting to leverage these subdivided features to solve this task finely. Then, we introduce a novel dynamic filter that eliminates noise cues and preserves critical features in the motion magnification and amplification generation phases. Overall, our unified framework, EulerMormer, is a pioneering effort to first equip with Transformer in learning-based VMM. The core of the dynamic filter lies in a global dynamic sparse cross-covariance attention mechanism that explicitly removes noise while preserving vital information, coupled with a multi-scale dual-path gating mechanism that selectively regulates the dependence on different frequency features to reduce spatial attenuation and complement motion boundaries. We demonstrate extensive experiments that EulerMormer achieves more robust video motion magnification from the Eulerian perspective, significantly outperforming state-of-the-art methods. The source code is available at https://github.com/VUT-HFUT/EulerMormer.

Carbon Emission Drivers and Critical Paths in the Interaction of the "Local-Domestic-International" Economic Cycle - A case study of Beijing

Abstract It is crucial to study the carbon emissions worldwide induced by urban consumption activities. Taking consumption-oriented city Beijing as an example, we constructed a nested multi-regional input-output model (MRIO), and measured carbon emissions and value-added in local, domestic, and international systems. Furthermore, the structural decomposition analysis (SDA) and structural path analysis (SPA) was applied to analyze cross-system driving forces and key paths of carbon emission changes. The conclusions show: (1) Beijing's consumption leads to the highest carbon emissions in the domestic system but the highest value-added in the local system. There is spatial inconsistency in carbon emissions and value-added. (2) The intermediate commodity input-output effect (ICIOE) of intra-domestic provinces is the main driving factors contributing to the reduction of carbon emissions. In contrast, the ICIOE of inter-domestic provinces is the main factor leading to the rise. (3) In the top 10 types of key paths for Beijing’s consumption-based carbon emissions (CBCE) growth, electric power and construction sectors in domestic systems are key sectors. Chemical products and transport equipment in foreign systems are key sectors for Beijing’s CBCE decrease. Our findings suggest Beijing enhancing cross-system cooperation to achieve carbon reduction targets. JEL classification numbers: R15. Keywords: Consumption-based carbon emissions, Multi-regional input-output, Structural decomposition analysis, Structural path analysis.

Decoding the inconsistency of six cropland maps in China

Accurate cropland information is critical for agricultural planning and production, especially in food-stressed countries like China. Although widely used medium-to-high-resolution satellite-based cropland maps have been developed from various remotely sensed data sources over the past few decades, considerable discrepancies exist among these products both in total area and in spatial distribution of croplands, impeding further applications of these datasets. The factors influencing their inconsistency are also unknown. In this study, we evaluated the consistency and accuracy of six cropland maps widely used in China in circa 2020, including three state-of-the-art 10-m products (i.e., Google Dynamic World, ESRI Land Cover, and ESA WorldCover) and three 30-m ones (i.e., GLC_FCS30, GlobeLand 30, and CLCD). We also investigated the effects of landscape fragmentation, climate, and agricultural management. Validation using a ground-truth sample revealed that the 10-m-resolution WorldCover provided the highest accuracy (92.3%). These maps collectively overestimated Chinese cropland area by up to 56%. Up to 37% of the land showed spatial inconsistency among the maps, concentrated mainly in mountainous regions and attributed to the varying accuracy of cropland maps, cropland fragmentation and management practices such as irrigation. Our work shed light on the promotion of future cropland mapping efforts, especially in highly inconsistent regions.

SCTrans: Self-align and cross-align transformer for few-shot segmentation

Few-shot Semantic Segmentation (FSS) refers to train a segmentation model that can be generalized to novel categories with limited labeled images. One challenge of FSS is spatial inconsistency between support and query images, e.g., appearance and texture. Most existing methods are only committed to utilizing the semantic-level prototypes of support images to guide mask predictions. These methods, nevertheless, only focus on the most discriminate regions of the object rather than holonomic feature representations. Besides, another question exists that the lack of interaction between paired support and query images. In this paper, we propose a self-align and cross-align transformer (SCTrans) to remedy the above limitations. Specifically, we design a feature fusion module (FFM) to incorporate low-level information from the query branch into mid-level semantic features, boosting the semantic representations of query images. In addition, a feature alignment module is designed to bidirectionally propagate semantic information from support to query images conditioned on more representative support and query features, increasing both intra-class similarities and inter-class differences. Extensive experiments on PASCAL-5i and COCO-20i show that our SCTrans significantly advances the state-of-the-art methods.

