Target Category Research Articles

Spontaneous transfer of relational category structures between category learning tasks: A novel approach to measure analogical transfer.

The ability to spontaneously access knowledge of relational concepts acquired in one domain and apply it to a novel domain has traditionally been explored in the analogy literature via the problem-solving paradigm. In the present work, we propose a novel procedure based on categorisation as a complementary approach to assess spontaneous analogical transfer-using one category learning task to enhance learning of the same underlying category structures in another domain. In Experiment 1, we demonstrate larger improvements in classification performance across blocks of training in a target category learning task among participants that underwent a base category learning task relative to a separate group of participants learning the target category structures for the first time, thus providing evidence for spontaneous transfer of the category structures. In Experiment 2, we demonstrate similar evidence of spontaneous transfer for participants that underwent a comparison-based base category learning task under a more rigorous context shift between the base and target category learning tasks. Additional exploratory analyses across both experiments showcase ways in which this paradigm can be used to answer questions regarding the analogical transfer of relational category structures and generate promising paths for future work.

Urine Sediment Detection Algorithm Based on Channel Enhancement and Deformable Convolution.

Urine sediment detection is a vital method in clinical urine analysis for evaluating an individual's kidney and urinary system health, as well as identifying potential diseases. Nevertheless, urine sediment images exhibit the characteristic of diverse shapes for the same category of targets. These characteristics pose a considerable challenge to the accurate identification of the visible components within the images. We approach urine sediment detection as an object detection task and have introduced the specialized YOLOv7-CSD algorithm for this purpose. In particular, we have integrated channel enhancement feature pyramid network (CE-FPN) and selective kernel (SK) into the YOLOv7 model to address the issue of model confusion in classifying and identifying tasks caused by the feature aliasing effects of feature pyramid network (FPN). Furthermore, we enhance the efficient layer aggregation networks (ELAN) network by adding a second channel, enabling the model to acquire a more extensive set of feature information. On top of this, we introduce the deformable convolutional v3 (DCNv3) operator, allowing the model to dynamically adjust its receptive field, addressing the issue of variable shapes. Tested on the USE dataset and a dataset for urine crystals, YOLOv7-CSD achieves accuracies of 92.8 and 89.6 , respectively.

GradToken: Decoupling tokens with class-aware gradient for visual explanation of Transformer network

Transformer networks have been widely used in the fields of computer vision, natural language processing, graph-structured data analysis, etc. Subsequently, explanations of Transformer play a key role in helping humans understand and analyze its decision-making and working mechanism, thereby improving the trustworthiness in its real-world applications. However, it is difficult to apply the existing explanation methods for convolutional neural networks to Transformer networks, due to the significant differences between their structures. How to design a specific and effective explanation method for Transformer poses a challenge in the explanation area. To address this challenge, we first analyze the semantic coupling problem of attention weight matrices in Transformer, which puts obstacles in providing distinctive explanations for different categories of targets. Then, we propose a gradient-decoupling-based token relevance method (i.e., GradToken) for the visual explanation of Transformer’s predictions. GradToken exploits the class-aware gradient to decouple the tangled semantics in the class token to the semantics corresponding to each category. GradToken further leverages the relations between the class token and spatial tokens to generate relevance maps. As a result, the visual explanation results generated by GradToken can effectively focus on the regions of selected targets. Extensive quantitative and qualitative experiments are conducted to verify the validity and reliability of the proposed method.

Multi‐scale feature extraction for energy‐efficient object detection in remote sensing images

AbstractObject detection in remote sensing images aims to interpret images to obtain information on the category and location of potential targets, which is of great importance in traffic detection, marine supervision, and space reconnaissance. However, the complex backgrounds and large scale variations in remote sensing images present significant challenges. Traditional methods relied mainly on image filtering or feature descriptor methods to extract features, resulting in underperformance. Deep learning methods, especially one‐stage detectors, for example, the Real‐Time Object Detector (RTMDet) offers advanced solutions with efficient network architectures. Nevertheless, difficulty in feature extraction from complex backgrounds and target localisation in scale variations images limits detection accuracy. In this paper, an improved detector based on RTMDet, called the Multi‐Scale Feature Extraction‐assist RTMDet (MRTMDet), is proposed which address limitations through enhancement feature extraction and fusion networks. At the core of MRTMDet is a new backbone network MobileViT++ and a feature fusion network SFC‐FPN, which enhances the model's ability to capture global and multi‐scale features by carefully designing a hybrid feature processing unit of CNN and a transformer based on vision transformer (ViT) and poly‐scale convolution (PSConv), respectively. The experiment in DIOR‐R demonstrated that MRTMDet achieves competitive performance of 62.2% mAP, balancing precision with a lightweight design.

