检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lyu, Yuanjie Xu, Tong Niu, Zihan Peng, Bo Ke, Jing Chen, Enhong The Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science University of Science and Technology of China Hefei230026 China

The prosperity of social media platforms has raised the urgent demand for semantic-rich services, e.g., event and storyline attribution. However, most existing research focuses on clip-level event understanding, primarily through basic captioning tasks, without analyzing the causes of events across an entire movie. This is a significant challenge, as even advanced multimodal large language models (MLLMs) struggle with extensive multimodal information due to limited context length. To address this issue, we propose a Two-Stage Prefix-Enhanced MLLM (TSPE) approach for event attribution, i.e., connecting associated events with their causal semantics, in movie videos. In the local stage, we introduce an interaction-aware prefix that guides the model to focus on the relevant multimodal information within a single clip, briefly summarizing the single event. Correspondingly, in the global stage, we strengthen the connections between associated events using an inferential knowledge graph, and design an event-aware prefix that directs the model to focus on associated events rather than all preceding clips, resulting in accurate event attribution. Comprehensive evaluations of two real-world datasets demonstrate that our framework outperforms state-of-the-art methods. Copyright © 2024, 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

DCSim: Computing and Networking Integration based Container Scheduling Simulator for data Centers

arXiv

引用

arXiv 2024年

作者： Hu, Jinlong Rao, Zhizhe Liu, Xingchen Deng, Lihao Dong, Shoubin Guangdong Key Lab of Multimodal Big Data Intelligent Analysis School of Computer Science and Engineering South China University of Technology Guangzhou China

The increasing prevalence of cloud-native technologies, particularly containers, has led to the widespread adoption of containerized deployments in data centers. The advancement of deep neural network models has increased the demand for container-based distributed model training and inference, where frequent data transmission among nodes has emerged as a significant performance bottleneck. However, traditional container scheduling simulators often overlook the influence of network modeling on the efficiency of container scheduling, primarily concentrating on modeling computational resources. In this paper, we focus on a container scheduling simulator based on collaboration between computing and networking within data centers. We propose a new container scheduling simulator for data centers, named DCSim. The simulator consists of several modules: a data center module, a network simulation module, a container scheduling module, a discrete event-driven module, and a data collection and analysis module. Together, these modules provide heterogeneous computing power modeling and dynamic network simulation capabilities. We design a discrete event model using SimPy to represent various aspects of container processing, including container requests, scheduling, execution, pauses, communication, migration, and termination within data centers. Among these, lightweight virtualization technology based on Mininet is employed to construct a software-defined network. An experimental environment for container scheduling simulation was established, and functional and performance tests were conducted on the simulator to validate its scheduling simulation capabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Coordinate-wise monotonic transformations enable privacy-preserving age estimation with 3D face point cloud

引用

Science China(Life Sciences) 2024年第7期67卷 1489-1501页

作者： Xinyu Yang Runhan Li Xindi Yang Yong Zhou Yi Liu Jing-Dong J.Han School of Life Sciences Peking UniversityBeijing 100871China Peking-Tsinghua Center for Life Sciences Academy for Advanced Interdisciplinary StudiesCenter for Quantitative Biology(CQB)Peking UniversityBeijing 100871China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information TechnologyBeijing Jiaotong UniversityBeijing 100044China Clinical Research Institute Shanghai General HospitalShanghai Jiao Tong University School of MedicineShanghai 200025China

The human face is a valuable biomarker of aging,but the collection and use of its image raise significant privacy *** we present an approach for facial data masking that preserves age-related features using coordinate-wise monotonic *** first develop a deep learning model that estimates age directly from non-registered face point clouds with high accuracy and *** show that the model learns a highly indistinguishable mapping using faces treated with coordinate-wise monotonic transformations,indicating that the relative positioning of facial information is a low-level biomarker of facial *** visual perception tests and computational3D face verification experiments,we demonstrate that transformed faces are significantly more difficult to perceive for human but not for machines,except when only the face shape information is *** study leads to a facial data protection guideline that has the potential to broaden public access to face datasets with minimized privacy risks.

