检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuhan Liu Yongjian Deng Hao Chen Zhen Yang College of Computer Science Beijing University of Technology Key Lab of Computer Network and Information Integration Southeast University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video Frame Interpolation (VFI) has witnessed a surge in popularity due to its abundant downstream applications. Event-based VFI (E-VFI) has recently propelled the ad-vancement of VFI. Thanks to the high temporal resolution benefits, event cameras can bridge the informational void present between successive video frames. Most state-of-the-art E-VFI methodologies follow the conventional VFI paradigm, which pivots on motion estimation between consecutive frames to generate intermediate frames through a process of warping and refinement. However, this reliance engenders a heavy dependency on the quality and consis-tency of keyframes, rendering these methods susceptible to challenges in extreme real-world scenarios, such as missing moving objects and severe occlusion dilemmas. This study proposes a novel E-VFI framework that directly synthesize intermediate frames leveraging event-based reference, obviating the necessity for explicit motion estimation and substantially enhancing the capacity to handle motion occlusion. Given the sparse and inher-ently noisy nature of event data, we prioritize the relia-bility of the event-based reference, leading to the development of an innovative event-aware reconstruction strategy for accurate reference generation. Besides, we implement a bi-directional event-guided alignment from keyframes to the reference using the introduced E-PCD module. Finally, a transformer-based decoder is adopted for prediction re-finement. Comprehensive experimental evaluations on both synthetic and real-world datasets underscore the superiority of our approach and its potential to execute high-quality VFI tasks.

关键词： Interpolation Motion estimation Noise Propulsion Transformers Rendering (computer graphics) Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Euphemism Detection by Transformers and Relational Graph Attention network 3

Euphemism Detection by Transformers and Relational Graph Att...

引用

3rd Workshop on Figurative Language Processing, FigLang 2022, as part of EMNLP 2022

作者： Wang, Yuting Liu, Yiyi Zhang, Ruqing Fan, Yixing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781959429111

Euphemism is a type of figurative language broadly adopted in social media and daily conversations. People use euphemisms for politeness or to conceal what they are discussing. Euphemism detection is a challenging task because of its obscure and figurative nature. Even humans may not agree on if a word expresses euphemism. In this paper, we propose to employ bidirectional encoder representations transformers (BERT), and relational graph attention network in order to model the semantic and syntactic relations between the target words and the input sentence. The best performing method of ours reaches a macro F1 score of 84.0 on the euphemism detection dataset of the third workshop on figurative language processing shared task 2022. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Visual Named Entity Linking: A New Dataset and A Baseline

Visual Named Entity Linking: A New Dataset and A Baseline

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Sun, Wenxiang Fan, Yixing Guo, Jiafeng Zhang, Ruqing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Visual Entity Linking (VEL) is a task to link regions of images with their corresponding entities in Knowledge Bases (KBs), which is beneficial for many computer vision tasks such as image retrieval, image caption, and visual question answering. While existing tasks in VEL either rely on textual data to complement a multi-modal linking or only link objects with general entities, which fails to perform named entity linking on large amounts of image data. In this paper, we consider a purely Visual-based Named Entity Linking (VNEL) task, where the input only consists of an image. The task is to identify objects of interest (i.e., visual entity mentions) in images and link them to corresponding named entities in KBs. Since each entity often contains rich visual and textual information in KBs, we thus propose three different sub-tasks, i.e., visual to visual entity linking (V2VEL), visual to textual entity linking (V2TEL), and visual to visual-textual entity linking (V2VTEL). In addition, we present a high-quality human-annotated visual person linking dataset, named WIKIPerson. Based on WIKIPerson, we establish a series of baseline algorithms for the solution of each sub-task, and conduct experiments to verify the quality of the proposed datasets and the effectiveness of baseline methods. We envision this work to be helpful for soliciting more works regarding VNEL in the future. The codes and datasets are publicly available at https://***/ict-bigdatalab/VNEL. © 2022 Association for Computational Linguistics.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1080-1099页

作者： Mai, Weijian Zhang, Jian Fang, Pengfei Zhang, Zhijun South China University of Technology School of Automation Science and Engineering Guangzhou510640 China Southeast University School of Computer Science and Engineering Nanjing210096 China South China University of Technology Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering Guangzhou510640 China Institute for Super Robotics Huangpu Guangzhou510555 China Nanchang University Jiangxi Thousand Talents Plan Nanchang330031 China Jishou University College of Computer Science and Engineering Jishou416000 China Guangdong Artificial Intelligence and Digital Economy Laboratory Pazhou Lab Guangzhou510335 China Shaanxi University of Technology Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Hanzhong723001 China Changsha Normal University School of Information Science and Engineering Changsha410100 China Guangdong University of Petrochemical Technology School of Automation Science and Engineering Institute of Artificial Intelligence and Automation Maoming525000 China