Advancing Proteolysis Targeting Chimera (PROTAC) Nanotechnology in Protein Homeostasis Reprograming for Disease Treatment.

Proteolysis targeting chimeras (PROTACs) represent a transformative class of therapeutic agents that leverage the intrinsic protein degradation machinery to modulate the hemostasis of key disease-associated proteins selectively. Although several PROTACs have been approved for clinical application, suboptimal therapeutic efficacy and potential adverse side effects remain challenging. Benefiting from the enhanced targeted delivery, reduced systemic toxicity, and improved bioavailability, nanomedicines can be tailored with precision to integrate with PROTACs which hold significant potential to facilitate PROTAC nanomedicines (nano-PROTACs) for clinical translation with enhanced efficacy and reduced side effects. In this review, we provide an overview of the recent progress in the convergence of nanotechnology with PROTAC design, leveraging the inherent properties of nanomaterials, such as lipids, polymers, inorganic nanoparticles, nanohydrogels, proteins, and nucleic acids, for precise PROTAC delivery. Additionally, we discuss the various categories of PROTAC targets and provide insights into their clinical translational potential, alongside the challenges that need to be addressed.

Strategic behavior in multi-criteria sorting with trust relationships-based consensus mechanism: Application in supply chain risk management

Strategic behavior is common in multi-criteria sorting, where manipulated alternatives are allocated to the target category to achieve the intended goal. Engaging in such strategic behavior in sorting consensus often comes at a cost, which is closely tied to the degree of preference adjustments and the level of trust relationships among decision makers. This study investigates strategic behavior using piecewise cost-based consensus mechanism in social trust network. Firstly, the trust relationship dependent piecewise cost is formally defined and formulated by considering the impact of trust relationship on the preference adjustments willingness to achieve sorting consensus. Then, based on the trust relationship dependent piecewise cost, a preference strategic manipulation model is proposed to achieve strategic behavior in sorting consensus, which is implemented by minimizing the cost of strategically guiding decision makers in adjusting their preferences. Considering that social trust network affects strategic manipulation, a preference-network collaborative strategic manipulation model is further proposed, which is designed to strategically guide decision makers in adjusting both their preferences and social trust networks. Moreover, the practicality of proposed strategic manipulation models is exemplified through a case study on supply chain risk management and their performance is validated via simulation analysis.

Initial implicit association between whole grains and taste does not predict consumption of whole grains in low-whole grain consumers: a pilot randomized controlled trial.

Health benefits of whole grain (WG) consumption are well documented. Current Dietary Guidelines for Americans recommend at least half of total grains consumed be WG; however, Americans consume less than one serving of WG per day. Inferior taste of whole grain products as compared with refined grain products has been reported as one of the main barriers to acceptability and consumption of whole grains. In this pilot study, we aimed to determine if mere exposure to WG foods in self-reported low WG consumers would improve their implicit associations between WG and pleasant taste. Healthy adults (n=45) were provided a variety of WG or refined grain (RG) products for home use for 6 weeks. Intake was measured by calculating disappearance and verified by a daily log. At the beginning and end of the intervention, we administered an Implicit Association Test (IAT), a computer test designed to measure indirectly the strength of association between pairs of concepts: (a) two contrasted target categories (WG and RG food images) and (b) two contrasted attribute categories (words relating to pleasant or unpleasant taste) via a classification task. Response time was used to calculate IAT D scores, indicating the strength of implicit associations between WG and RG and positive or negative taste. ANCOVA showed that average D scores at the end of the study shifted significantly toward a positive implicit association between WG and good taste (p<0.05) in participants whose baseline D scores indicated an initial preference for RG over WG. No significant differences were found between the WG and RG groups in overall consumption of provided grain products. These findings suggest that mere exposure to WG products over an extended period of time in a free-living situation can improve automatic attitudes toward WG, potentially leading to increased consumption of WG foods. Clinicaltrials.Gov, identifier NCT01403857.

