检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Mingshuang Luo Ruibing Hou Zhuo Li Hong Chang Zimo Liu Yaowei Wang Shiguang Shan Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS China and Peng Cheng Laboratory China and University of Chinese Academy of Sciences China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS China WeChat Tencent Inc Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS China and University of Chinese Academy of Sciences China Peng Cheng Laboratory China Peng Cheng Laboratory China and Harbin Institute of Technology Shenzhen

ISBN: (纸本)9798331314385

This paper presents M3 GPT, an advanced Multimodal, Multitask framework for Motion comprehension and generation. M3 GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M3 GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M3 GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M3GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: https://***/M3GPT/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AlphaFold2 and its applications in the fields of biology and medicine

引用

Signal Transduction and Targeted Therapy 2023年第4期8卷 1630-1643页

作者： Zhenyu Yang Xiaoxi Zeng Yi Zhao Runsheng Chen West China Biomedical Big Data Center West China HospitalSichuan UniversityChengdu 610041China Key Laboratory of Intelligent Information Processing Advanced Computer Research CenterInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190China Key Laboratory of RNA Biology Center for Big Data Research in HealthInstitute of BiophysicsChinese Academy of SciencesBeijing 100101China Pingshan Translational Medicine Center Shenzhen Bay LaboratoryShenzhen 518118China

AlphaFold2(AF2)is an artificial intelligence(AI)system developed by DeepMind that can predict three-dimensional(3D)structures of proteins from amino acid sequences with atomic-level *** structure prediction is one of the most challenging problems in computational biology and chemistry,and has puzzled scientists for 50 *** advent of AF2 presents an unprecedented progress in protein structure prediction and has attracted much *** release of structures of more than 200 million proteins predicted by AF2 further aroused great enthusiasm in the science community,especially in the fields of biology and ***2 is thought to have a significant impact on structural biology and research areas that need protein structure information,such as drug discovery,protein design,prediction of protein function,et *** the time is not long since AF2 was developed,there are already quite a few application studies of AF2 in the fields of biology and medicine,with many of them having preliminarily proved the potential of *** better understand AF2 and promote its applications,we will in this article summarize the principle and system architecture of AF2 as well as the recipe of its success,and particularly focus on reviewing its applications in the fields of biology and *** of current AF2 prediction will also be discussed.

关键词： system fields Fold

来源：评论

学校读者我要写书评

暂无评论

Harnessing Hierarchical lab.l Distribution Variations in Test Agnostic Long-tail Recognition 41

Harnessing Hierarchical Label Distribution Variations in Tes...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Zhiyong Xu, Qianqian Wang, Zitai Li, Sicong Han, Boyu Bao, Shilong Cao, Xiaochun Huang, Qingming School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test lab.l distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test lab.l distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the lab.l distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is availab.e at https://***/scongl/DirMixE. Copyright 2024 by the author(s)

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Weighted ROC curve in cost space: extending AUC to cost-sensitive learning 23

Weighted ROC curve in cost space: extending AUC to cost-sens...

引用

Proceedings of the 37th International Conference on Neural information processing Systems

作者： Huiyang Shao Qianqian Xu Zhiyong Yang Peisong Wen Peifeng Gao Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS and BDKM University of Chinese Academy of Sciences

In this paper, we aim to tackle flexible cost requirements for long-tail datasets, where we need to construct a (1) cost-sensitive and (2) class-distribution robust learning framework. The misclassification cost and the area under the ROC curve (AUC) are popular metrics for (1) and (2), respectively. However, limited by their formulations, models trained with AUC are not well-suited for cost-sensitive decision problems, and models trained with fixed costs are sensitive to the class distribution shift. To address this issue, we present a new setting where costs are treated like a dataset to deal with arbitrarily unknown cost distributions. Moreover, we propose a novel weighted version of AUC where the cost distribution can be integrated into its calculation through decision thresholds. To formulate this setting, we propose a novel bilevel paradigm to bridge weighted AUC (WAUC) and cost. The inner-level problem approximates the optimal threshold from sampling costs, and the outer-level problem minimizes the WAUC loss over the optimal threshold distribution. To optimize this bilevel paradigm, we employ a stochastic optimization algorithm (SACCL) which enjoys the same convergence rate (O(ε-4)) with the SGD. Finally, experiment results show that our algorithm performs better than existing cost-sensitive learning methods and two-stage AUC decisions approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extracting Variable-Depth Logical Document Hierarchy from Long Documents:Method,Evaluation,and Application

