检索结果-内蒙古大学图书馆

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Wang, Yigao Liu, Changzhen Wang, Yufei Wu, Shengjie Wang, Cheng Chen, Longbiao Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart Cities China Ministry of Education of China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Xiamen China

ISBN: (纸本)9798350312270

This paper presents a method for active 3D mapping leveraging heterogeneous crowd robots. By incorporating a UAV with its aerial perspective and powerful perception capabilities, the blind spots present in ground robot mapping are successfully eliminated, resulting in more comprehensive and accurate mapping outcomes. Furthermore, our heterogeneous crowd robots exhibits high scalability, allowing for the addition of a specified number of robots based on the mapping requirements of different indoor environments, while also supporting dynamic addition and removal. This scalability enables the system to cater to diverse applications and establishes a foundation for a more robust, comprehensive, and sustainable collective robot system. Through this research, we fully demonstrate the advantages of integrating heterogeneous robotic systems and how different types of robots with complementary capabilities collaborate to improve indoor 3D mapping processes. In particular, the introduced CrowdOS plays a significant role in task assignment and coordination, offering powerful functionalities for intelligent task allocation and coordination among different robots. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Natural Semantic Task Understanding and Scheduling System for Crowd Robots 9

A Natural Semantic Task Understanding and Scheduling System ...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Wu, Shengjie Ji, Junxiang Luo, Ruixiang Wang, Yufei Wang, Yigao Zeng, Wenting Liu, Changzhen Chen, Longbiao Wang, Cheng Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart Cities 361005 China Ministry of Education of China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing 361005 China

ISBN: (纸本)9798350319804

With the rapid development of robotic technology and the increasing demand for intelligent services, crowd robots have emerged as a promising solution for multi-robot cooperation. This study introduces a novel approach that combines large language models and reinforcement learning for natural semantic task understanding and scheduling in crowd-robot systems. Our system effectively interprets complex and ambiguous tasks described in natural language, facilitating task allocation to robots in various scenarios by adjusting the prompt template. With reinforcement learning, the system optimizes robot resource utilization and user experience from a global and long-term perspective. Our system combines robust security and reliability with a convenient user interface. Experiments on real-world datasets demonstrate that our system could accurately understand natural semantic tasks and efficiently schedule crowd robots. Case study and System Usability Scale (SUS) surveys illustrate the effectiveness and usability of our system, revealing its significant practical value in accurately parsing task commands and markedly improving task execution efficiency. Moreover, this research has considerable implications for the further development and application of crowd robots. © 2023 IEEE.

关键词： Command Parsing Crowd Robots Large Language Model Reinforcement Learning Task Allocation

来源：评论

学校读者我要写书评

暂无评论

AnyTrans: Translate AnyText in the Image with Large Scale Models

AnyTrans: Translate AnyText in the Image with Large Scale Mo...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Qian, Zhipeng Zhang, Pei Yang, Baosong Fan, Kai Ma, Yiwei Wong, Derek F. Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Tongyi Lab China NLP2CT Lab University of Macau China

ISBN: (纸本)9798891761681

This paper introduces AnyTrans, an all-encompassing framework for the task-In-Image Machine Translation (IIMT), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, diffusion models' advanced inpainting and editing abilities make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the IIMT task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration 38

Mining and Transferring Feature-Geometry Coherence for Unsup...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Xiong, Kezheng Xiang, Haoen Xu, Qingshan Wen, Chenglu Shen, Siqi Li, Jonathan Wang, Cheng Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Nanyang Technological University Singapore University of Waterloo Waterloo Canada

Point cloud registration, a fundamental task in 3D vision, has achieved remarkable success with learning-based methods in outdoor environments. Unsupervised outdoor point cloud registration methods have recently emerged to circumvent the need for costly pose annotations. However, they fail to establish reliable optimization objectives for unsupervised training, either relying on overly strong geometric assumptions, or suffering from poor-quality pseudo-labels due to inadequate integration of low-level geometric and high-level contextual information. We have observed that in the feature space, latent new inlier correspondences tend to cluster around respective positive anchors that summarize features of existing inliers. Motivated by this observation, we propose a novel unsupervised registration method termed INTEGER to incorporate high-level contextual information for reliable pseudo-label mining. Specifically, we propose the Feature-Geometry Coherence Mining module to dynamically adapt the teacher for each mini-batch of data during training and discover reliable pseudo-labels by considering both high-level feature representations and low-level geometric cues. Furthermore, we propose Anchor-Based Contrastive Learning to facilitate contrastive learning with anchors for a robust feature space. Lastly, we introduce a Mixed-Density Student to learn density-invariant features, addressing challenges related to density variation and low overlap in the outdoor scenario. Extensive experiments on KITTI and nuScenes datasets demonstrate that our INTEGER achieves competitive performance in terms of accuracy and generalizability [Code Release]. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

