检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ge, Wenqi Tang, Chao Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision SUSTech Shenzhen China

Object search is a fundamental skill for household robots, yet the core problem lies in the robot's ability to locate the target object accurately. The dynamic nature of household environments, characterized by the arbitrary placement of daily objects by users, makes it challenging to perform target localization. To efficiently locate the target object, the robot needs to be equipped with knowledge at both the object and room level. However, existing approaches rely solely on one type of knowledge, leading to unsatisfactory object localization performance and, consequently, inefficient object search processes. To address this problem, we propose a commonsense scene graph-based target localization, CSG-TL, to enhance target object search in the household environment. Given the pre-built map with stationary items, the robot models the room-level spatial knowledge with object-level commonsense knowledge generated by a large language model (LLM) to a commonsense scene graph (CSG), supporting both types of knowledge for CSG-TL. To demonstrate the superiority of CSG-TL on target localization, extensive experiments are performed on the real-world ScanNet dataset and the AI2THOR simulator. Moreover, we have extended CSG-TL to an object search framework, CSG-OS, validated in both simulated and real-world environments. Code and videos are available at https://***/view/csg-os. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Commonsense Scene Graph-based Target Localization for Object Search

Commonsense Scene Graph-based Target Localization for Object...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Wenqi Ge Chao Tang Hong Zhang Shenzhen Key Laboratory of Robotics and Computer Vision SUSTech Shenzhen China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Object search is a fundamental skill for household robots, yet the core problem lies in the robot’s ability to locate the target object accurately. The dynamic nature of household environments, characterized by the arbitrary placement of daily objects by users, makes it challenging to perform target localization. To efficiently locate the target object, the robot needs to be equipped with knowledge at both the object and room level. However, existing approaches rely solely on one type of knowledge, leading to unsatisfactory object localization performance and, consequently, inefficient object search processes. To address this problem, we propose a commonsense scene graph-based target localization, CSG-TL, to enhance target object search in the household environment. Given the pre-built map with stationary items, the robot models the room-level spatial knowledge with object-level commonsense knowledge generated by a large language model (LLM) to a commonsense scene graph (CSG), supporting both types of knowledge for CSG-TL. To demonstrate the superiority of CSG-TL on target localization, extensive experiments are performed on the real-world ScanNet dataset and the AI2THOR simulator. Moreover, we have extended CSG-TL to an object search framework, CSG-OS, validated in both simulated and real-world environments. Code and videos are available at https://***/view/csg-os.

关键词： Location awareness Codes Large language models Laboratories Search problems Commonsense reasoning Intelligent robots Videos

来源：评论

学校读者我要写书评

暂无评论

A deep convolutional neural network for diabetic retinopathy detection via mining local and long-range dependence

引用

CAAI Transactions on Intelligence Technology 2024年第1期9卷 153-166页

作者： Xiaoling Luo Wei Wang Yong Xu Zhihui Lai Xiaopeng Jin Bob Zhang David Zhang Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina Shenzhen Institute of Artificial Intelligence and Robotics for Society ShenzhenChina College of Big Data and Internet Shenzhen Technology UniversityShenzhenChina The Department of Computer and Information Science University of MacaoMacaoMacaoChina The Chinese University of Hong Kong(Shenzhen) ShenzhenChina

Diabetic retinopathy(DR),the main cause of irreversible blindness,is one of the most common complications of *** present,deep convolutional neural networks have achieved promising performance in automatic DR detection *** convolution operation of methods is a local cross-correlation operation,whose receptive field de-termines the size of the local neighbourhood for ***,for retinal fundus photographs,there is not only the local information but also long-distance dependence between the lesion features(*** and exudates)scattered throughout the whole *** proposed method incorporates correlations between long-range patches into the deep learning framework to improve DR ***-wise re-lationships are used to enhance the local patch features since lesions of DR usually appear as *** Long-Range unit in the proposed network with a residual structure can be flexibly embedded into other trained *** experimental results demon-strate that the proposed approach can achieve higher accuracy than existing state-of-the-art models on Messidor and EyePACS datasets.