引用

Journal of Computer Science & technology 2022年第3期37卷 699-718页

作者： Rong-Yu Cao Yi-Xuan Cao Gan-Bin Zhou Ping Luo Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China WeChat Search Application Department Tencent Holdings Ltd.Beijing 100080China Peng Cheng Laboratory Shenzhen 518066China

In this paper,we study the problem of extracting variable-depth"logical document hierarchy"from long documents,namely organizing the recognized"physical document objects"into hierarchical *** discovery of logical document hierarchy is the vital step to support many downstream applications(e.g.,passage-based retrieval and high-quality information extraction).However,long documents,containing hundreds or even thousands of pages and a variable-depth hierarchy,challenge the existing *** address these challenges,we develop a framework,namely Hierarchy Extraction from Long Document(HELD),where we"sequentially"insert each physical object at the proper position on the current *** whether each possible position is proper or not can be formulated as a binary classification *** further improve its effectiveness and efficiency,we study the design variants in HELD,including traversal orders of the insertion positions,heading extraction explicitly or implicitly,tolerance to insertion errors in predecessor steps,and so *** for evaluations,we find that previous studies ignore the error that the depth of a node is correct while its path to the root is *** such mistakes may worsen the downstream applications seriously,a new measure is developed for a more careful *** empirical experiments based on thousands of long documents from Chinese financial market,English financial market and English scientific publication show that the HELD model with the"root-to-leaf"traversal order and explicit heading extraction is the best choice to achieve the tradeoff between effectiveness and efficiency with the accuracy of 0.972,6,0.729,1 and 0.957,8 in the Chinese financial,English financial and arXiv datasets,***,we show that the logical document hierarchy can be employed to significantly improve the performance of the downstream passage retrieval *** summary,we conduct a systematic study on this task in terms of methods

关键词： logical document hierarchy long documents passage retrieval

来源：评论

学校读者我要写书评

暂无评论

DragEntity:Trajectory Guided Video Generation using Entity and Positional Relationships

arXiv

引用

arXiv 2024年

作者： Wan, Zhang Tang, Sheng Wei, Jiawei Zhang, Ruize Cao, Juan Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China Zhengzhou University Zhengzhou China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllab.e video generation receiving significant attention. However, existing control methods still face two limitations: Firstly, control conditions (such as depth maps, 3D Mesh) are difficult for ordinary users to obtain directly. Secondly, it’s challenging to drive multiple objects through complex motions with multiple trajectories simultaneously. In this paper, we introduce DragEntity, a video generation model that utilizes entity representation for controlling the motion of multiple objects. Compared to previous methods, DragEntity offers two main advantages: 1) Our method is more user-friendly for interaction because it allows users to drag entities within the image rather than individual pixels. 2) We use entity representation to represent any object in the image, and multiple objects can maintain relative spatial relationships. Therefore, we allow multiple trajectories to control multiple objects in the image with different levels of complexity simultaneously. Our experiments validate the effectiveness of DragEntity, demonstrating its excellent performance in fine-grained control in video generation. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

End States Guided Matching Network for Retrieval-based Multi-turn Conversation 3

End States Guided Matching Network for Retrieval-based Multi...

引用

2021年第三届先进计算机技术、信息科学与通信国际会议(CTISC2021)

作者： Weixin Tan Dandan Song Yujin Gao Lab of High Volume language Information Processing & Cloud Computing Beijing Lab of Intelligent Information TechnologyBeijing Institute of Technology

ISBN: (纸本)9781665418683

Multi-turn conversation response selection aims to choose the best response from multiple candidates based on matching it with the dialogue context. Mostly, a response full of context-related information tends to be a proper ***, in some cases, a brief response like "ok" could be the more appropriate one. We find that it is a semantically ended conversation that a brief response usually comes after,so there is no need to provide any context-related information after that. Thus, in addition to match the response with context,it is also critical to recognize the state of whether a dialogue has ended, and learn how to get necessary information from context of different end states separately. To achieve this, we propose an end states guided matching network to determine and incorporate the end states by jointly consider the length of response and the local similarity between the response and last few utterances. In addition, we adopt multiple descriptive sequence representations for a more reliable matching *** results demonstrate that our model outperforms the state-of-the-art methods in multiple datasets.

