As the fourth pole of China's economic growth, Chengdu-Chongqing urban agglomeration plays a significant role in reinforcing ecological barrier upper reaches Yangtze River, and is crucial for environmental protection strategies. In this paper, Google Earth Engine (GEE) MODIS images from 2000, 2005, 2010, 2015, 2022 were utilized to construct Improved Remote Sensing Ecological Index (IRSEI) characterize quality more accurately than RSEI. Additionally, combined with nighttime light remote...

Group activities usually involve spatio-temporal dynamics among many interactive individuals, while only a few participants at several key frames essentially define the activity. Therefore, effectively modeling group-relevant and suppressing irrelevant actions (and interactions) are vital for group activity recognition. In this paper, we propose novel method based on deep reinforcement learning to progressively refine low-level features high-level relations of activities. Firstly, construct...

ABSTRACT The conventional use of the acetone method for waterborne polyurethane acrylate(WPUA) preparation encounters challenges in completely eliminating volatile organic compound emissions, presenting obstacles to meeting potentially stricter emission standards future. This work investigated possibility preparing WPUA using without solvents. For first time, it was found that excessive neutralizing agents can contribute performance regulation dispersions by inhibiting crystallization hard...

Medical anatomy segmentation is essential for computer-aided diagnosis and lesion localization in medical images. For example, segmenting individual ribs benefits localizing the lung lesions providing vital measurements (such as rib spacing) generating reports. Existing methods segment shape-different anatomies striped ribs, bulky lungs, angular scapula) with same network architecture, morphology heterogeneity heavily overlooked. Although some shape-aware operators like deformable...

With the increasing incidence of thyroid cancer worldwide and demand for surgery, risk parathyroid injury is also increasing, which will lead to postoperative hypoparathyroidism (HP) hypocalcemia. In order improve quality life patients after there an urgent need develop a novel platform that can identify gland immediately during surgery. The promotes increase blood calcium concentration by secreting hormone (PTH). Therefore, in this study, we used sensitive surface-enhanced Raman...

Benefiting from its succinctness and robustness, skeleton-based action recognition has recently attracted much attention. Most existing methods utilize local networks (e.g recurrent, convolutional, graph convolutional networks) to extract spatio-temporal dynamics hierarchically. As a consequence, the non-local dependencies, which contain more details semantics respectively, are asynchronously captured in different level of layers. Moreover, limited domain ignore information frequency domain....

Benefiting from its succinctness and robustness, skeleton-based action recognition has recently attracted much attention. Most existing methods utilize local networks (e.g. recurrent network, convolutional graph network) to extract spatio-temporal dynamics hierarchically. As a consequence, the non-local dependencies, which contain more details semantics respectively, are asynchronously captured in different level of layers. Moreover, limited domain ignore information frequency domain. To...

Point clouds are widely applied in 3D visual sensing and perception. However, manually annotating point is much more tedious time-consuming than that for 2D images. Fortunately, semi-supervised learning can leverage massive unlabeled data to alleviate this issue, which becoming a promising technique nowadays. In paper, we propose novel (SSL) framework cloud classification, named HPSSL. Its unsupervised branch performs both the representation embedding pseudo-classification tasks....

In this article, we analyzed the experimental data based on TaOx memristor and found that threshold switching (TS) characteristics are related to temperature, its logarithmic I–V curve is in good agreement with space charge limiting current conduction mechanism. We use mechanism establish a TS physical model then build an LTspice model. The fitted data, which basically consistent. Next, using simulate leaky integrate-and-fire neuron circuit, basic dynamics realized. By changing external...

Hainan Island has become an important molybdenum (Mo) producer in East China, with the proven and measured metal Mo reserves of > 0.29 Mt 0.69 Mt, respectively. The known Mo-related deposits occurrence which genetically might be attributed to porphyry- hydrothermal vein types are hosted predominantly within Cretaceous granitoids. These granitoids belong high-K calc-alkaline, metaluminous weakly peraluminous I-type series, have geochemical affinities arc-related basalts as defined by SiO2...

