Arbitrary-scale super-resolution (ASSR) aims to learn a single model for image super-resolution at arbitrary magnifying scales. Existing ASSR networks typically comprise an off-the-shelf scale-agnostic feature extract...
network monitoring and measurement is an important part of realizing the network digital twin. However, it introduces the problem of high cost when obtaining the status data of physical networks. Therefore, to efficie...
详细信息
A Temporal Knowledge Graph (TKG) is a sequence of KGs with respective timestamps, which adopts quadruples in the form of (subject, relation, object, timestamp) to describe dynamic facts. TKG reasoning has facilitated ...
详细信息
In 2020,the COVID-19 pandemic has brought“digital contact tracing”to the forefront of public *** the context of COVID-19,technology has offered public health investigators a new capability for locating infected indi...
详细信息
In 2020,the COVID-19 pandemic has brought“digital contact tracing”to the forefront of public *** the context of COVID-19,technology has offered public health investigators a new capability for locating infected individuals,i.e.,digital contact *** this technology,investigators were able to track the location of patients without relying on their memory,which alleviated disease surveillance *** practical application of this technology is known as“Exposure Notification.”Developers were able to complete the creation and operation of this digital contact tracing system within a few weeks,and they made the code open-source to ensure that Apple and Android users worldwide could utilize it.
A Temporal Knowledge Graph (TKG) is a sequence of KGs corresponding to different timestamps. TKG reasoning aims to predict potential facts in the future given the historical KG sequences. One key of this task is to mi...
详细信息
Emerging non-volatile devices have shown great potential in computing in-memory (CIM). This work proposes a logic design method based on the complementary resistance switching (CRS) structure, which is connected by tw...
详细信息
Graph contrastive learning (GCL) emerges as the most representative approach for graph representation learning, which leverages the principle of maximizing mutual information (InfoMax) to learn node representations ap...
详细信息
Deep convolutional neural networks (DCNs) have recently experienced rapid development in the direction of lightweight and edge deployment. However, accelerators for DCNs face challenges in balancing computational and ...
详细信息
Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspectiv...
Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24.
Due to over-abundant information on the Web, information filtering becomes a key task for online users to obtain relevant suggestions and how to extract the most related item is always a key topic for researchers in v...
详细信息
Due to over-abundant information on the Web, information filtering becomes a key task for online users to obtain relevant suggestions and how to extract the most related item is always a key topic for researchers in various fields. In this paper, we adopt tools used to analyze complex networks to evaluate user reputation and item quality. In our proposed Accumulative Time Based Ranking (ATR) algorithm, we take into account the growth record of the network to identify the evolution of the reputation of users and the quality of items, by incorporating two behavior weighting factors which can capture the hidden facts on reputation and quality dynamics for each user and item respectively. Our proposed ATR algorithm mainly combines the iterative approach to rank user reputation and item quality with temporal dependence compared with other reputation evaluation methods. We show that our algorithm outperforms other benchmark ranking algorithms in terms of precision and robustness on empirical datasets from various online retailers and the citation datasets among research publications. Therefore, our proposed method has the capability to effectively evaluate user reputation and item quality.
暂无评论