检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xu, Ningyu Zhang, Qi Du, Chao Luo, Qiang Qiu, Xipeng Huang, Xuanjing Zhang, Menghan School of Computer Science Fudan University Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Research Institute of Intelligent Complex Systems Fudan University Shanghai China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Shanghai China Ministry of Education Key Laboratory of Contemporary Anthropology Fudan University Shanghai China

People acquire concepts through rich physical and social experiences and use them to understand the world. In contrast, large language models (LLMs), trained exclusively through next-token prediction over language data, exhibit remarkably human-like behaviors. Are these models developing concepts akin to humans, and if so, how are such concepts represented and organized? To address these questions, we reframed the classic reverse dictionary task to simulate human concept inference in context and investigated the emergence of human-like conceptual representations within LLMs. Our results demonstrate that LLMs can flexibly derive concepts from linguistic descriptions in relation to contextual cues about other concepts. The derived representations converged towards a shared, context-independent structure that effectively predicted human behavior across key psychological phenomena, including computation of similarities, categories and semantic scales. Moreover, these representations aligned well with neural activity patterns in the human brain, even in response to visual rather than linguistic stimuli, providing evidence for biological plausibility. These findings establish that structured, human-like conceptual representations can naturally emerge from language prediction without real-world grounding. More broadly, our work positions LLMs as promising computational tools for understanding complex human cognition and paves the way for better alignment between artificial and human intelligence. Copyright © 2025, 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

Self-distillation Augmented Masked Autoencoders for Histopathological Image Classification

arXiv

引用

arXiv 2022年

作者： Luo, Yang Chen, Zhineng Zhou, Shengtian Gao, Xieping Fudan University Shanghai China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University China

Self-supervised learning (SSL) has drawn increasing attention in histopathological image analysis in recent years. Compared to contrastive learning which is troubled with the false negative problem, i.e., semantically similar images are selected as negative samples, masked autoencoders (MAE) building SSL from a generative paradigm is probably a more appropriate pre-training. In this paper, we introduce MAE and verify the effect of visible patches for histopathological image understanding. Moreover, a novel SD-MAE model is proposed to enable a self-distillation augmented MAE. Besides the reconstruction loss on masked image patches, SD-MAE further imposes the self-distillation loss on visible patches to enhance the representational capacity of the encoder located shallow layer. We apply SD-MAE to histopathological image classification, cell segmentation and object detection. Experiments demonstrate that SD-MAE shows highly competitive performance when compared with other SSL methods in these tasks. © 2022, CC BY-NC-SA.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Yolov9-Spe: A Novel Deep Learning Method For Classroom Student Behavior Detection

SSRN

引用

SSRN 2024年

作者： Liu, Junxiu Wu, Fengxiang Lu, Baoshan Qin, Sheng Fu, Qiang Luo, Yuling Guangxi Key Lab of Brain-inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin541004 China Guangxi Wireless Broadband Communication and Signal Processing Key Laboratory Guilin University of Electronic Technology Guilin541004 China

Deep learning can significantly enhance student behavior detection in classrooms. However, challenges such as small target recognition, blurry data, occlusion, and multi-scale detection persist. To address these, we propose YOLOv9-SPE, an improved model based on YOLOv9, incorporating Space-to-Depth Convolution (SPD-Conv), Partial Convolution (PConv), and an Efficient Multi-Scale Attention (EMA) Module. SPD-Conv enhances small target recognition and improves feature extraction for blurry data, while PConv, adapted from FasterNet, addresses occlusion issues. EMA is integrated to handle multi-scale targets in classroom student behavior detection. Experimental results on a student behavior dataset show that YOLOv9-SPE achieves a 2.1% improvement in mean average precision over the original YOLOv9. These enhancements provide a more accurate and efficient method for monitoring and analyzing student behavior in educational settings. © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Overlapping Local Community Detection Algorithm Based on Node Transitivity and Modularity Density 15th

An Overlapping Local Community Detection Algorithm Based on ...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Huang, Xintong Wu, Ling Guo, Kun College of Mathematics and Computer Sciences Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350116 China

