Using robots to collect data is an effective way to obtain information from the environment and communicate it to a static base station. Furthermore, robots have the capability to communicate with one another, potenti...
Using robots to collect data is an effective way to obtain information from the environment and communicate it to a static base station. Furthermore, robots have the capability to communicate with one another, potentially decreasing the time for data to reach the base station. We present a Mixed Integer Linear Program that reasons about discrete routing choices, continuous robot paths, and their effect on the latency of the data collection task. We analyze our formulation, discuss optimization challenges inherent to the data collection problem, and propose a factored formulation that finds optimal answers more efficiently. Our work is able to find paths that reduce latency by up to 101% compared to treating all robots independently in our tested scenarios.
Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of existing works face two problems: the low recall of RPN in unseen classes and the confusion of unseen classes with backgroun...
Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of existing works face two problems: the low recall of RPN in unseen classes and the confusion of unseen classes with background. In this paper, we present the first method that combines DETR and meta-learning to perform zero-shot object detection, named Meta-ZSDETR, where model training is formalized as an individual episode based meta-learning task. Different from Faster R-CNN based methods that firstly generate class-agnostic proposals, and then classify them with visual-semantic alignment module, Meta-ZSDETR directly predict class-specific boxes with class-specific queries and further filter them with the predicted accuracy from classification head. The model is optimized with meta-contrastive learning, which contains a regression head to generate the coordinates of class-specific boxes, a classification head to predict the accuracy of generated boxes, and a contrastive head that utilizes the proposed contrastive-reconstruction loss to further separate different classes in visual space. We conduct extensive experiments on two benchmark datasets MS COCO and PASCAL VOC. Experimental results show that our method outperforms the existing ZSD methods by a large margin.
Sentiment analysis is the task of mining the authors’ opinions about specific entities. It allows organizations to monitor different services in real time and act accordingly. Reputation is what is generally said or ...
详细信息
An intelligent reflecting surface(IRS)is proposed to enhance the physical layer security in the Rician fading channel wherein the angular direction of the eavesdropper(ED)is aligned with a legitimate user.A two-phase ...
详细信息
An intelligent reflecting surface(IRS)is proposed to enhance the physical layer security in the Rician fading channel wherein the angular direction of the eavesdropper(ED)is aligned with a legitimate user.A two-phase communication system under active attacks and passive eavesdropping is considered in this *** base station avoids direct transmission to the attacked user in the first phase,whereas other users cooperate in forwarding signals to the attacked user in the second phase,with the help of IRS and energy harvesting *** the occurrence of active attacks,an outage-constrained beamforming design problem is investigated under the statistical cascaded channel error model,which is solved by using the Bernstein-type *** average secrecy rate maximization problem for the passive eavesdropping is formulated,which is then addressed by a low-complexity *** numerical results of this study reveal that the negative effect of the ED’s channel error is larger than that of the legitimate user.
Breast carcinoma (BRCA) is a leading cause of mortality in women worldwide. Understanding the driving factors behind BRCA initiation, progression, and evolution is crucial. This study proposes a novel method to identi...
详细信息
The Cancer is the second-leading cause of death for women aged 20–59 worldwide and very few men. Compared to other cancers, breast cancer kills more people. According to ***, 13% of American women are at risk of havi...
详细信息
ISBN:
(数字)9798350350845
ISBN:
(纸本)9798350350852
The Cancer is the second-leading cause of death for women aged 20–59 worldwide and very few men. Compared to other cancers, breast cancer kills more people. According to ***, 13% of American women are at risk of having this cancer, and approximately 80% of them advance, which decreases recovery and treatment success. Deep learning methods for BC detection have been successful thanks to AI. This improves early diagnosis, increasing patient survival. This publication provides a detailed review of the deep learning-based BC diagnosis literature. It aims to help practitioners and researchers understand this domain's issues and trends. This article reviews looks at deep learning methods for breast cancer detection. Next, we examine and synthesize the latest AI-based breast cancer diagnostic studies using multiple breast DL modalities. We also provide a complete overview of breast-cancer imaging datasets, emphasizing their importance in AI-driven algorithms and deep learning model training. The investigation found that the CNN is the most widely used and accurate BC diagnosis model. Also, accuracy measures are the key way to evaluate such models. To provide a complete reference for breast cancer imaging researchers from the details of the researchers works. we can say that The performance of breast cancer detection is influenced by three factors: (1) the efficacy of the CAD system, (2) the characteristics of the population under analysis, and (3) the proficiency of the radiologists utilizing the system. CAD can assist in detecting microcalcifications, which may serve as potential indicators of
Fourier neural operator(FNO)model is developed for large eddy simulation(LES)of three-dimensional(3D)*** fields of isotropic turbulence generated by direct numerical simulation(DNS)are used for training the FNO model ...
详细信息
Fourier neural operator(FNO)model is developed for large eddy simulation(LES)of three-dimensional(3D)*** fields of isotropic turbulence generated by direct numerical simulation(DNS)are used for training the FNO model to predict the filtered velocity field at a given *** input of the FNO model is the filtered velocity fields at the previous several time-nodes with large time *** the a posteriori study of LES,the FNO model performs better than the dynamic Smagorinsky model(DSM)and the dynamic mixed model(DMM)in the prediction of the velocity spectrum,probability density functions(PDFs)of vorticity and velocity increments,and the instantaneous flow ***,the proposed model can significantly reduce the computational cost,and can be well generalized to LES of turbulence at higher Taylor-Reynolds numbers.
Semantic Change Detection (SCD) is recognized as both a crucial and challenging task in the field of image analysis. Traditional methods for SCD have predominantly relied on the comparison of image pairs. However, thi...
详细信息
We demonstrate optical initialization and readout of electron spins of a single T center in a silicon nanophotonic waveguide. We present progress for coherent control of the waveguide single spin for silicon spin-phot...
详细信息
Predicting pedestrian behavior is a crucial task for intelligent driving systems. Accurate predictions require a deep understanding of various contextual elements that could impact the way pedestrians behave. To addre...
Predicting pedestrian behavior is a crucial task for intelligent driving systems. Accurate predictions require a deep understanding of various contextual elements that could impact the way pedestrians behave. To address this challenge, we propose a novel framework that relies on different data modalities to predict future trajectories and crossing actions of pedestrians from an egocentric perspective. Specifically, our model utilizes a cross-modal Transformer architecture to capture dependencies between different data types. The output of the Transformer is augmented with representations of interactions between pedestrians and other traffic agents conditioned on the pedestrian and ego-vehicle dynamics that are generated via a semantic attentive interaction module. Lastly, the context encodings are fed into a multi-stream decoder framework using a gated-shared network. We evaluate our algorithm on public pedestrian behavior benchmarks, PIE and JAAD, and show that our model improves state-of-the-art in trajectory and action prediction by up to 22% and 13% respectively on various metrics. The advantages of the proposed components are investigated via extensive ablation studies.
暂无评论