关键词： face point cloud age estimation face verification privacy coordinate-wise monotonic transformation

来源：评论

学校读者我要写书评

暂无评论

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTURAL MOTIFS 11

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTUR...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zhang, Zaixi Min, Yaosen Zheng, Shuxin Liu, Qi Anhui Province Key Lab 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 Anhui Hefei China Institute of Interdisciplinary Information Sciences Tsinghua University China Microsoft Research United States

Designing ligand molecules that bind to specific protein binding sites is a fundamental problem in structure-based drug design. Although deep generative models and geometric deep learning have made great progress in drug design, existing works either sample in the 2D graph space or fail to generate valid molecules with realistic substructures. To tackle these problems, we propose a Fragment-based LigAnd Generation framework (FLAG), to generate 3D molecules with valid and realistic substructures fragment-by-fragment. In FLAG, a motif vocabulary is constructed by extracting common molecular fragments (i.e., motif) in the dataset. At each generation step, a 3D graph neural network is first employed to encode the intermediate context information. Then, our model selects the focal motif, predicts the next motif type, and attaches the new motif. The bond lengths/angles can be quickly and accurately determined by cheminformatics tools. Finally, the molecular geometry is further adjusted according to the predicted rotation angle and the structure refinement. Our model not only achieves competitive performances on conventional metrics such as binding affinity, QED, and SA, but also outperforms baselines by a large margin in generating molecules with realistic substructures. Our code is publicly available at https://***/zaixizhang/FLAG. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

TCMLLM-PR:evaluation of large language models for prescription recommendation in traditional Chinese medicine

引用

Digital Chinese Medicine 2024年第4期7卷 343-355页

作者： TIAN Haoyu YANG Kuo DONG Xin ZHAO Chenxi YE Mingwei WANG Hongyan LIU Yiming HU Minjie ZHU Qiang YU Jian ZHANG Lei ZHOU Xuezhong Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science&TechnologyBeijing Jiaotong UniversityBeijing 100044China National Data Center of Traditional Chinese Medicine China Academy of Chinese Medical SciencesBeijing 100700China

Objective To develop and evaluate a fine-tuned large language model(LLM)for traditional Chinese medicine(TCM)prescription recommendation named *** First,we constructed an instruction-tuning dataset containing 68654 samples(ap-proximately 10 million tokens)by integrating data from eight sources,including four TCM textbooks,Pharmacopoeia of the People’s Republic of China 2020(CHP),Chinese Medicine Clinical Cases(CMCC),and hospital clinical records covering lung disease,liver disease,stroke,diabetes,and splenic-stomach ***,we trained TCMLLM-PR using Chat-GLM-6B with P-Tuning v2 *** evaluation consisted of three aspects:(i)compari-son with traditional prescription recommendation models(PTM,TCMPR,and PresRecST);(ii)comparison with TCM-specific LLMs(ShenNong,Huatuo,and HuatuoGPT)and general-domain ChatGPT;(iii)assessment of model migration capability across different disease *** employed precision,recall,and F1 score as evaluation *** The experiments showed that TCMLLM-PR significantly outperformed baseline models on TCM textbooks and CHP datasets,with F1@10 improvements of 31.80%and 59.48%,*** cross-dataset validation,the model performed best when migrating from TCM textbooks to liver disease dataset,achieving an F1@10 of *** of real-world cases demonstrated that TCMLLM-PR's prescription recommendations most closely matched actual doctors’*** This study integrated LLMs into TCM prescription recommendations,leverag-ing a tailored instruction-tuning dataset and developing *** study will pub-licly release the best model parameters of TCMLLM-PR to promote the development of the decision-making process in TCM practices(https://***/2020MEAI/TCMLLM).