M3ixup: A multi-modal data augmentation approach for image captioning

引用

Pattern Recognition 2025年 158卷

作者： Li, Yinan Ji, Jiayi Sun, Xiaoshuai Zhou, Yiyi Luo, Yunpeng Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University 361005 China

Despite the great success, most models in image captioning (IC) are still stuck in the dilemma of generating simple and non-discriminative captions. In this paper, we study this problem from the perspective of data augmentation and propose a novel method called Multi-modal Mixup (M3ixup). Compared with the original Mixup strategy designed for image classification, the proposed M3ixup has three novel designs to mix IC samples from the aspects of visual features, sentence embeddings and loss values, respectively. In practice, M3ixup can not only enrich the diversity of IC training data, but also enforce the model to focus more on visual information for captioning, thereby alleviating the negative effect of dataset bias and addressing the issue of simple captioning. To validate M3ixup, we apply it to three baseline models and conduct extensive experiments on MS COCO. The experimental results demonstrate that our proposed M3ixup can not only improve the discriminability and quality of generated captions, but also help the baseline models obtain obvious performance gains, i.e., improving the CIDEr scores of the state-of-the-art model from 133.8 to 135.3 on off-line testing and 135.4 to 137.1 on online testing. © 2024

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Sensing Road Obstacles After Natural Disasters: A Survey

Sensing Road Obstacles After Natural Disasters: A Survey

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Muhammad, Auwal Sagir You, Jianyi He, Xin Chen, Longbiao Wang, Cheng School of Informatics Xiamen361005 China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen361005 China

ISBN: (纸本)9798350312270

Natural disasters, such as earthquakes, hurricanes, and flooding, can cause significant damage to roads and highways, leading to the formation of road obstacles that pose risks to drivers and hinder rescue efforts. With the rapid development of sensing technologies, a number of technologies have been proposed for disaster management, especially in disaster response and recovery. In this paper, we present a comprehensive review of sensing technologies for road obstacles focusing on the events of the aftermath of a natural disaster. Firstly, we discussed the major sensing technologies that are applied in disaster management including Vision, Lidar, Radar, and Ultrasonic. Secondly, we discussed the different techniques used in processing sensing data. Thirdly, we discussed the application of sensing technologies in the events of post-disaster and finally, we discussed the challenges faced in applying sensing technologies and highlighted areas for future studies. © 2023 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

PixelFace+: Towards Controllable Face Generation and Manipulation with Text Descriptions and Segmentation Masks 23

PixelFace+: Towards Controllable Face Generation and Manipul...

引用

31st ACM International Conference on multimedia, MM 2023

作者： Du, Xiaoxiong Peng, Jun Zhou, Yiyi Zhang, Jinlu Chen, Siting Jiang, Guannan Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Contemporary Amperex Technology Co. Limited China

ISBN: (纸本)9798400701085

Synthesizing vivid human portraits is a research hot spot in image generation with a wide scope of applications. In addition to fidelity, generation controllability is another key factor that has long plagued its development. To address this issue, existing solutions usually adopt either textual or visual conditions for the target face synthesis, e.g., descriptions or segmentation masks, which still cannot fully control the generation due to the intrinsic shortages of each condition. In this paper, we propose to make use of both types of prior information to facilitate controllable face generation. In particular, we hope to produce coarse-grained information about faces based on the segmentation masks, such as face shapes and poses, and the text description is used to render detailed face attributes, e.g., face color, makeup and gender. More importantly, we hope that the generation can be easily controlled via interactively editing both types of information, making face generation more applicable to real-world applications. To accomplish this target, we propose a novel face generation model termed PixelFace+. In PixelFace+, both the text and mask are encoded as pixel-wise priors, based on which the pixel synthesis process is conducted to produce the expected portraits. Meanwhile, the loss objectives are also carefully designed to make sure that the generated faces are semantically aligned with both text and mask inputs. To validate the proposed PixelFace+, we conducted a comprehensive set of experiments on the widely recognized benchmark called MMCelebA. We not only quantitatively compare PixelFace+ with a bunch of newly proposed Text-to-Face(T2F) generation methods, but also give plenty of qualitative analyses. The experimental results demonstrate that PixelFace+ not only outperforms existing generation methods in both image quality and conditional matching but also shows a much superior controllability of face generation. More importantly, PixelFace+ presents a co