ISBN: (纸本)9789811625398

The local community detection (LCD) method can discover the local community structure in which the seed node is located. Compared with global community detection, local community detection is characterized by its low cost and high efficiency. However, most existing LCD methods only return a non-overlapping community. Individuals in the real world may participate in multiple communities, which can only be discovered by using overlapping local community detection methods. In this study, an overlapping local community detection algorithm based on modularity and node transitivity. First, the scope and structure information of the overlapping communities are obtained according to the node transitivity. Second, NMF is used to obtain the number of overlapping communities. Finally, the local modularity density based on edge weights is used to refine the detected local communities. The experimental results validate the high performance of our method to the other method in comparison. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

ONE2SET + Large Language Model: Best Partners for keyphrase Generation

arXiv

引用

arXiv 2024年

作者： Shao, Liangying Zhang, Liang Peng, Minlong Ma, Guoqi Yue, Hao Sun, Mingming Su, Jinsong School of Informatics Xiamen University China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Xiamen University Ministry of Culture and Tourism China Cognitive Computing Lab Baidu Research China Beijing Institute of Mathematical Sciences and Applications China

keyphrase generation (KPG) aims to automatically generate a collection of phrases representing the core concepts of a given document. The dominant paradigms in KPG include ONE2SEQ and ONE2SET. Recently, there has been increasing interest in applying large language models (LLMs) to KPG. Our preliminary experiments reveal that it is challenging for a single model to excel in both recall and precision. Further analysis shows that: 1) the ONE2SET paradigm owns the advantage of high recall, but suffers from improper assignments of supervision signals during training;2) LLMs are powerful in keyphrase selection, but existing selection methods often make redundant selections. Given these observations, we introduce a generate-then-select framework decomposing KPG into two steps, where we adopt a ONE2SET-based model as generator to produce candidates and then use an LLM as selector to select keyphrases from these candidates. Particularly, we make two important improvements on our generator and selector: 1) we design an Optimal Transport-based assignment strategy to address the above improper assignments;2) we model the keyphrase selection as a sequence labeling task to alleviate redundant selections. Experimental results on multiple benchmark datasets show that our framework significantly surpasses state-ofthe- art models, especially in absent keyphrase prediction. We release our code at https: //***/DeepLearnXMU/KPG-SetLLM. Copyright © 2024, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach

arXiv

引用

arXiv 2024年

作者： Zhu, Yabin Wang, Qianwu Li, Chenglong Tang, Jin Huang, Zhixiang The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University School of Public Safety and Emergency Management Anhui University of Science and Technology Hefei231131 China School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Security Artificial Intelligence School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Center for Big Data and Population Health of IHM China

The complementary benefits from visible and thermal infrared data are widely utilized in various computer vision task, such as visual tracking, semantic segmentation and object detection, but rarely explored in Multiple Object Tracking (MOT). In this work, we contribute a large-scale Visible-Thermal video benchmark for MOT, called VT-MOT. VT-MOT has the following main advantages. 1) The data is large scale and high diversity. VT-MOT includes 582 video sequence pairs, 401k frame pairs from surveillance, drone, and handheld platforms. 2) The cross-modal alignment is highly accurate. We invite several professionals to perform both spatial and temporal alignment frame by frame. 3) The annotation is dense and high-quality. VT-MOT has 3.99 million annotation boxes annotated and double-checked by professionals, including heavy occlusion and object re-acquisition (object disappear and reappear) challenges. To provide a strong baseline, we design a simple yet effective tracking framework, which effectively fuses temporal information and complementary information of two modalities in a progressive manner, for robust visible-thermal MOT. A comprehensive experiment are conducted on VT-MOT and the results prove the superiority and effectiveness of the proposed method compared with state-of-the-art methods. From the evaluation results and analysis, we specify several potential future directions for visible-thermal MOT. The project is released in https://***/wqw123wqw/PFTrack. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Distributed Storage Middleware Based on HBase and Redis 15th

A Distributed Storage Middleware Based on HBase and Redis

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Xu, Lingling Chen, Yuzhong Guo, Kun College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789811625398