B - 62 Cognitive Training Targeting Reward Responsiveness Promotes more Efficient Affective Processing in an Interference Go/NoGo Task

Abstract Objective Abnormalities in emotional processing are commonly seen in depression and anxiety, disorders also associated with decreased reward sensitivity i.e., anhedonia. We tested a noninvasive, cognitive training program aimed at boosting reward responsiveness and gaged if it may also improve affective processing efficiency. Methods Individuals (N = 50; 54% Female; 18–65 yo) with low hedonic tone (Positive and Negative Affect Scale/PANAS score &amp;lt; 25) and diagnostic levels of depression and/or anxiety (Patient Health Questionnaire-8/PHQ-8 or General Anxiety Disorder-7/GAD-7 score ≥ 10) who responded to community-posted flyers completed an affective go/no-go (AGN) task before and after completing an exploratory reward learning task, i.e., a multi-arm bandit (MAB). Participants were randomly assigned to a high-reward MAB training with either high variance (HV) or low variance (LV) in reward rates, HV being expected to boost reward maximization. In the AGN, participants saw negative and positive pictures and had to respond as fast as possible to pictures of a given target category (positive or negative). Results Following the HV vs LV training MAB, participants were more accurate (higher likelihood of hits), which was more evident in negative target blocks relative to positive target blocks (odds ratio/OR:0.61, 95% CI = [0.38,0.98]; z = −2.045, p = 0.041). Participants exhibited stronger decreases in hits response times following the HV vs LV training MAB, but across all target blocks (B:-37 ms, 95% CI = [−56,-18]; t = −3.806, p &amp;lt; 0.001). Conclusions A novel cognitive training program aimed at boosting reward sensitivity may help improve patients’ processing of emotionally taxing stimuli. Targeting reward sensitivity is a critical component of improving clinical outcomes in depressed and anxious patients..

GMS-YOLO: An Algorithm for Multi-Scale Object Detection in Complex Environments in Confined Compartments.

Many compartments are prone to pose safety hazards such as loose fasteners or object intrusion due to their confined space, making manual inspection challenging. To address the challenges of complex inspection environments, diverse target categories, and variable scales in confined compartments, this paper proposes a novel GMS-YOLO network, based on the improved YOLOv8 framework. In addition to the lightweight design, this network accurately detects targets by leveraging more precise high-level and low-level feature representations obtained from GhostHGNetv2, which enhances feature-extraction capabilities. To handle the issue of complex environments, the backbone employs GhostHGNetv2 to capture more accurate high-level and low-level feature representations, facilitating better distinction between background and targets. In addition, this network significantly reduces both network parameter size and computational complexity. To address the issue of varying target scales, the first layer of the feature fusion module introduces Multi-Scale Convolutional Attention (MSCA) to capture multi-scale contextual information and guide the feature fusion process. A new lightweight detection head, Shared Convolutional Detection Head (SCDH), is designed to enable the model to achieve higher accuracy while being lighter. To evaluate the performance of this algorithm, a dataset for object detection in this scenario was constructed. The experiment results indicate that compared to the original model, the parameter number of the improved model decreased by 37.8%, the GFLOPs decreased by 27.7%, and the average accuracy increased from 82.7% to 85.0%. This validates the accuracy and applicability of the proposed GMS-YOLO network.

WB-LRP: Layer-wise relevance propagation with weight-dependent baseline

DeepLift is a special Layer-wise Relevance Propagation (LRP) algorithm that assigns importance to features by evaluating the impact of small perturbations in input features on the output. However, we discover that only perturbations parallel to the plane defined by weights and input features affect the output. To address this issue, we propose a new LRP algorithm that offers more accurate instance-level explanation for neural networks. Firstly, we derive the baselines for various existing LRP algorithms using DeepLift theory and identify that these baselines often disregard model weights, sample features, or both. Secondly, the Weight-dependent Baseline Layer-wise Relevance Propagation (WB-LRP) algorithm is proposed to address this problem, by deriving the norm-invariant rule (m-rule) according to our discovery. Then, the m-rule is extended to the positive norm-invariant rule (m+-rule), focusing specifically on the positive parts of the weights. Finally, we extend the WB-LRP theory to accommodate various baseline settings, creating a framework that integrates nearly all existing LRP algorithms. Experimental results show that the relevance interpretation depends on both model weights and sample features. The proposed WB-LRP algorithm can be designed with different baselines to adjust the proportions of model weights and sample features in the visualization results, thus enabling separate visualization of the relevance of sample features and model weights to the target category.

