检索结果-内蒙古大学图书馆

9th Symposium on Novel Photoelectronic Detection Technology and applications

作者： Liu, Jiaqing Li, Yi Liang, Dong Xu, Guoming Zhou, Pucheng Ma, Jian School of Internet Anhui University Hefei China National Engineering Research Center for Agro-Ecological Big Data Analysis & Application Anhui University Hefei China Anhui Provincial Key Laboratory of Polarized Light Imaging Detection Hefei China School of Electrical and Electronics Engineering Anhui Wenda University of Information Engineering Hefei China

ISBN: (纸本)9781510664432

Due to the limitation of the detector, the spatial resolution of the polarization image obtained by space-modulated full-polarization computed imaging is low. In general, there are a lot of valuable high-frequency components in low resolution space, but it is difficult to reconstruct high frequency information by deep learning method. Through the research of the previous super-resolution reconstruction method based on deep learning, it is found that it is difficult to obtain better lifting effect only by stacking residual blocks to build a deeper network. A polarization imaging bi-attention recursive residual network super-resolution reconstruction method is proposed. In the network structure, bi-attention recursive residual group is used as the deep feature extraction module, and the bi-attention module contained in this module is used to adaptively learn image features of different channels and different transformation Spaces in the deep network. In order to provide the concentrated learning efficiency of high-frequency information, jump connections are introduced into the network structure, and the shallow feature extraction and reconstruction of images are completed by a convolution layer and a sub-pixel convolution algorithm respectively. The experimental verification is carried out under the actual imaging system and simulation data, and compared with other methods in terms of visual effect and quantitative results. Experimental results verify that the proposed method can effectively reconstruct the contour structure and texture details of the detection target in subjective image quality, and is superior to the comparison method in objective evaluation index. © 2023 SPIE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Winning the CVPR'2022 AQTC Challenge: A Two-stage Function-centric Approach

arXiv

引用

arXiv 2022年

作者： Wu, Shiwei He, Weidong Xu, Tong Wang, Hao Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence University of Science and Technology of China China

Affordance-centric Question-driven Task Completion for Egocentric Assistant (AQTC) is a novel task which helps AI assistant learn from instructional videos and scripts and guide the user step-by-step. In this paper, we deal with the AQTC via a two-stage Function-centric approach, which consists of Question2Function Module to ground the question with the related function and Function2Answer Module to predict the action based on the historical steps. We evaluated several possible solutions in each module and obtained significant gains compared to the given baselines. Our code is available at https://***/starsholic/LOVEU-CVPR22-AQTC. © 2022, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment

arXiv

引用

arXiv 2024年

作者： Wang, Fei Liu, Haoyu Bi, Haoyang Shen, Xiangzhuang Zhu, Renyu Wu, Runze Lin, Minmin Lv, Tangjie Fan, Changjie Liu, Qi Huang, Zhenya Chen, Enhong School of Computer Science and Technology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China NetEase Inc Hangzhou China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China

For the purpose of efficient and cost-effective large-scale data labeling, crowdsourcing is increasingly being utilized. To guarantee the quality of data labeling, multiple annotations need to be collected for each data sample, and truth inference algorithms have been developed to accurately infer the true labels. Despite previous studies having released public datasets to evaluate the efficacy of truth inference algorithms, these have typically focused on a single type of crowdsourcing task and neglected the temporal information associated with workers’ annotation activities. These limitations significantly restrict the practical applicability of these algorithms, particularly in the context of long-term and online truth inference. In this paper, we introduce a substantial crowdsourcing annotation dataset collected from a real-world crowdsourcing platform. This dataset comprises approximately two thousand workers, one million tasks, and six million annotations. The data was gathered over a period of approximately six months from various types of tasks, and the timestamps of each annotation were preserved. We analyze the characteristics of the dataset from multiple perspectives and evaluate the effectiveness of several representative truth inference algorithms on this dataset. We anticipate that this dataset will stimulate future research on tracking workers’ abilities over time in relation to different types of tasks, as well as enhancing online truth inference. Copyright © 2024, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

FormerTime: Hierarchical Multi-Scale Representations for Multivariate Time Series Classification

arXiv

引用

arXiv 2023年

作者： Cheng, Mingyue Liu, Qi Liu, Zhiding Li, Zhi Luo, Yucong Chen, Enhong Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China Shenzhen International Graduate School Tsinghua University Shenzhen China