In the era of big data, traditional relational databases face challenges in massive data storage. HBase is a non-relational database based on column storage which is used widely for big data storage. The writing performance of HBase is high, but the unbalanced load caused by its uneven data storage strategy is the bottleneck of its reading performance. HBase needs to access disks to get query results. Therefore, the efficiency of disk access has a great impact on the query performance of HBase. In view of the above problems, this paper proposes a storage middleware which utilizes HBase for load balancing and Redis for memory caching. Specifically, we improve HBase’s original load balancing algorithm for Regions and RegionServers and customize a Redis cache eviction algorithm according to the data’s query and update frequency. Furthermore, the coprocessor of HBase is used to synchronize data between HBase and Redis. Experiments on synthetic datasets show that the proposed storage middleware achieves better writing and reading performance than HBase. The load balancing algorithm employed in the middleware is better than HBase's original algorithm. The hit rate of the customized cache eviction algorithm is also higher than that of the LRU algorithm. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translation

arXiv

引用

arXiv 2022年

作者： Shao, Chenze Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Non-autoregressive translation (NAT) models are typically trained with the cross-entropy loss, which forces the model outputs to be aligned verbatim with the target sentence and will highly penalize small shifts in word positions. Latent alignment models relax the explicit alignment by marginalizing out all monotonic latent alignments with the CTC loss. However, they cannot handle non-monotonic alignments, which is non-negligible as there is typically global word reordering in machine translation. In this work, we explore non-monotonic latent alignments for NAT. We extend the alignment space to non-monotonic alignments to allow for the global word reordering and further consider all alignments that overlap with the target sentence. We non-monotonically match the alignments to the target sentence and train the latent alignment model to maximize the F1 score of non-monotonic matching. Extensive experiments on major WMT benchmarks show that our method substantially improves the translation performance of CTC-based models. Our best model achieves 30.06 BLEU on WMT14 En-De with only one-iteration decoding, closing the gap between non-autoregressive and autoregressive models.2 Copyright © 2022, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of KMeans Based on Unified Batch and Streaming processing 15th

The Design and Implementation of KMeans Based on Unified Bat...

引用

15th CCF Conference on Computer Supported Cooperative Work and Social computing, Chinese CSCW 2020

作者： Chen, Hao Guo, Kun Chen, Yuzhong Guo, Hong College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789811625398

Clustering algorithms aim at gathering similar data points from a dataset in an unsupervised manner. Although the batch clustering algorithms have relatively high accuracy, they cannot make use of the dynamic clustering results efficiently. The requirement of using the whole dataset in calculation results in the problems of resource waste and high time cost. On the contrary, incremental clustering only needs to update the varied part of a model upon the arrival of new data, which makes it unnecessary to recluster the whole data all the time. The feature is very suitable for the streaming data process, but it decreases the accuracy of the algorithms and cannot satisfy the low latency requirement of real-time data processing. In response to this problem, the paper proposes a novel unified batch and streaming clustering model (UBSCM) based on streaming computation, which includes a streaming cluster feature updating mechanism (SCFUM). The Flink framework is used to implement a new streaming KMeans algorithm based on UBSCM (KMeansUBSP). The experiments on the real-world datasets validate that the new streaming KMeans algorithm is effective in clustering the batch and streaming data in a unified manner. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Real-Time Action Detection Method based on Multi-Scale Spatiotemporal Feature

Real-Time Action Detection Method based on Multi-Scale Spati...

引用

Image processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Xin Miao Xiao Ke Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou Fujian China

ISBN: (纸本)9781665464697

Spatiotemporal action detection relies on the learning of video spatial and temporal information. The current state-of-the-art convolutional neural network-based action detectors have achieved remarkable results using 2D CNN or 3D CNN architectures. However, due to the complexity of the network structure and spatiotemporal information perception, these methods are usually used in a non-real-time, offline manner. The main challenge of spatiotemporal action detection is to design an effective detection network architecture and effectively perceive the fused spatiotemporal features. Aiming at the above problems, our paper proposes a real-time action detection method based on multi-scale spatiotemporal feature. Aiming at the problem that only 2D or 3D backbone network cannot effectively model spatiotemporal features, we extract spatiotemporal features by multi-branch feature extraction networks respectively. For the lack of descriptiveness of single-scale spatiotemporal features, a multi-scale spatiotemporal feature-aware attention network is proposed to learn long-term temporal dependencies and spatial context information. And the fusion between temporal and spatial features is guided by fusion attention to highlight more discriminative spatiotemporal feature representations. The proposed method achieves 82.59% and 78.30% accuracy on two spatiotemporal action datasets UCF101-24 and JHMDB-21, respectively and reaching 73 frames/s.

关键词： Solid modeling Computer vision Three-dimensional displays Machine learning Detectors Network architecture Feature extraction

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：