Identifying the Relationships between Landscape Pattern and Ecosystem Service Value from a Spatiotemporal Variation Perspective in a Mountain–Hill–Plain Region

Identifying the changes in landscape pattern and ecosystem service value (ESV) and clarifying their relationship in temporal changes and spatial variations can provide insight into regional landscape features and scientific support for regional landscape planning. Leveraging land use data from the Yihe River Basin, we quantitatively assessed the landscape pattern and ESV shifts spanning from 2000 to 2018 using the landscape pattern indexes and the equivalence factor method. We employed Pearson correlation metrics and the geographically weighted regression model to explore the interrelation of their spatiotemporal variations. Our results show the following: (1) Forestland represents the most expansive land cover category. Apart from construction land, all other types experienced a decline in area. The most notable change occurred in the area of construction land. (2) The aggregation of the overall landscape shows a downward trend. The levels of fragmentation, landscape diversity, and richness increased. (3) Throughout the entire study period, the overall ESV gradually decreased, and the land cover type with the greatest contribution to the ESV was forestland. (4) In terms of temporal changes, the patch density and edge density of the overall area are significantly negatively correlated with total ESVs. The largest values for the patch index, perimeter–area fractal dimension (PAFRAC), and aggregation are significantly positively correlated with total ESVs. (5) In terms of spatial variation, the contagion index (CONTAG), PAFRAC, and the Shannon diversity index (SHDI) were noticeably correlated with ESVs. The CONTAG is positively correlated with ESVs upstream, but negatively midstream and downstream. The SHDI is negatively correlated with ESVs upstream, but positively midstream and downstream. The PAFRAC exhibits a positive correlation with ESVs for the most part. The association between the landscape pattern indexes and ESVs exhibits temporal and spatial inconsistencies in most instances, suggesting a spatiotemporal scale effect in their relationship. This study recommends that the local government devises a long-term strategy for urban development and exercises stringent control over the unregulated expansion of construction land. Through reasonable territorial spatial planning, government departments could enhance the connectivity of the overall landscape pattern of the Yihe River Basin to achieve the reasonable allocation and sustainable development of regional resources.

Real-Time Monitoring of Animals and Environment in Broiler Precision Farming—How Robust Is the Data Quality?

Increasing digitalization in animal farming, commonly addressed as Precision Livestock Farming (PLF), offers benefits in terms of productivity, sustainability, reduced labor and improved monitoring of animal welfare. However, the large amounts of collected data must be stored, processed and evaluated in a proper way. In practice, challenges of continuous and exact data collection can arise, e.g., from air pollutants like dust occluding cameras and sensors, degrading material, the ever-present commotion caused by animals, workers and machines, regularly required maintenance or weak signal transmission. In this study, we analyzed the quality of multi-source spatio-temporal data from a broiler house with 8100 birds over a period of 31 months collected by the Farmer Assistant System (FAS). This is a ceiling-suspended robot equipped with several sensors and cameras that continuously collect data while moving through the barn. The data analysis revealed numerous irregularities: missing values, outliers, repetitive measurements, systematic errors, and temporal and spatial inconsistencies. About 40–50% of all records collected with the early version of the FAS had to be sorted out. The newer version of FAS provided cleaner data, although still about 10–20% of the data had to be removed. Our study has shown that where sophisticated technological systems meet a challenging environment, a thorough and critical review of data completeness and quality is crucial to avoid misinterpretation. The pipeline developed here is designed to help developers and farmers detect failures in signal processing and localize the problem in the hardware components. Scientists, industrial developers and farmers should work more closely together to develop new PLF technologies to more easily advance digitization in agriculture.

