检索结果-内蒙古大学图书馆

12th National CCF Conference on Natural Language Processing and Chinese Computing, NLPCC 2023

作者： Tang, Yuanhang Ouyang, Yawen Wu, Zhen Zhang, Baohua Zhang, Jiaying Dai, Xinyu National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Big Data and Artificial Intelligence Laboratory Industrial and Commercial Bank of China Shanghai China

ISBN: (纸本)9783031446955

Recent studies show that advanced natural language understanding (NLU) models may exploit dataset biases to achieve superior performance on in-distribution datasets but fail to generalize to out-of-distribution datasets that do not contain such biases. Previous works have made promising progress in mitigating dataset biases with an extra model to estimate them. However, these methods rely on prior bias knowledge or tedious model-tuning tricks which may be hard to apply widely. To tackle the above problem, we propose to model biases by shuffling the words of the input sample, as word shuffling can break the semantics that relies on correct word order while keeping the biases that are unaffected. Thanks to word shuffling, we further propose IDOS, a unified debiasing method that enables bias estimation and debiased prediction by one single NLU model. Experimental results on three NLU benchmarks show that despite its simplicity, our method improves the generalization ability of NLU models and achieves a comparable performance to previous debiasing methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Safe Reinforcement Learning-Based Adaptive Hierarchical Control Approach for Virtual Coupling Trains 21

Safe Reinforcement Learning-Based Adaptive Hierarchical Cont...

引用

21st International Conference on Networking, Sensing and Control, ICNSC 2024

作者： Zhang, Lei Cheng, Gaoyun Wang, Wei Beijing Jiaotong University Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing China Traffic Control Technology Co. Ltd. Beijing China

ISBN: (纸本)9798350365221

Virtual coupling presents a promising solution for enhancing urban rail transit efficiency through collaborative operations facilitated by information communication rather than physical connections. However, effectively controlling virtual coupling trains presents substantial challenges, particularly in managing implicit and nonlinear safety constraints. This paper proposes a novel adaptive hierarchical control approach to address these challenges, modeling the control problem as a Constrained Markov Decision Process (CMDP). The proposed approach integrates an upper controller utilizing safe reinforcement learning (RL) and a lower controller employing Proportional Integral Derivative (PID). Safe RL incorporates an unrolling safety layer (USL) into the RL algorithm, effectively addressing safety constraints inherent in the system. Additionally, dynamic adjustment of PID parameters based on the state of the virtual coupling trains enables precise control of train operations. This hierarchical architecture capitalizes on the adaptability of safe RL while leveraging the stability of PID, facilitating dynamic strategy adjustments in response to environmental changes to ensure virtual coupling stability and reliability. Simulation experiments validate the efficacy of the proposed approach, demonstrating significant advantages in controlling virtual coupling trains and thereby enhancing operational efficiency and safety. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing

arXiv

引用

arXiv 2024年

作者： He, Liyang Chen, Enhong Huang, Zhenya Wang, Fei Wang, Shijin Liu, Jiayu Sha, Jing School of Computer Science and Technology University of Science and Technology of 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 State Key Laboratory of Cognitive Intelligence Hefei China State Key Laboratory of Cognitive Intelligence Hefei China School of Data Science University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Hefei China iFLYTEK AI Research State Key Laboratory of Cognitive Intelligence Hefei China

Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent advancements in the field demonstrate that employing large-scale backbones (e.g., ViT) in unsupervised semantic hashing models can yield substantial improvements. However, the inference delay has become increasingly difficult to overlook. Knowledge distillation provides a means for practical model compression to alleviate this delay. Nevertheless, the prevailing knowledge distillation approaches are not explicitly designed for semantic hashing. They ignore the unique search paradigm of semantic hashing, the inherent necessities of the distillation process, and the property of hash codes. In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models. To ensure the effectiveness of two kinds of search paradigms in the context of semantic hashing, BRCD first aligns the semantic spaces between the teacher and student models through a contrastive knowledge distillation objective. Additionally, to eliminate noisy augmentations and ensure robust optimization, a cluster-based method within the knowledge distillation process is introduced. Furthermore, through a bit-level analysis, we uncover the presence of redundancy bits resulting from the bit independence property. To mitigate these effects, we introduce a bit mask mechanism in our knowledge distillation objective. Finally, extensive experiments not only showcase the noteworthy performance of our BRCD method in comparison to other knowledge distillation methods but also substantiate the generality of our methods across diverse semantic hashing models and backbones. The code for BRCD is available at https://***/hly1998/BRCD. 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

Adaptive Successive POI Recommendation via Trajectory Sequences Processing and Long Short-Term Preference Learning

引用

Computers, Materials & Continua 2024年第10期81卷 685-706页

作者： Yali Si Feng Li Shan Zhong Chenghang Huo Jing Chen Jinglian Liu School of Computer Science and Engineering Changshu Institute of TechnologyChangshu215500China Suzhou Industrial Intelligence and Big Data Laboratory Suzhou215000China School of Information Science and Engineering Yanshan UniversityQinhuangdao066004China College of Electronic and Information Engineering Guangdong Ocean UniversityZhanjiang524088China

Point-of-interest(POI)recommendations in location-based social networks(LBSNs)have developed rapidly by incorporating feature information and deep learning ***,most studies have failed to accurately reflect different users’preferences,in particular,the short-term preferences of inactive *** better learn user preferences,in this study,we propose a long-short-term-preference-based adaptive successive POI recommendation(LSTP-ASR)method by combining trajectory sequence processing,long short-term preference learning,and spatiotemporal ***,the check-in trajectory sequences are adaptively divided into recent and historical sequences according to a dynamic time ***,an adaptive filling strategy is used to expand the recent check-in sequences of users with inactive check-in behavior using those of similar active *** further propose an adaptive learning model to accurately extract long short-term preferences of users to establish an efficient successive POI recommendation system.A spatiotemporal-context-based recurrent neural network and temporal-context-based long short-term memory network are used to model the users’recent and historical checkin trajectory sequences,*** experiments on the Foursquare and Gowalla datasets reveal that the proposed method outperforms several other baseline methods in terms of three evaluation *** specifically,LSTP-ASR outperforms the previously best baseline method(RTPM)with a 17.15%and 20.62%average improvement on the Foursquare and Gowalla datasets in terms of the Fβmetric,respectively.

关键词： Location-based social networks adaptive successive point-of-interest recommendation long short-term preference trajectory sequences

来源：评论

学校读者我要写书评

暂无评论

Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing

Uniform Attention Maps: Boosting Image Fidelity in Reconstru...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Mo, Wenyi Zhang, Tianyu Bai, Yalong Su, Bing Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Du Xiaoman Technology China

ISBN: (纸本)9798331510831

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering simplicity and efficiency. However, existing tuning-free approaches often struggle with balancing fidelity and editing precision. Reconstruction errors in DDIM Inversion are partly attributed to the cross-attention mechanism in U-Net, which introduces misalignments during the inversion and reconstruction process. To address this, we analyze reconstruction from a structural perspective and propose a novel approach that replaces traditional cross-attention with uniform attention maps, significantly enhancing image reconstruction fidelity. Our method effectively minimizes distortions caused by varying text conditions during noise prediction. To complement this improvement, we introduce an adaptive mask-guided editing technique that integrates seamlessly with our reconstruction approach, ensuring consistency and accuracy in editing tasks. Experimental results demonstrate that our approach not only excels in achieving high-fidelity image reconstruction but also performs robustly in real image composition and editing scenarios. This study underscores the potential of uniform attention maps to enhance the fidelity and versatility of diffusion-based image processing methods. Code is available at https://***/Mowenyii/Uniform-Attention-Maps. © 2025 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Virtual Image Generation: Bridging Reality and Virtuality for Long-Tail Traffic scenes 4

Virtual Image Generation: Bridging Reality and Virtuality fo...