In the era of artificial intelligence generated content (AIGC), conditional multimodal synthesis technologies (e.g., text-to-image) are dynamically reshaping the natural content. Brain signals, serving as potential reflections of how the brain interprets external information, exhibit a distinctive one-to-many correspondence with various external modalities. This correspondence makes brain signals emerge as a promising guiding condition for multimodal synthesis (e.g., image, text, and audio), which is crucial for developing practical brain–computer interface systems and unraveling complex mechanisms underlying human perception. This survey comprehensively examines the emerging field of brain-conditional multimodal synthesis, termed AIGC-brain, to delineate the current landscape and future directions. To begin, related neuroimaging datasets and generative models are introduced as the foundation of AIGC-brain decoding and analysis. Next, we present a comprehensive taxonomy according to AIGC-brain methodologies, followed by task-specific representative work and implementation details to facilitate in-depth comparison and analysis. Quality assessments are then introduced for both qualitative and quantitative evaluation. Finally, this survey explores insights gained, outlining current challenges and prospects of AIGC-brain. As a pioneering survey, this article paves the way for future advances in AIGC-brain research. © 2020 IEEE.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Few Shot Contrastive Spectral Clustering with Meta Learning and Neighbor Mining

Few Shot Contrastive Spectral Clustering with Meta Learning ...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Nongxiao Wang Xulun Ye Jieyu Zhao Qing Wang Department of Computer Science and Technology Ningbo University China Key Lab of Mobile Network Application Technology of Zhejiang Province Ningbo China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Spectral clustering is widely used in the field of unsupervised learning and has been successfully applied in various data analysis tasks. However, in practical scenarios, it’s common to get few labeled data at low cost, resulting limited labeled data in few categories, while the rest are completely unlabeled. Relying solely on the unsupervised clustering framework can’t leverage the existing supervised information. Using a supervised meta-learning paradigm alone poses challenges when dealing with the majority categories of completely unlabeled data. Therefore, we propose a few-shot contrastive spectral clustering combined with meta learning and neighbor mining framework (FCSMN). First we leverage few shot labeled information to obtain a meta-learning feature embedding with strong generalization capabilities, and acquire semantic feature spaces using an unsupervised contrastive learning model. Then, we mine neighbors in these two feature spaces separately and align them. Next, we jointly reinforce intra-cluster compactness and inter-cluster separability at both instance and cluster level. To satisfies the conditions of spectral clustering, we impose orthogonality constraints at the last layer. Experiments on three datasets demonstrate the effectiveness our proposed method.

关键词： Metalearning Costs Semantics Neural networks Contrastive learning Data augmentation Data mining

来源：评论

学校读者我要写书评

暂无评论

Prediction of Potential Repurposed Drugs against SARS-CoV-2 based on Text Mining and Molecular Docking Analysis 23

Prediction of Potential Repurposed Drugs against SARS-CoV-2 ...

引用

Proceedings of the 2023 6th International Conference on Artificial Intelligence and Pattern Recognition

作者： Jie Zhou Yi-Qing Xu Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology China

ISBN: (纸本)9798400707674

Many research papers focusing the relationships between drugs and coronavirus-related protein interactions are indexed in the PubMed database. These studies provide a reference for predicting potential repurposed drugs against SARS-CoV-2. Drug repurposing, the most efficient strategy to quickly deploy new effective therapeutic drugs against SARS-CoV-2, can shorten the time and reduce the cost compared to de novo drug discovery. The purpose of this study was to predict potential repurposed drugs and drug pairs against SARS-CoV-2 using text mining and molecular docking *** first constructed a coronavirus-related protein names list and a drug names list using the relevant protein and drug databases. We also constructed a qualifier list. A crawler program was implemented to retrieve the desired parts from the relevant papers in the PubMed database using records from the three query lists. Based on these extracted parts, we constructed a document set, a document drug names set, and a document protein names set. Then, we used the method proposed in our previous work to calculate the document vector of each document in the document set and the TF, IDF, and TF–IDF values. We calculated the vectors of each drug and protein in the document drug names set and document protein names set based on the document vectors. The cosine similarity between the protein vector and drug vector was calculated and the score of the pair of protein and drug was defined by the cosine similarity. Next, we selected the protein–drug pairs that scored above a given threshold as the predicted interactions for coronavirus-related protein–drug pairs and then extracted all the drugs from these predicted interactions and combined them to form distinct drug pairs. Finally, the drugs with PubChem 3D structure were simulated by a molecular docking tool with the four recently identified important SARS-CoV-2 proteins, and the drug pairs were simulated by the molecular docking tool with the SARS-CoV-2

关键词： SARS-CoV-2 coronavirus drug repurposing molecular docking text mining

来源：评论

学校读者我要写书评

暂无评论

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs’ Overconfidence Helps Retrieval Augmentation

arXiv

引用

arXiv 2024年

作者： Ni, Shiyu Bi, Keping Guo, Jiafeng Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS China University of Chinese Academy of Sciences China

