Recognizing emotions in dialogues is vital for effective human-computer interaction, yet remains a challenging task in Natural Language Processing (NLP). Previous studies in Emotion Recognition in Conversation (ERC) h...
详细信息
An expansion of Internet of Things (IoTs) has led to significant challenges in wireless data harvesting, dissemination, and energy management due to the massive volumes of data generated by IoT devices. These challeng...
详细信息
作者：
Yu, DawenCheng, HaoFuzhou University
Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education The Academy of Digital China Fuzhou350108 China Wuhan University
School of Remote Sensing and Information Engineering Wuhan430079 China
Bird’s-eye-view (BEV) building mapping from remote sensing images is a studying hotspot with broad applications. In recent years, deep learning (DL) has significantly advanced the development of automatic building ex...
详细信息
Learning-based multi-view depth estimation approaches have achieved remarkable success, primarily by accurately matching correspondences between the reference and source views to construct distinguishable cost volume....
Learning-based multi-view depth estimation approaches have achieved remarkable success, primarily by accurately matching correspondences between the reference and source views to construct distinguishable cost volume. Existing methods using plane sweeping with ordered and preset sampling fail to make the initial cost volume discriminative. Additionally, insufficient cost aggregation exacerbates the challenges in achieving accurate depth estimation within low-texture regions and object boundaries. In this paper, we propose a novel multi-view depth estimation network, termed $$\text {SP-A}\text {I}^{2}$$ (sparse prior guided cost construction and adaptive intra and inter scale cost aggregation). Specifically, we propose a sparse prior guided strategy for dynamic and nonuniform sampling across a wide depth range to construct the cost volume, which introduces reasonable and fine-grained spatial partitioning to refine the depth with higher accuracy. Furthermore, to improve the depth quality under challenging regions, a novel adaptive intra and inter scale cost aggregation ( $$\text {A}\text {I}^{2}$$ -SA) module is proposed to enhance the power of feature representation. The proposed $${\hbox {SP-A}}\text {I}^{2}$$ is trained end-to-end and experimental results demonstrate that our method achieves state-of-the-art results on various benchmark datasets.
We introduce a hierarchy of tests satisfied by any probability distribution P that represents the quantum correlations generated in prepare-and-measure (P&M) quantum multichain-shaped networks, assuming only the i...
详细信息
We introduce a hierarchy of tests satisfied by any probability distribution P that represents the quantum correlations generated in prepare-and-measure (P&M) quantum multichain-shaped networks, assuming only the inner-product information of prepared states. The P&M quantum multichain-shaped networks involve multiple measurement parties, with each measurement party potentially having multiple sequential receivers. We adapt the original Navascués, Pironio, and Acín (NPA) hierarchy by incorporating a finite number of linear and positive semi-definite constraints to characterize the quantum correlations in P&M quantum multichain-shaped networks. These constraints in each hierarchy are derived from sequential measurements and the inner-product matrix of prepared states. The adapted NPA hierarchy is further applied to tackle some quantum information tasks, including sequential quantum random access codes (QRACs) and semi-device-independent randomness certification. First, we derive the optimal trade-off between the two sequential receivers in the 2→1 sequential QRACs, and investigate randomness certification in its double violation region. Second, considering the presence of an eavesdropper in actual communication, we show how much local and global randomness can be certified using the optimal trade-off of 2→1 sequential QRACs. We also quantify the amount of local and global randomness that can be certified from the complete set of probabilities generated by the two sequential receivers. Our conclusion is that utilizing the full set of probabilities certifies more randomness than relying solely on the optimal trade-off relationship.
The development of effective drug therapies is a complex and multifaceted problem involving various biological, chemical, and computational challenges. Traditional drug development methods are often time-consuming and...
详细信息
Genetic algorithms (GAs) are a powerful class of optimization techniques inspired by the principles of natural selection and genetics. One of the theoretical cornerstones of GAs is schema theory, which provides a fram...
详细信息
Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) and data collection (DC) have been popular research issues. Different from existing works that consider MEC and DC scenarios separately, this paper in...
详细信息
An expansion of Internet of Things (IoTs) has led to significant challenges in wireless data harvesting, dissemination, and energy management due to the massive volumes of data generated by IoT devices. These challeng...
详细信息
Graph-based Cognitive Diagnosis (CD) has attracted much research interest due to its strong ability on inferring students' proficiency levels on knowledge concepts. While graph-based CD models have demonstrated re...
详细信息
ISBN:
(纸本)9798400712456
Graph-based Cognitive Diagnosis (CD) has attracted much research interest due to its strong ability on inferring students' proficiency levels on knowledge concepts. While graph-based CD models have demonstrated remarkable performance, we contend that they still cannot achieve optimal performance due to the neglect of edge heterogeneity and uncertainty. Edges involve both correct and incorrect response logs, indicating heterogeneity. Meanwhile, a response log can have uncertain semantic meanings, e.g., a correct log can indicate true mastery or fortunate guessing, and a wrong log can indicate a lack of understanding or a careless mistake. In this paper, we propose an Informative Semantic-aware Graph-based Cognitive Diagnosis model (ISG-CD), which focuses on how to utilize the heterogeneous graph in CD and minimize effects of uncertain edges. Specifically, to explore heterogeneity, we propose a semantic-aware graph neural networks based CD model. To minimize effects of edge uncertainty, we propose an Informative Edge Differentiation layer from an information bottleneck perspective, which suggests keeping a minimal yet sufficient reliable graph for CD in an unsupervised way. We formulate this process as maximizing mutual information between the reliable graph and response logs, while minimizing mutual information between the reliable graph and the original graph. After that, we prove that mutual information maximization can be theoretically converted to the classic binary cross entropy loss function, while minimizing mutual information can be realized by the Hilbert-Schmidt Independence ***, we adopt an alternating training strategy for optimizing learnable parameters of both the semantic-aware graph neural networks based CD model and the edge differentiation layer. Extensive experiments on three real-world datasets have demonstrated the effectiveness of ISG-CD.
暂无评论