Opto-CLIP reveals dynamic FMRP regulation of mRNAs upon CA1 neuronal activation.

Neuronal diversity and function are intricately linked to the dynamic regulation of RNA metabolism, including splicing, localization, and translation. Electrophysiologic studies of synaptic plasticity, models for learning and memory, are disrupted in Fragile X Syndrome (FXS). FXS is characterized by the loss of FMRP, an RNA-binding protein (RBP) known to bind and suppress translation of specific neuronal RNAs. Since molecular studies have demonstrated that synaptic plasticity in CA1 excitatory hippocampal neurons is protein-synthesis dependent, together these observations have suggested a potential role for FMRP in synaptic plasticity in FXS. To explore this model, we developed a new experimental platform, Opto-CLIP, to integrate optogenetics with cell-type specific FMRP CLIP and RiboTag in CA1 hippocampal neurons, allowing investigation of FMRP-regulated dynamics after neuronal activation. We tracked changes in FMRP binding and ribosome-associated RNA profiles 30 minutes after neuronal activation. Our findings reveal a significant reduction in FMRP-RNA binding to transcripts encoding nuclear proteins, suggesting FMRP translational inhibition may be de-repressed to allow rapid translational responses required for neuronal homeostasis. In contrast, FMRP binding to transcripts encoding synaptic targets were generally stable after activation, but all categories of targets demonstrated variability in FMRP translational control. Opto-CLIP revealed differential regulation of subsets of transcripts within CA1 neurons rapidly after depolarization, and offers promise as a generally useful platform to uncover mechanisms of RBP-mediated RNA regulation in the context of synaptic plasticity.

YOLO-HyperVision: A vision transformer backbone-based enhancement of YOLOv5 for detection of dynamic traffic information

With the increase of traffic flow in modern urban areas, traffic congestion has become a serious problem that affects people’s normal production and life. Using target detection technology instead of manual labor can quickly detect the road traffic situation and provide timely information about the traffic flow. However, when using drones to observe the traffic flow in the air, the perspective effect will cause the detected vehicles and pedestrians to be very small, and the scale difference between different categories of targets is large, which increases the detection difficulty of a single convolutional neural network model. In order to solve the problem of low accuracy of traditional single-stage target detection models, this study proposes an improved Yolov5 vehicle target detection model with Vision Transformer (VIT) backbone, You Only Look Once-HyperVision (YOLO-HV), which aims to solve the problem of poor multi-scale target recognition performance caused by the inability of traditional CNN networks to integrate contextual information, and help drones achieve more efficient and accurate traffic flow recognition functions. This study deeply integrates the Vision Transformer (VIT) backbone and Convolutional Neural Network (CNN), effectively combining the multi-scale detection advantages of Vision Transformer and the inductive bias ability of Convolutional Neural Network, and adds multi-scale residual modules and context correlation enhancement modules, which greatly improves the recognition accuracy of single-stage detectors for drone images. Through comparative experiments on the VisDrone dataset, it is found that the detection performance of this model is improved compared with several commonly used detection models. YOLO-HV can increase the mean average precision (mAP) by 3.3% compared with the pure convolutional network of the same model size. YOLO-HV model has achieved excellent performance in the task of traffic flow image detection taken by drones, and can more accurately identify and classify road vehicles than various target detection models.