Deep learning-based algorithms, e.g., convolutional networks, have significantly facilitated multivariate time series classification (MTSC) task. Nevertheless, they suffer from the limitation in modeling long-range dependence due to the nature of convolution operations. Recent advancements have shown the potential of transformers to capture long-range dependence. However, it would incur severe issues, such as fixed scale representations, temporal-invariant and quadratic time complexity, with transformers directly applicable to the MTSC task because of the distinct properties of time series data. To tackle these issues, we propose FormerTime, an hierarchical representation model for improving the classification capacity for the MTSC task. In the proposed FormerTime, we employ a hierarchical network architecture to perform multi-scale feature maps. Besides, a novel transformer encoder is further designed, in which an efficient temporal reduction attention layer and a well-informed contextual positional encoding generating strategy are developed. To sum up, FormerTime exhibits three aspects of merits: (1) learning hierarchical multi-scale representations from time series data, (2) inheriting the strength of both transformers and convolutional networks, and (3) tacking the efficiency challenges incurred by the self-attention mechanism. Extensive experiments performed on 10 publicly available datasets from UEA archive verify the superiorities of the FormerTime compared to previous competitive baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge Learning

arXiv

引用

arXiv 2023年

作者： Liu, Jiayu Huang, Zhenya Zhai, Chengxiang Liu, Qi Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China University of Illinois at Urbana-Champaign United States

Mathematical reasoning is one of the crucial abilities of general artificial intelligence, which requires machines to master mathematical logic and knowledge from solving problems. However, existing approaches are not transparent (thus not interpretable) in terms of what knowledge has been learned and applied in the reasoning process. In this paper, we propose a general Learning by Applying (LeAp) framework to enhance existing models (backbones) in a principled way by explicit knowledge learning. In LeAp, we perform knowledge learning in a novel problem-knowledge-expression paradigm, with a Knowledge Encoder to acquire knowledge from problem data and a Knowledge Decoder to apply knowledge for expression reasoning. The learned mathematical knowledge, including word-word relations and word-operator relations, forms an explicit knowledge graph, which bridges the knowledge "learning" and "applying" organically. Moreover, for problem solving, we design a semantics-enhanced module and a reasoning-enhanced module that apply knowledge to improve the problem comprehension and symbol reasoning abilities of any backbone, respectively. We theoretically prove the superiority of LeAp's autonomous learning mechanism. Experiments on three real-world datasets show that LeAp improves all backbones' performances, learns accurate knowledge, and achieves a more interpretable reasoning process. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking

arXiv

引用

arXiv 2023年

作者： Yu, Yang Liu, Qi Zhang, Kai Zhang, Yuren Song, Chao Hou, Min Yuan, Yuqing Ye, Zhihao Zhang, Zaixi Yu, Sanshi Lei Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China OPPO Research Institute China Hefei University of Technology China

User modeling, which aims to capture users' characteristics or interests, heavily relies on task-specific labeled data and suffers from the data sparsity issue. Several recent studies tackled this problem by pre-training the user model on massive user behavior sequences with a contrastive learning task. Generally, these methods assume different views of the same behavior sequence constructed via data augmentation are semantically consistent, i.e., reflecting similar characteristics or interests of the user, and thus maximizing their agreement in the feature space. However, due to the diverse interests and heavy noise in user behaviors, existing augmentation methods tend to lose certain characteristics of the user or introduce noisy behaviors. Thus, forcing the user model to directly maximize the similarity between the augmented views may result in a negative transfer. To this end, we propose to replace the contrastive learning task with a new pretext task: Augmentation-Adaptive Self-Supervised Ranking (AdaptSSR), which alleviates the requirement of semantic consistency between the augmented views while pre-training a discriminative user model. Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users. We further employ an in-batch hard negative sampling strategy to facilitate model training. Moreover, considering the distinct impacts of data augmentation on different behavior sequences, we design an augmentation-adaptive fusion mechanism to automatically adjust the similarity order constraint applied to each sample based on the estimated similarity between the augmented views. Extensive experiments on both public and industrial datasets with six downstream tasks verify the effectiveness of AdaptSSR. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Continuous Control Perspective for Reinforcement-Learning-based Sequential Recommendation

arXiv

引用

arXiv 2024年

作者： Wang, Jun Wu, Likang Liu, Qi Yang, Yu School of Data Science City University of Hong Kong Kowloon Hong Kong College of Management and Economics Tianjin University Tianjin China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Anhui Hefei China State Key Laboratory of Cognitive Intelligence Anhui Hefei China

Sequential recommendation, where user preference is dynamically inferred from sequential historical behaviors, is a critical task in recommender systems (RSs). To further optimize long-term user engagement, offline reinforcement-learning-based RSs have become a mainstream technique as they provide an additional advantage in avoiding global explorations that may harm online users’ experiences. However, previous studies mainly focus on discrete action and policy spaces, which might have difficulties in handling dramatically growing items efficiently. To mitigate this issue, in this paper, we aim to design an algorithmic framework applicable to continuous policies. To facilitate the control in the low-dimensional but dense user preference space, we propose an Efficient Continuous Control framework (ECoC). Based on a statistically tested assumption, we first propose the novel unified action representation abstracted from normalized user and item spaces. Then, we develop the corresponding policy evaluation and policy improvement procedures. During this process, strategic exploration and directional control in terms of unified actions are carefully designed and crucial to final recommendation decisions. Moreover, beneficial from unified actions, the conservatism regularization for policies and value functions are combined and perfectly compatible with the continuous framework. The resulting dual regularization ensures the successful offline training of RL-based recommendation policies. Finally, we conduct extensive experiments to validate the effectiveness of our framework. The results show that compared to the discrete baselines, our ECoC is trained far more efficiently. Meanwhile, the final policies outperform baselines in both capturing the offline data and gaining long-term rewards. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Target Hierarchy-Guided Knowledge Tracing: Fine-Grained Knowledge State Modeling