P07.04.A ELASTIC IMAGE FUSION OF INTRAOPERATIVE ULTRASOUND AND PREOPERATIVE MRI FOR IMPROVING NAVIGATION ACCURACY IN BRAIN TUMOR SURGERY

Abstract BACKGROUND In brain surgery, neuronavigation based on preoperative MRI is limited by various physical and operational factors, such as surgery-induced brain shift. Using navigated intraoperative ultrasound (iUS) imaging and 3D iUS image reconstruction may help improve neuronavigation. However, the registration of MRI and US scans can lead to spatial inconsistencies between the two modalities. This study aims to evaluate the clinical integration of navigated iUS imagining and its potential to improve the accuracy of resection during brain tumor surgery by comparing the performance of rigid and elastic MRI-iUS image fusion algorithms during retrospective evaluation. MATERIAL AND METHODS N = 50 patients with brain tumors were prospectively enrolled in this trial. The neuronavigation system (BrainLab AG) used in the study allowed for the reconstruction and integration of 3D iUS imaging, which was acquired multiple times throughout the surgery using a tracked ultrasound probe (BK Medical). Prototypes of automatic rigid and elastic MRI-iUS image fusion algorithms (Brainlab Elements Image Fusion) were retrospectively applied to improve co-registration accuracy between the MRI and iUS data. To evaluate the image co-registration accuracy, anatomical landmarks were defined in the MRI and iUS scans and used to measure Euclidean distances between each landmark pair. RESULTS Improvements in the image quality over the course of the study indicated that skills in US handling are essential. Contrast behavior and tumor structure influence the visibility of the tumor in the US. Artifacts caused by hemostatic agents challenge the US image quality and the fluid-filled resection cavity requires experience in probe handling. In terms of image fusion, significant mismatches of the iUS and MRI data were reported. For scans acquired before resection, rigid fusion using a novel co-registration algorithm may enhance the registration accuracy with mean target registration errors for two representative patients of 6.5/8.9 mm and 3.7/3.4 mm before and after registration update, respectively. For iUS scans acquired after tumor resection, rigid fusion is inherently limited due to non-linear brain shifts. Therefore, elastic image fusion has been applied to provide deformable MR-iUS image co-registration. CONCLUSION Navigated iUS imaging can be integrated into clinical routine and the use of MR-iUS image co-registration for updating navigation is a promising tool to compensate brainshift during surgical resection. However, further studies are needed to quantify the accuracy and assess whether iUS could potentially replace the use of iMRI in resection control of selected cases.

A multiscalar and multiproxy geoarchaeological approach to site formation processes at the Middle and Upper Palaeolithic site of La Roche-à-Pierrot, Saint-Césaire, France

The site of La Roche-à-Pierrot in Saint-Césaire (Charente-Maritime, France) produced a succession of Mousterian, Châtelperronian and Aurignacian occupations, and continues to play a central role in debates concerning the Middle-to-Upper Palaeolithic transition. The source of controversy surrounding the site relates to ambiguities concerning the overall archaeological sequence, the cultural association of the human remains found at the site and the limited number of robust absolute dates. Here, we present the results of a multiscalar, multiproxy geoarchaeological investigation of the site's sedimentary sequence. Our study integrates geomorphology, field lithostratigraphy, microstratigraphy, geochemistry and absolute dating methods (radiocarbon and optically stimulated luminescence) designed to characterize site formation processes. We propose a site formation model involving the evolution of a karstified limestone cliff from a semi-closed system to an exposed slope deposit, with sediments at the base of the cliff accumulating under periglacial conditions of MIS3, broadly between ca. 59.9 ± 3.9 ka and ca. 37.7 ka. The lowermost Mousterian occupations took place in a semi-closed, sheltered space in which sedimentary rates were low, involving mainly cryoclastic roof spall and episodic percolation of fine-grained sediment. This depositional environment generated a Mousterian archaeological palimpsest in the proximal area and translocated downslope. Subsequent Mousterian, Châtelperronian and Aurignacian remains embedded within diamictons were deposited in an open-air context, on a sloping surface at the apex of a palaeotalus, and possibly above the site, at the top of the cliff. The resulting diachronous surfaces and immature deposits were subject to solifluction and slopewash, with low sedimentary rates. Our geoarchaeological study sheds new light on previously noted spatial inconsistencies in the archaeological sequence and constitutes a rigorous framework for further archaeological research at the site, highlighting the potential of a multiscalar, multiproxy site formation research to improve stratigraphic investigation of Palaeolithic sites in similar geomorphological contexts.