Ammonia borane-based targets for new developments in laser-driven proton boron fusion

Nuclear fusion reactions involving protons and boron-11 nuclei are sparking increasing interest thanks to advancements in high-intensity, short-pulse laser technology. This type of reaction holds potential for a wide array of applications, from controlled nuclear fusion to radiobiology and cancer therapy. In line with this motivation, solid ammonia borane samples were developed as target material for proton-boron (pB) nuclear fusion. Following synthesis and shaping, these samples were tested for the first time in a laser-plasma pB fusion experiment. An investigation campaign focusing on surface chemical/physical analysis was carried out to characterize such samples in terms of composition of B and H, precursors of the pB fusion nuclear reaction, thus having a key impact on the yield of the generated nuclear products, i.e., alpha particles. A follow-up experiment used an 8 J, 800 fs laser pulse with an intensity of 2 × 1019 W cm−2 to irradiate the targets, generating ∼ 108 alpha particles per steradian. The alpha particle energy range (2–6 MeV) and normalized yield per laser energy of up to (6 × 107 J/sr) are comparable with the best previous alpha particle yields found in literature. These results pave the way for a yet unexplored category of pB fusion targets.

Confidence correction for trained graph convolutional networks

Adopting Graph Convolutional Networks (GCNs) for transductive node classification is a hot research direction in artificial intelligence. Vanilla GCNs are primarily under-confident and struggle to clarify the final classification results explicitly due to the lack of supervision. Existing works mainly alleviated this issue by improving annotation deficiency and introducing addition regularization terms. However, these methods need to re-train the model from the beginning, which is computationally expensive for large dataset and model. To deal with this problem, a novel confidence correction mechanism (CCM) for trained GCNs is proposed in this work. Such mechanism aims at calibrating the confidence output of each node in the inference stage by jointly inferring the feature and predicted pseudo label. Specifically, in the inference stage, it uses the predicted pseudo label to select target-related features over all network to obtain a more confident and better result. Such selectivity is formulated as an optimization problem to maximize the category score of each node. In addition, the greedy optimization strategy is utilized to solve this problem and we have mathematically proven that the proposed mechanism can reach the local optimum by mathematical induction. Note that such mechanism is flexible and can be introduced to most GCN-based model. Extensive experimental results on benchmark datasets show that the proposed method can promote the confidence of the final target category and improve the performance of GCNs in the inference stage.

Distractor similarity and category variability effects in search

Categorical search involves looking for objects based on category information from long-term memory. Previous research has shown that search efficiency in categorical search is influenced by target/distractor similarity and category variability (i.e., heterogeneity). However, the interaction between these factors and their impact on different subprocesses of search remains unclear. This study examined the effects of target/distractor similarity and category variability on processes of categorical search. Using multidimensional scaling, we manipulated target/distractor similarity and measured category variability for target categories that participants searched for. Eye-tracking data were collected to examine attentional guidance and target verification. The results demonstrated that the effect of category variability on response times (RTs) was dependent on the level of target/distractor similarity. Specifically, when distractors were highly similar to target categories, there was a negative relation between RTs and variability, with low variability categories producing longer RTs than higher variability categories. Surprisingly, this trend was only present in the eye-tracking measures of target verification but not attentional guidance. Our results suggest that searchers more effectively guide attention to low-variability categories compared to high-variability categories, regardless of the degree of similarity between targets and distractors. However, low category variability interferes with target match decisions when distractors are highly similar to the category, thus the advantage that low category variability provides to searchers is not equal across processes of search.

Internationalisation of a Mayor: Sadiq Khan’s Involvement in the Brexit Process

After his re-election as the mayor of London, Khan underlined “the scars of Brexit” that are not healed yet. His political stance against leaving the EU has formed a critical interference of Khan in a foreign policy decision of national government. In the light of the literature on internationalisation of non-central government, this study aims to explain Khan’s “actorness” in the aftermath of Brexit referendum by utilizing Hocking’s (1999) theoretical framework. Dimensions of the mayor’s involvement in the Brexit process are explained under the categories of initiators, channels and targets; yet a new grouping titled voices proposed by this study would complete the whole picture of analysis. The press releases derived from the official website of London government constitute the basis of research material.