Large Language Models (LLMs) have been found to have difficulty knowing they do not possess certain knowledge and tend to provide specious answers in such cases. Retrieval Augmentation (RA) has been extensively studied to mitigate LLMs’ hallucinations. However, due to the extra overhead and unassured quality of retrieval, it may not be optimal to conduct RA all the time. A straightforward idea is to only conduct retrieval when LLMs are uncertain about a question. This motivates us to enhance the LLMs’ ability to perceive their knowledge boundaries to help RA. In this paper, we first quantitatively measure LLMs’ such ability and confirm their overconfidence. Then, we study how LLMs’ certainty about a question correlates with their dependence on external retrieved information. We propose several methods to enhance LLMs’ perception of knowledge boundaries and show that they are effective in reducing overconfidence. Additionally, equipped with these methods, LLMs can achieve comparable or even better performance of RA with much fewer retrieval calls. The code can be found at https://***/ShiyuNee/When-to-Retrieve. Copyright © 2024, 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

Reproducibility Analysis and Enhancements for Multi-Aspect Dense Retriever with Aspect Learning

arXiv

引用

arXiv 2024年

作者： Bi, Keping Sun, Xiaojie Guo, Jiafeng Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS China University of Chinese Academy of Sciences China

Multi-aspect dense retrieval aims to incorporate aspect information (e.g., brand and category) into dual encoders to facilitate relevance matching. As an early and representative multi-aspect dense retriever, MADRAL learns several extra aspect embeddings and fuses the explicit aspects with an implicit aspect "OTHER" for final representation. MADRAL was evaluated on proprietary data and its code was not released, making it challenging to validate its effectiveness on other datasets. We failed to reproduce its effectiveness on the public MA-Amazon data, motivating us to probe the reasons and re-examine its components. We propose several component alternatives for comparisons, including replacing "OTHER" with "CLS" and representing aspects with the first several content tokens. Through extensive experiments, we confirm that learning "OTHER" from scratch in aspect fusion is harmful. In contrast, our proposed variants can greatly enhance the retrieval performance. Our research not only sheds light on the limitations of MADRAL but also provides valuable insights for future studies on more powerful multi-aspect dense retrieval models. Code will be released at: https://***/sunxiaojie99/Reproducibility-for-MADRAL. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Roland: Robust In-band Parallel Communication for Magnetic MIMO Wireless Power Transfer System 42

Roland: Robust In-band Parallel Communication for Magnetic M...

引用

42nd IEEE International Conference on Computer Communications, INFOCOM 2023

作者： Zhou, Wangqiu Zhou, Hao Cui, Xiang Wang, Xinyu Wang, Xiaoyan Liu, Zhi Linke Lab School of Computer Science and Technology University of Science and Technology of China China University of Science and Technology of China Cas Key Laboratory of Wireless-Optical Communications China Deqing Alpha Innovation Institute Huzhou China Ibaraki University Graduate School of Science and Engineering Ibaraki Japan The University of Electro-Communications Department of Computer and Network Engineering Tokyo182-8585 Japan

ISBN: (纸本)9798350334142

In recent years, receiver (RX) feedback communication has attracted increasing attention to enhance the charging performance for magnetic resonant coupling (MRC) based wireless power transfer (WPT) systems. People prefer to adopt the in-band implementation with minimal overhead costs. However, the influence of RX-RX coupling couldn't be directly ignored like that in the RFID field, i.e., strong couplings and relay phenomenon. In order to solve these two critical issues, we propose a Robust layer-level in-band parallel communication protocol for MIMO MRC-WPT systems (called Roland). Technically, we first utilize the observed channel decomposability to construct group-level channel relationship graph for eliminating the interference caused by strong RX-RX couplings. Then, we generalize such method to deal with the RX dependency due to relay phenomenon. Finally, we conduct extensive experiments on a prototype testbed to evaluate the effectiveness of the proposed scheme. The results demonstrate that our Roland could provide ≥95% average decoding accuracy for concurrent feedback communication of 14 devices. Compared with the state-of-the-art solution, the proposed protocol Roland can achieve an average decoding accuracy improvement of 20.41%. © 2023 IEEE.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?

arXiv

引用

arXiv 2024年

作者： Ni, Shiyu Bi, Keping Yu, Lulu Guo, Jiafeng CAS Key Lab of Network Data Science and Technology ICT CAS China University of Chinese Academy of Sciences China

Large language models (LLMs) have been found to produce hallucinations when the question exceeds their internal knowledge boundaries. A reliable model should have a clear perception of its knowledge boundaries, providing correct answers within its scope and refusing to answer when it lacks knowledge. Existing research on LLMs’ perception of their knowledge boundaries typically uses either the probability of the generated tokens or the verbalized confidence as the model’s confidence in its response. However, these studies overlook the differences and connections between the two. In this paper, we conduct a comprehensive analysis and comparison of LLMs’ probabilistic perception and verbalized perception of their factual knowledge boundaries. First, we investigate the pros and cons of these two perceptions. Then, we study how they change under questions of varying frequencies. Finally, we measure the correlation between LLMs’ probabilistic confidence and verbalized confidence. Experimental results show that 1) LLMs’ probabilistic perception is generally more accurate than verbalized perception but requires an in-domain validation set to adjust the confidence threshold. 2) Both perceptions perform better on less frequent questions. 3) It is challenging for LLMs to accurately express their internal confidence in natural language. © 2024, CC BY.

关键词： Depth perception

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：