Deep learning-driven diagnosis: A multi-task approach for segmenting stroke and Bell's palsy

Strong efforts have been undertaken to enhance the diagnosis and identification of diseases that cause facial paralysis, such as Bell's palsy and stroke, because of their detrimental social effects. Stroke is one of the most serious and potentially fatal conditions among the major cardiovascular disorders. We are introducing a deep-learning-based method for early diagnosis of facial paralysis diseases such as stroke and Bell's palsy. Recognizing the costs associated with traditional diagnostic techniques like magnetic resonance tomography (MRI) and computed tomography (CT) scan images, our model employs a multi-task network, integrating face parsing, facial asymmetry parsing, and category enhancement. Spatial inconsistencies are addressed via a depth-map estimation module that leverages an instance-specific kernel approach. To clarify the boundaries of facial components, we use category edge detection with a foreground attention module, generating generic geometric structures and detailed semantic cues. Our model is trained on two datasets, comprising individuals with regular smiles and those with one-sided facial weakness. This cost-effective, easily accessible solution can streamline the diagnostic process, minimizing data gaps, and reducing needless rescreening and intervention costs.

Constructing Spatio-Temporal Graphs for Face Forgery Detection

Recently, advanced development of facial manipulation techniques threatens web information security, thus, face forgery detection attracts a lot of attention. It is clear that both spatial and temporal information of facial videos contains the crucial manipulation traces, which are inevitably created during the generation process. However, most existing face forgery detectors only focus on the spatial artifacts or the temporal incoherence, and they are struggling to learn a significant and general kind of representations for manipulated facial videos. In this work, we propose to construct spatial-temporal graphs for fake videos to capture the spatial inconsistency and the temporal incoherence at the same time. To model the spatial-temporal relationship among the graph nodes, a novel forgery detector named Spatio-Temporal Graph Network (STGN) is proposed, which contains two kinds of graph-convolution-based units, the Spatial Relation Graph Unit (SRGU) and the Temporal Attention Graph Unit (TAGU). To exploit spatial information, the SRGU models the inconsistency between each pair of patches in the same frame, instead of focusing on the low-level local spatial artifacts which are vulnerable to samples created by unseen manipulation methods. And, the TAGU is proposed to model the long-distance temporal relation among the patches at the same spatial position in different frames with a graph attention mechanism based on the inter-node similarity. With the SRGU and the TAGU, our STGN can combine the discriminative power of spatial inconsistency and the generalization capacity of temporal incoherence for face forgery detection. Our STGN achieves state-of-the-art performances on several popular forgery detection datasets. Extensive experiments demonstrate both the superiority of our STGN on intra manipulation evaluation and the effectiveness for new sorts of face forgery videos on cross manipulation evaluation.

User-Aware Evaluation for Medium-Resolution Forest-Related Datasets in China: Reliability and Spatial Consistency

Forest cover data are fundamental to sustainable forest management and conservation. Available medium-resolution publicly shared forest-related datasets provide primary information on forest distribution. The evaluation of relevant datasets is of great importance to learn about the differences, characterize the accuracy, and provide a reference for rational use. This study presents an evaluation and analysis of the forest-related datasets in China around 2020, including TreeCover and the forest-related layer (latter referred to as the forest datasets) in WorldCover, Esri land cover, FROM-GLC10, GlobeLand30, and GLC_FCS30. These forest datasets, that are obtained by aggregating forest-related lasses based on the classification schemes, are analyzed from spatial consistency and accuracy comparison. The results illustrate that forest datasets with 10m resolution are generally more precise than those with 30m resolution in China. WorldCover shows the highest accuracy, with producer accuracy and user accuracy of 91.4% and 87.09%, respectively. These datasets exhibit high accuracy but great spatial inconsistency. The more consistent the regions are, the more accurate the accuracy is. High consistency (≥5, i.e., classified into forests by five datasets) areas account for 56.49% of areas of forest classified (AFC), while the area of low consistency (≤2) reach 25.51% of AFC. The analysis delves into the datasets, offering a reliable reference for the usage of these datasets.