关键词： information science Computational modeling Computer network reliability Reliability Data mining

来源：评论

学校读者我要写书评

暂无评论

COMPLEX-VALUED CROSS-DOMAIN FEW-SHOT LEARNING NETWORK FOR POLSAR IMAGE CLASSIFICATION

COMPLEX-VALUED CROSS-DOMAIN FEW-SHOT LEARNING NETWORK FOR PO...

引用

IET International Radar Conference 2023, IRC 2023

作者： Cao, Yice Zhu, Dayi Wu, Zhenhua Chen, Jie Huang, Zhixiang Yang, Lixia Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electronics and Information Engineering Anhui University Hefei230601 China 38th Research Institute China Electronics Technology Group Corporation Hefei230088 China

ISBN: (纸本)9781839539954

Gathering reliable lab.led samples for polarimetric synthetic aperture (PolSAR) image classification is lab.rious. Moreover, applying a trained classifier to new domains often leads to noticeable performance degradation due to domain disparities. Therefore, this paper proposes the novel complex-valued cross-domain (CD) few-shot learning classification (CCFSLC) method for PolSAR images to address these issues. Firstly, the transferrable knowledge learning module (TKLM) with a complex-valued feature encoder (CVFE) is trained using source data with sufficient lab.led samples. Then, the deep few-shot learning module (DFSLM), constructed using the pre-trained CVFE, is trained by episodes in both source and target domains, with only minimal target lab.led samples. Meanwhile, the adversarial domain adaptation module (ADAM) is employed to eliminate domain shift. The proposed CCFSLC mainly focuses on exploring discriminative information from raw PolSAR data, while reducing the domain gap to recognize novel categories in unseen domains with only a few annotated samples. Experiments on typical PolSAR datasets validate the effectiveness of the proposed method. © The Institution of Engineering & technology 2023.

关键词： Polarimeters

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Development of a Universal RNA Dual-Terminal lab.ling Method for Sensing RNA-Ligand Interactions

引用

CCS Chemistry 2023年第1期5卷 221-233页

作者： Longhuai Cheng Dejun Ma Jie Zhang Xueying Kang Yang Wu Yi Zhao Long Yi Zhen Xi State Key Laboratory of Elemento-Organic Chemistry Department of Chemical BiologyCollege of ChemistryNational Pesticide Engineering Research CenterCollaborative Innovation Center of Chemical Science and EngineeringNankai UniversityTianjin 300071 State Key Laboratory of Organic-Inorganic Composites and Beijing Key Laboratory of Bioprocess Beijing University of Chemical Technology(BUCT)Beijing 100029 Key Laboratory of Intelligent Information Processing Research Center for Ubiquitous Computing SystemsInstitute of Computing TechnologyChinese Academy of SciencesBeijing 100190

Dual lab.ling of an RNA can provide Förster resonance energy transfer(FRET)sensors for studying RNA folding,miRNA maturation,and RNA-protein ***,we report the development of a highly efficient strategy for direct dual-terminal lab.ling of any RNA of *** explored new Michael cycloaddition for facile lab.ling of 5′-terminal RNA with improved *** chemical tetrazinylation of RNA at the 3′-terminus was achieved with the highly efficient and catalysis-free tetrazine-cycloalkyne *** single-terminal lab.ling methods were combined for dual-terminal lab.ling of an RNA including short hairpin RNA,pre-miRNA,riboswitch,and noncoding ***,these dual-lab.led RNA-based FRET sensors were used to monitor RNA-ligand interactions in vitro and in live *** is anticipated that these universal RNA lab.ling strategies will be useful to study RNA structures and functions.

关键词： dual lab.ling Förster resonance energy transfer sensor Michael cycloaddition tetrazinecycloalkyne ligation RNA-ligand interaction

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：