关键词： Large language models Instruction-tuning Prescription recommendation Traditional Chinese medicine(TCM) Assisted decision-making

来源：评论

学校读者我要写书评

暂无评论

LMDTA: Molecular Pre-trained and Interaction Fine-tuned Attention Neural Network for Drug-Target Affinity Prediction

LMDTA: Molecular Pre-trained and Interaction Fine-tuned Atte...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Minjie Hu Kuo Yang Kuan Xu Xuezhong Zhou Institute of Medical Intelligence Beijing Key Lab of Traffic Data Analysis and Mining School of Computer Science & Technology Beijing Jiaotong University Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Accurately predicting drug-target binding affinity is crucial for advancing drug discovery. Recent molecular pre-training models and biological large models provide general molecular representations, but effectively leveraging these features for specific tasks like Drug-Target Affinity (DTA) prediction remains challenging. To address this, we propose LMDTA, a novel attention-based neural network combining molecular pre-training with interaction fine-tuning for affinity prediction. LMDTA learns complex drug and protein representations through pre-trained models, while fine-tuning an interaction-specific model for the DTA task. The two-side attention mechanism integrates pre-trained and fine-tuned features, capturing key drug-target interactions. Experiments on benchmark datasets show LMDTA achieves state-of-the-art performance, with ablation studies validating the model’s design.

关键词： Proteins Drugs Protein engineering Biological system modeling Neural networks Predictive models Benchmark testing Robustness data models Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Pseudo Sample Synthesis Based on Task-Irrelevant Augmentation for Generalized Zero-Shot Learning

Pseudo Sample Synthesis Based on Task-Irrelevant Augmentatio...

引用

International Conference on Big data and Information Analytics (BigDIA)

作者： Yaogong Feng Xiaowen Huang Feng Jiang Yangyang Sun Jitao Sang Beijing Institute of Control and Electronics Technology Beijing China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

Generalized zero-shot learning try to recognizes images from seen and unseen classes. Recent methods construct two complementary visual representations, or directly disentangle the overall visual representations to synthesize pseudo samples to achieve it. But there are still two challenging problems: (1) data-consuming. Constructing two complementary visual representations requires massive training data, which may cause poor per-formance when samples are limited. (2) Ignoring task-irrelevant features during synthesizing. The typical disentanglement-based methods synthesize pseudo samples without using learned task-irrelevant features. However, these features have better represen-tation transferability, which can contribute to more diversity syn-thesizing. In this paper, we propose the Pseudo Sample Synthesis based on Task-irrelevant Augmentation (PS 2 TA) that synthesizes by taking advantage of task-irrelevant features disentangled from global visual features, which has two key modules. (1) Anchor-pseudo-sample Synthesis Module, with which we synthesize class anchor pseudo samples that guarantee the conformity between pseudo samples and their corresponding semantics. (2) Diverse-pseudo-sample Synthesis Module. We disentangle task-irrelevant features from the global visual representations and synthesize diverse pseudo samples augmented by task-irrelevant features based on the anchor pseudo samples, which guarantees the diversity of pseudo samples. Extensive experiments on three benchmarks and different tasks demonstrate our method is competitive.

关键词： Continuing education Visualization Image recognition Zero shot learning Semantics Training data Big data Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Fuzzy cognitive maps learning algorithm based on modified covariance matrix adaptation evolution strategy

Fuzzy cognitive maps learning algorithm based on modified co...

引用

2023 International Conference on Cloud Computing, Performance Computing, and Deep Learning, CCPCDL 2023

作者： Li, Zhuofan Wang, Jingping Zhang, Yingjun Huang, Hua Yin, Hui Xu, Hongli Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Information Technology Center Beijing Jiaotong University Beijing100044 China Key Laboratory of Beijing for Railway Engineering Beijing Jiaotong University Beijing100044 China