引用

4th IEEE International Conference on Digital Twins and Parallel intelligence, DTPI 2024

作者： Xu, Feibing Zhang, Hui Suo, Xiaohua Li, Yidong Beijing Jiaotong University Ministry of Education Key Laboratory of Big Data & Artificial Intelligence in Transportation China Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China

ISBN: (纸本)9798350349252

Although visual perception algorithms have made significant progress in most normal scenes, it is still challenging for autonomous driving systems to accurately perceive long-tail scenes that occur less frequently, which can lead to serious traffic safety issues. However, existing open-source datasets do not systematically collect sufficient long-tail scenes. To fill this gap, we propose a pipeline for designing large-scale, diverse long-tail traffic scenes and generating virtual datasets based on the parallel vision approach. A virtual dataset named Vir-LTTS (virtual long-tail traffic scenes) is built, comprising various scenes such as extreme weather conditions, adverse lighting conditions, traffic accidents, unique forms of traffic objects, and blurry images caused by camera defects. We investigate the potential of training models using the Vir-LTTS dataset in long-tail traffic scenes. Experimental results show that pre-training with Vir-LTTS significantly improves the performance of visual models in long-tail traffic scenes. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

LQTTrack:Multi-Object Tracking by Focusing on Low-Quality Targets Association

引用

Computers, Materials & Continua 2024年第10期81卷 1449-1470页

作者： Suya Li Ying Cao Hengyi Ren Dongsheng Zhu Xin Xie Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information EngineeringHenan UniversityKaifeng475001China College of Information Science and Technology&Artificial Intelligence Nanjing Forestry UniversityNanjing210037China School of Computer Nanjing University of Posts and TelecommunicationsNanjing210023China

Multi-object tracking(MOT)has seen rapid improvements in recent ***,frequent occlusion remains a significant challenge in MOT,as it can cause targets to become smaller or disappear entirely,resulting in lowquality targets,leading to trajectory interruptions and reduced tracking *** from some existing methods,which discarded the low-quality targets or ignored low-quality target ***,with a lowquality association strategy(LQA),is proposed to pay more attention to low-quality *** the association scheme of LQTTrack,firstly,multi-scale feature fusion of FPN(MSFF-FPN)is utilized to enrich the feature information and assist in subsequent data ***,the normalized Wasserstein distance(NWD)is integrated to replace the original Inter over Union(IoU),thus overcoming the limitations of the traditional IoUbased methods that are sensitive to low-quality targets with small sizes and enhancing the robustness of low-quality target ***,the third association stage is proposed to improve the matching between the current frame’s low-quality targets and previously interrupted trajectories from earlier frames to reduce the problem of track fragmentation or error tracking,thereby increasing the association success rate and improving overall multi-object tracking *** experimental results demonstrate the competitive performance of LQTTrack on benchmark datasets(MOT17,MOT20,and DanceTrack).

关键词： Low-quality targets association strategy feature fusion multi-object tracking tracking-by-detection

来源：评论

学校读者我要写书评

暂无评论

SSC3OD: Sparsely Supervised Collaborative 3D Object Detection from LiDAR Point Clouds

SSC3OD: Sparsely Supervised Collaborative 3D Object Detectio...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Han, Yushan Zhang, Hui Zhang, Honglei Li, Yidong Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China School of Computer and Information Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798350337020