The prefrontal cortex (PFC), which plays key roles in many higher cognitive processes, is a hierarchical system consisting of multi-scale organizations. Optimizing the working state at each scale essential for PFC's information processing. Typical optimal states different scales have been separately reported, including dopamine-mediated inverted-U profile memory (WM) level, critical dynamics network and detailed balance excitatory inhibitory currents (E/I balance) cellular level. However, it...

Behavioral analysis of macaques provides important experimental evidence in the field neuroscience. In recent years, video-based automatic animal behavior has received widespread attention. However, methods capable extracting and analyzing daily movement trajectories their living cages remain underdeveloped, with previous approaches usually requiring specific environments to reduce interference from occlusion or environmental change. Here, we introduce a novel method, called MonkeyTrail,...

Abstract In this work, a compact model of the diffusive memristor is proposed from perspective transition electronic transmission mechanisms induced by dynamics filament. First, new physical established based on tunneling that are used to fit experimental data, and results indicate it versatile enough for various memristors. addition, threshold voltage ( V th ) negatively correlates with ratio ionic migration diffusion coefficient u i /Ds ), hold h positively Ds/u which useful selection...

Instructional videos are very useful for completing complex daily tasks, which naturally contain abundant clip-narration pairs. Existing works procedure understanding keen on pretraining various video-language models with these pairs and then fine-tuning downstream classifiers localizers in predetermined category space. These proficient at representing short-term actions, basic objects, their combinations, but they still far from long-term procedures. In addition, the faces problem of...

Abstract In recent years, structural colors derived from photonic crystals (PCs) with a periodically ordered nanostructure are gorgeous and iridescent, but once their structure is destroyed, they will fade. this work, the feasibility of application bio‐based waterborne polyurethanes (WPU) in color films was explored. The stability PCs enhanced WPU as kind green product, which can replace solvent polyurethane one. A tung oil polyol (TOP) fabricated by one‐step method simple purification...

Vegetation biophysical products offer unique opportunities to examine long-term vegetation dynamics and land surface phenology (LSP). It is important understand the time-series performances of various global for change research. However, few endeavors have been dedicated assessing characteristics or LSP extraction derived from different satellite products, especially in mountainous areas with highly fragmented rugged surfaces. In this paper, we assessed detections Global LAnd Surface...

An important challenge for neural networks is to learn incrementally, i.e., new classes without catastrophic forgetting. To overcome this problem, generative replay technique has been suggested, which can generate samples belonging learned while learning ones. However, such models usually suffer from increased distribution mismatch between the generated and original along process. In work, we propose DeepCollaboration (D-Collab), a collaborative framework of deep discriminative solve problem...

Grazing intensity (GI) is an important indicator for grazing situations in pastoral areas. However, it has been difficult to be observed directly the field, due randomness and dynamics of behavior livestock. Consequently, lack actual GI information become a common issue studies on quantitatively estimating GI. In this paper, novel quantitative estimation method proposed based Space-Air-Ground integrated monitoring technology. It systematically integrates GPS tracking technology, Unmanned...

Many convolutional neural networks have been proposed for image classification in recent years. Most tend to decrease the plane size of feature maps stage-by-stage, such that generated within each stage show same size. This concept governs design most networks. However, it can also lead semantic deficiency high-resolution as they are always placed shallow layers a network. Here, we propose novel network architecture, named ScaleNet, which consists stacked convolution-deconvolution blocks and...

High sensitivity, consistent conductivity, and suitable mechanical strength were essential for strain sensor performance in the field of flexible wearables. The hydrogel containing poly(3,4-ethylenedioxythiophene)/lignosulfonate (PEDOT/LS) was bound to destroy network affect its characteristics, even if it could safely consistently increase conductivity. In this work, a salting-out after freeze-casting assisted UV-curing (SFUV) strategy first offered as solution problem. Waterborne...

Dissipative soliton generation in a novel MIR mode-locked laser is presented. The emits at 2.8 um with ~30 nm bandwidth, and the spectral transitions of molecules between different states are observed.