ISBN: (纸本)9781510666474

Fuzzy cognitive maps (FCMs) are an efficient soft computing tool commonly used for modeling and analyzing complex systems, and have significant advantages in knowledge representation and fast reasoning. At present, many researchers have devoted themselves to solving the learning problem of FCMs. However, most of the existing learning algorithms are prone to local convergence and are not suitable for large-scale FCMs learning problems. Moreover, the learning problem of FCMs is often a complex non-convex optimization problem, which is easy to cause the final learning result of the algorithm to be only a local optimal solution. To address these limitations, this paper proposes a novel algorithm for learning FCMs by combining multimodal optimization and modified covariance matrix adaptation evolution strategy (CMA-ES), termed as MCMA-ES. First, the learning problem of FCMs is modeled as a multimodal optimization problem (MMOP), and then a multimodal optimization algorithm is proposed by combining the detect multimodal clustering (DMC) and CMA-ES, and the cubic chaos factor is combined to enhance the capability of local search. Finally the proposed algorithm is combined with the decomposition strategy to learn FCMs. Experiments are carried out on 5 benchmark datasets, and MCMA-ES is also applied to 15 groups of large-scale gene regulatory system reconstruction problems. The experimental results show that MCMA-ES has high learning generalization and accuracy. © 2023 SPIE.

关键词： Fuzzy Cognitive Maps

来源：评论

学校读者我要写书评

暂无评论

A Method to Explore the Synchronous Changes of High-Traffic Events Based on Dynamic Networks 9

A Method to Explore the Synchronous Changes of High-Traffic ...

引用

9th International Conference on Fuzzy Systems and data Mining, FSDM 2023

作者： Huang, Yu-Wen Wang, Li-Na Zang, Chen-Rui College of Sciences Inner Mongolia University of Technology Hohhot010051 China Inner Mongolia Key Lab. of Statistical Analysis Theory for Life Data and Neural Network Modeling Hohhot010051 China Inner Mongolia Branch China Unicom Hohhot010050 China

ISBN: (纸本)9781643684703

With the rapid development of mobile communication technologies, the mobile network has evolved into a highly heterogeneous network structure. Based on dynamic networks, we mainly investigated a method to explore the synchronous changes of high-traffic events. Event coincidence analysis is used to quantify the concurrency of high-traffic events. A variety of network measures are used to analyze the dynamic spatio-temporal characteristics of high-traffic. The static network is constructed to analyze the synchronous influence area and the temporal and spatial characteristics of high-traffic of base station. Taking hour as the time window, the dynamic network is constructed to study the dynamic spatio-temporal variation rule of high-traffic and the interactive relationship of traffic between base stations. It is found that static network is a small-world network. The spatial connectivity of high-traffic events at the base station is high, and the spatial connectivity is not sensitive to temporal changes. The traffic of different base stations has interactive relation at the same time in different days. © 2023 The authors and IOS Press.

关键词： Base stations

来源：评论

学校读者我要写书评

暂无评论

MITF:Cross-modal Image-text Retrieval Method with Mapping Images to Text Features 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Lou, Xinyue Li, You Qi, Rui Chen, Yufeng Xu, Jinan School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China Beijing Key Lab of Traffic Data Analysis and Mining Beijing100044 China

ISBN: (纸本)9780000000002

To address the cross-modal image-text retrieval challenge, it’s essential to close the semantic gap between vision and language. However, the prevailing dual-stream model which separates image encoder and text encoder during training complicates the problem. In this paper, we propose a mapping network to map information from different modalities (image and text) to a single modality (text), called MITF network, with the purpose of improving the fusion and alignment of cross-modal semantics. Given a frozen pre-trained model, Chinese-CLIP, we train the MITF network to convert the visual embedding into the corresponding pseudo language tokens. Additionally, we also introduce a mechanism that automatically learns prompt to enhance the model’s understanding of pseudo language tokens. To speed up the retrieval process, the Faiss index is employed. Experimental findings on three datasets show that our method achieves an absolute 3.7% MR gain and quadruples retrieval speed compared to the vanilla Chinese-CLIP model. Additionally, the image-text feature visualization results further show that our method improves the alignment between image features and text features. © 2024 China National Conference on Computational Linguistics.

关键词： Semantics

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：