Collaborative 3D object detection, with its improved interaction advantage among multiple agents, has been widely explored in autonomous driving. However, existing collaborative 3D object detectors in a fully supervised paradigm heavily rely on large-scale annotated 3D bounding boxes, which is labor-intensive and time-consuming. To tackle this issue, we propose a sparsely supervised collaborative 3D object detection framework SSC3OD, which only requires each agent to randomly label one object in the scene. Specifically, this model consists of two novel components, i.e., the pillar-based masked autoencoder (Pillar-MAE) and the instance mining module. The Pillar-MAE module aims to reason over high-level semantics in a self-supervised manner, and the instance mining module generates high-quality pseudo labels for collaborative detectors online. By introducing these simple yet effective mechanisms, the proposed SSC3OD can alleviate the adverse impacts of incomplete annotations. We generate sparse labels based on collaborative perception datasets to evaluate our method. Extensive experiments on three large-scale datasets reveal that our proposed SSC3OD can effectively improve the performance of sparsely supervised collaborative 3D object detectors. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Two Dimensional Feature Engineering Method for Relation Extraction 5

A Two Dimensional Feature Engineering Method for Relation Ex...

引用

5th International Conference on Control, Robotics, and Intelligent System, CCRIS 2024

作者： Wang, Hao Chen, Yanping Yang, Weizhe Lin, Chuan Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry Huaxi District Guizhou China State Key Laboratory of Public Big Data Huaxi District Guizhou China Guizhou University Huaxi District Guizhou China

ISBN: (数字)9781510685871

ISBN: (纸本)9781510685864

Transforming a sentence into a 2D representation, similar to table structures, reveals a semantic plane where elements can represent potential relations between paired entities. The 2D representation effectively addresses the common issue of overlapping relations. However, previous works directly transformed the representation from raw input, neglecting the utilization of prior knowledge, which is essential to support the entity relation extraction task. In this paper, we propose a 2D feature engineering method. The method innovatively integrates prior knowledge within 2D sentence representations, marking an advancement over previous strategies, and employs an attention mechanism to build the hitherto overlooked association between entities and prior knowledge. The fusion of prior knowledge and targeted attention enhances the model’s relational discernment capabilities. Evaluations on three benchmark datasets—ACE05 Chinese, ACE05 English, and CLTC—demonstrate the efficacy of the proposed method. It surpasses existing techniques, achieving state-of-the-art performance with F1 score improvements of 0.88%, 3.27%, and 2.83% respectively. The results indicate that 2D feature engineering can take advantage of a 2D sentence representation and make full use of prior knowledge. © 2024 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

AGM: Adaptive Graph Enhanced Graph Matching for Planar Tracking 14

AGM: Adaptive Graph Enhanced Graph Matching for Planar Track...

引用

14th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2023

作者： Huang, Shiyao Wang, Tao Zhao, Gongpei Li, Yidong Beijing Jiaotong University Ministry of Education School of Computer and Lnformation Technology Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing100044 China

ISBN: (纸本)9798350371024

In recent years, graph matching has made substantial progress in planar object tracking, offering end-to-end learning capabilities. However, these methods often fall short in real-world tracking tasks due to their reliance on static, manually constructed graphs that fail to effectively account for the dynamic distribution of feature points and their relationships within individual video frames. To address these challenges, we introduce the adaptive graph matching (AGM) Network, a resilient object tracking model designed to handle complex transformations and changes in object appearance with significant accuracy. The cornerstone of AGM lies in its innovative construction of dynamic graphs that model the feature points across video frames. Nodes represent key feature points in the graph, while edges adaptively form based on the spatial relationships and descriptors of these points. This allows the graph to adjust flexibly to the properties and relationships inherent in the feature points of each frame, enhancing its fidelity to the actual structure and changes of the planar object across the video sequence. AGM employs self-attention mechanisms to guide the adaptive graph construction, and cross-attention mechanisms to capture the relationships between adjacency matrices and their associated features. Our ablation study shows that these self and cross-attention mechanisms play an integral role in enhancing the model's tracking performance, providing a more robust solution to real-world complications such as motion blur and object occlusion. We trained AGM and validated its performance on three datasets. The results show that AGM consistently outperforms other state-of-the-art models, demonstrating the effectiveness of our approach. © 2023 IEEE.

关键词： Computer vision

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：