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Monte Carlo Tree Search Based Prompt Autogeneration for Jailbreak Attacks against LLMs 31

Monte Carlo Tree Search Based Prompt Autogeneration for Jail...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wu, Suhuang Wang, Huimin Zhao, Yutian Wu, Xian Zheng, Yefeng Li, Wei Li, Hui Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China Tencent Jarvis Lab China Medical Artificial Intelligence Lab Westlake University China Faculty of Computing Harbin Institute of Technology China

ISBN: (纸本)9798891761964

Jailbreak attacks craft specific prompts or append adversarial suffixes to prompts, thereby inducing language models to generate harmful or unethical content and bypassing the model's safety guardrails. With the recent blossom of large language models (LLMs), there's a growing focus on jailbreak attacks to probe their safety. While current white-box attacks typically focus on meticulously identifying adversarial suffixes for specific models, their effectiveness and efficiency diminish when applied to different LLMs. In this paper, we propose a Monte Carlo Tree Search (MCTS) based Prompt Auto-generation (MPA) method to enhance the effectiveness and efficiency of attacks across various models. MPA automatically searches for and generates adversarial suffixes for valid jailbreak attacks. Specifically, we first identify a series of action candidates that could potentially trick LLMs into providing harmful responses. To streamline the exploration of adversarial suffixes, we design a prior confidence probability for each MCTS node. We then iteratively auto-generate adversarial prompts using the MCTS framework. Extensive experiments on multiple open-source models (like Llama, Gemma, and Mistral) and closed-source models (such as ChatGPT) show that our proposed MPA surpasses existing methods in search efficiency as well as attack effectiveness. The codes are available at https://***/KDEGroup/MPA. © 2025 Association for Computational Linguistics.

关键词： Guard rails

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based AUV Localization in Underwater Acoustic Sensor Networks

Reinforcement Learning Based AUV Localization in Underwater ...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Liu, Chuhuan Chen, Yifan Xiao, Liang Yang, Helin Su, Wei You, Xudong Xiamen University Department of Information and Communication Engineering Xiamen China Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China China

ISBN: (纸本)9798350345384

Many crucial underwater tasks are performed based on the precise positions of target nodes in underwater acoustic sensor networks (UASNs). However, due to significant signal attenuation and long propagation latency in acoustic communication, it is challenging to achieve accurate and energy-efficient underwater localization. In this paper, we propose an autonomous underwater vehicles (AUVs) localization scheme to determine the selection and transmit power of beacons based on range measurements between AUVs and mobile beacons using the two-ray travel time of localization signals. Then, a safe reinforcement learning algorithm is proposed to select the AUV localization policy based on the AUV depth, the previous number of selected beacons and received signal strengths. Performance analysis in terms of computational complexity and Cramer-Rao lower bound is provided. Simulation results based on the isogradient sound speed model show that the proposed scheme achieves higher localization accuracy, lower energy consumption and higher utility compared with the benchmark. © 2023 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

3D-GRES: Generalized 3D Referring Expression Segmentation 24

3D-GRES: Generalized 3D Referring Expression Segmentation

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Wu, Changli Liu, Yihang Ji, Jiayi Ma, Yiwei Wang, Haowei Luo, Gen Ding, Henghui Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Xiamen China Youtu Lab Tencent Shanghai China Institute of Big Data Fudan University Shanghai China

ISBN: (纸本)9798400706868

3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the versatility of the task. To overcome this limitation, we introduce Generalized 3D Referring Expression Segmentation (3D-GRES), which extends the capability to segment any number of instances based on natural language instructions. In addressing this broader task, we propose the Multi-Query Decoupled Interaction Network (MDIN), designed to break down multi-object segmentation tasks into simpler, individual segmentations. MDIN comprises two fundamental components: Text-driven Sparse Queries (TSQ) and Multi-object Decoupling Optimization (MDO). TSQ generates sparse point cloud features distributed over key targets as the initialization for queries. Meanwhile, MDO is tasked with assigning each target in multi-object scenarios to different queries while maintaining their semantic consistency. To adapt to this new task, we build a new dataset, namely Multi3DRes. Our comprehensive evaluations on this dataset demonstrate substantial enhancements over existing models, thus charting a new path for intricate multi-object 3D scene comprehension. The benchmark and code are available at https://***/sosppxo/MDIN. © 2024 ACM.

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：