SSRN

引用

SSRN 2024年

作者： Sun, Xinjie Zhang, Kai Shen, Shuanghong Wang, Fei Guo, Yuxiang Liu, Qi School of Computer Science and Technology University of Science and Technology of China Hefei China School of Data Science University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence Hefei China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hefei China

Knowledge Tracing (KT) focuses on modeling the exercise process of students, assessing their knowledge state changes during the exercise process, and further providing targeted guidance for teaching and learning. Current KT models have made significant progress by utilizing deep learning technologies to model relevant attributes of the questions. However, in current knowledge tracing strategies, we have yet to exhaustively explore how to precisely evaluate the hierarchies of students’ knowledge mastery (encompassing Remembering, Understanding, Applying, Analyzing, Evaluating, and Creating) to better discern their current target hierarchy. To address the limitations of the KT model in accurately identifying and positioning target hierarchy, our research focuses on two key areas: first, we dynamically track students’ target hierarchies by evaluating their feedback on questions at different hierarchies;second, we assess their actual question-solving abilities within these target hierarchies, thereby optimizing our evaluation of their knowledge status. Based on these insights, we propose the Target Hierarchy-guided Knowledge Tracing (THKT) model. In this model, we first incorporate the identification of question hierarchy into the model representation. Then, to avoid homogenization of the target hierarchy, we dynamically track the appropriate hierarchy for students based on their varying feedback to questions of the same hierarchy, thereby pinpointing their learning target hierarchies. Simultaneously, we develop a KCs applied ability learning module that works in conjunction with the target hierarchies to generate interpretable prediction results. The proposed THKT model has been tested and evaluated using three public, real-world educational datasets. The findings clearly demonstrate that our approach shines in the realm of KT prediction tasks, providing significantly interpretability. For broader research, we plan to provide the source code at: https://***/xinj

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Towards a Holistic Understanding of Mathematical Questions with Contrastive Pre-training

arXiv

引用

arXiv 2023年

作者： Ning, Yuting Huang, Zhenya Lin, Xin Chen, Enhong Tong, Shiwei Gong, Zheng Wang, Shijin Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China iFLYTEK Co. Ltd China

Understanding mathematical questions effectively is a crucial task, which can benefit many applications, such as difficulty estimation. Researchers have drawn much attention to designing pre-training models for question representations due to the scarcity of human annotations (e.g., labeling difficulty). However, unlike general free-format texts (e.g., user comments), mathematical questions are generally designed with explicit purposes and mathematical logic, and usually consist of more complex content, such as formulas, and related mathematical knowledge (e.g., Function). Therefore, the problem of holistically representing mathematical questions remains underexplored. To this end, in this paper, we propose a novel contrastive pre-training approach for mathematical question representations, namely QuesCo, which attempts to bring questions with more similar purposes closer. Specifically, we first design two-level question augmentations, including content-level and structure-level, which generate literally diverse question pairs with similar purposes. Then, to fully exploit hierarchical information of knowledge concepts, we propose a knowledge hierarchy-aware rank strategy (KHAR), which ranks the similarities between questions in a fine-grained manner. Next, we adopt a ranking contrastive learning task to optimize our model based on the augmented and ranked questions. We conduct extensive experiments on two real-world mathematical datasets. The experimental results demonstrate the effectiveness of our model. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

ShapeWordNet: An Interpretable Shapelet Neural Network for Physiological Signal Classification

arXiv

引用

arXiv 2023年

作者： He, Wenqiang Cheng, Mingyue Liu, Qi Li, Zhi Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hefei China Shenzhen International Graduate School Tsinghua University Shenzhen China

Physiological signals are high-dimensional time series of great practical values in medical and healthcare applications. However, previous works on its classification fail to obtain promising results due to the intractable data characteristics and the severe label sparsity issues. In this paper, we try to address these challenges by proposing a more effective and interpretable scheme tailored for the physiological signal classification task. Specifically, we exploit the time series shapelets to extract prominent local patterns and perform interpretable sequence discretization to distill the whole-series information. By doing so, the long and continuous raw signals are compressed into short and discrete token sequences, where both local patterns and global contexts are well preserved. Moreover, to alleviate the label sparsity issue, a multi-scale transformation strategy is adaptively designed to augment data and a cross-scale contrastive learning mechanism is accordingly devised to guide the model training. We name our method as ShapeWordNet and conduct extensive experiments on three real-world datasets to investigate its effectiveness. Comparative results show that our proposed scheme remarkably outperforms four categories of cutting-edge approaches. Visualization analysis further witnesses the good interpretability of the sequence discretization idea based on shapelets. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：