Selective nitration of Hsp90 acts as a metabolic switch promoting tumor cell proliferation

Tumors develop in an oxidative environment characterized by peroxynitrite production and downstream protein tyrosine (Y) nitration. We showed that tyrosine nitration supports schwannoma cell proliferation and regulates cell metabolism in the inheritable tumor disorder NF2-related Schwannomatosis (NF2-SWN). Here, we identified the chaperone Heat shock protein 90 (Hsp90) as the first nitrated protein that acts as a metabolic switch to promote schwannoma cell proliferation. Doubling the endogenous levels of nitrated Hsp90 in schwannoma cells or supplementing nitrated Hsp90 into normal Schwann cells increased their proliferation. Metabolically, nitration on either Y33 or Y56 conferred Hsp90 distinct functions; nitration at Y33 (Hsp90NY33) down-regulated mitochondrial oxidative phosphorylation, while nitration at Y56 (Hsp90NY56) increased glycolysis by activating the purinergic receptor P2X7 in both schwannoma and normal Schwann cells. Hsp90NY33 and Hsp90NY56 showed differential subcellular and spatial distribution corresponding with their metabolic and proliferative functions in schwannoma three-dimensional cell culture models. Collectively, these results underscore the role of tyrosine nitration as a post-translational modification regulating critical cellular processes. Nitrated proteins, particularly nitrated Hsp90, emerge as a novel category of tumor-directed therapeutic targets.

Class-agnostic counting and localization with feature augmentation and scale-adaptive aggregation

Compared to traditional class-specific counting, class-agnostic counting (CAC) enables the counting of arbitrary novel categories with only a few exemplars. The core issue of CAC lies in feature matching between the query image and exemplars. However, the scarce user-given exemplars make it difficult to adequately cover the diverse appearance of target objects, which poses challenges for feature matching. In this paper, we propose a Class-Agnostic Counting and Localization model (CACL) to enrich the exemplars by mining more inherent instances from the query feature. Specifically, CACL consists mainly of Self-Augment Feature Matching (SAFM) and Scale-Adaptive Spatial Aggregation (SASA). SAFM collects features of target instances frequently occurring in the query feature to augment the limited user-given exemplar, thus producing more comprehensive semantic features of the target category. To improve the robustness against scale variation, we design the SASA to enable the model to aggregate multiscale features adaptively. Compared to previous density map-based approaches, our method can locate the target objects which is more practical in real-world applications. Extensive experiments on FSC-147 suggest that our method achieves a competitive counting performance compared to state-of-the-art methods. Moreover, cross-dataset experiments demonstrate superior generalization in class-specific counting tasks.

Efficient flexible voxel-based two-stage network for 3D object detection in autonomous driving

3D object detection from the LiDAR point cloud plays an important role in autonomous driving. It is difficult to balance inference speed and detection accuracy when performing 3D point cloud object detection due to the large size of point cloud data and its unstructured storage, which makes it difficult to represent its features. To address the challenge, we propose a two-stage point cloud object detector, AFV-RCNN. In stage-1, the attention flexible voxel feature encoding layer is introduced, which utilizes flexible voxels to enhance feature encoding speed and focuses on foreground points to be detected through voxel attention. In stage-2, the multi-level and grid-based multi-scale RoI (Region of Interest) feature fusion module is designed. It directly extracts complete 3D structures from 3D region proposals and focuses on both local and global features through multi-scale partitioning. In the training stage, GHM-C Loss is applied to address the challenges associated with imbalanced target categories and the imbalance between difficult and easy samples in the classification task. We evaluate the model on the public KITTI Dataset and Waymo Open Dataset. The mAP in KITTI for 3D detection is 73.41% and inference on a single GPU reaches 30.0 fps. Compared with other state-of-the-art methods, AFV-RCNN achieves both the inference speed of a single-stage detector and the detection accuracy of a two-stage detector. It ensures higher detection accuracy while efficiently processing the point cloud.

Yarn target detection of a braiding machine based on the YOLO algorithm

Braiding machines occupy an important position in the textile industry. Aiming at the characteristics of high real-time requirements for yarn target detection in braiding machines, small yarn change curvature, and large background interference, based on the YOLOv7 algorithm model, the lightweight convolution GSConv and VoVGSCSP modules are used to replace the ELAN-H module in the YOLOv7 algorithm to reduce the complexity of the model and improve the detection speed. In order to solve the problems of confusing detection target categories and poor detection effect of targets with small curvature change, a new bounding box loss function, wise intersection over union loss, is introduced to solve the imbalance of sample quality and improve the robustness and generalization ability of the model. The ablation experiment proves that the added modules can be well fused together. The mean average precision, precision, recall, frames per second, and GFLOPs of the improved YOLOv7 are 92.2%, 93.1%, 89.7%, 123.6, and 89.9, respectively.