关键词： image classification medical image processing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities

arXiv

引用

arXiv 2025年

作者： Wu, Bizhu Xie, Jinheng Shen, Keming Kong, Zhe Ren, Jianfeng Bai, Ruibin Qu, Rong Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China School of Computer Science University of Nottingham Ningbo China Ningbo China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National University of Singapore Singapore Sun Yat-sen University Shenzhen Campus China School of Computer Science University of Nottingham Nottingham United Kingdom

Recent motion-aware large language models have demonstrated promising potential in unifying motion comprehension and generation. However, existing approaches primarily focus on coarse-grained motion-text modeling, where text describes the overall semantics of an entire motion sequence in just a few words. This limits their ability to handle fine-grained motion-relevant tasks, such as understanding and controlling the movements of specific body parts. To overcome this limitation, we pioneer MG-MotionLLM, a unified motion-language model for multi-granular motion comprehension and generation. We further introduce a comprehensive multi-granularity training scheme by incorporating a set of novel auxiliary tasks, such as localizing temporal boundaries of motion segments via detailed text as well as motion detailed captioning, to facilitate mutual reinforcement for motion-text modeling across various levels of granularity. Extensive experiments show that our MG-MotionLLM achieves superior performance on classical text-to-motion and motion-to-text tasks, and exhibits potential in novel fine-grained motion comprehension and editing tasks. Project page: CVI-SZU/MG-MotionLLM Copyright © 2025, 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

NuSegDG: Integration of heterogeneous space and Gaussian kernel for domain-generalized nuclei segmentation

引用

Knowledge-Based Systems 2025年 322卷

作者： Lou, Zhenye Xu, Qing Jiang, Zekun He, Xiangjian Li, Chenxin Chen, Zhen Wang, Yi He, Maggie M. Duan, Wenting Sichuan University Pittsburgh Institute Sichuan University Chengdu China School of Computer Science Computer Vision and Intellifent Perception Laboratory and Municipal Digital Port Technology Key Laboratory University of Nottingham Ningbo Zhejiang China West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu China Centre for Artificial Intelligence and Robotics (CAIR) Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong School of Software Dalian University of Technology Dalian 116600 China Department of Electronic Engineering The Chinese University of Hong Kong 999077 Hong Kong Department of Cardiology Gold Coast University Hospital QLD Australia School of Computer Science University of Lincoln Lincoln LN6 7TS United Kingdom

Domain-generalized nuclei segmentation refers to the generalizability of models to unseen domains based on knowledge learned from source domains and is challenged by various image conditions, cell types, and stain strategies. Recently, the Segment Anything Model (SAM) has made great success in universal image segmentation by interactive prompt modes (e.g., point and box). Despite its strengths, the original SAM presents limited adaptation to medical images. Moreover, SAM requires providing manual bounding box prompts for each object to produce satisfactory segmentation masks, so it is laborious in nuclei segmentation scenarios. To address these limitations, we propose a domain-generalizable framework for nuclei image segmentation, abbreviated to NuSegDG. Specifically, we first devise a Heterogeneous Space Adapter (HS-Adapter) to learn multi-dimensional feature representations of different nuclei domains by injecting a small number of trainable parameters into the image encoder of SAM. To alleviate the labour-intensive requirement of manual prompts, we introduce a Gaussian-Kernel Prompt Encoder (GKP-Encoder) to generate density maps driven by a single point, which guides segmentation predictions by mixing position prompts and semantic prompts. Furthermore, we present a Two-Stage Mask Decoder (TSM-Decoder) to effectively convert semantic masks to instance maps without the manual demand for morphological shape refinement. Based on our experimental evaluations, the proposed NuSegDG demonstrates state-of-the-art performance in nuclei semantic and instance segmentation, exhibiting superior domain generalization capabilities. The source code is available at https://***/xq141839/NuSegDG. © 2025 Elsevier B.V.

关键词： Domain generalization Foundation model Nuclei segmentation Parameter-efficient fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Attention-Based Feature Pyramid Networks for Object Detection 11th

Multi-scale Attention-Based Feature Pyramid Networks for Obj...

引用

11th International Conference on Image and Graphics, ICIG 2021

作者： Zhao, Xiaodong Chen, Junliang Liu, Minmin Ye, Kai Shen, Linlin Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

ISBN: (纸本)9783030873547

Feature pyramid network (FPN) is widely used for multi-scale object detection. While lots of FPN based methods have been proposed to improve detection performance, there exists semantic difference between cross-scale features. Therefore, simple connections bring spatial or channel information loss, while excessive connections bring extra parameters and inference cost. Besides, the fusion of too many features may lead to the information decay and feature aliasing. To deal with the above problems, we propose the Multi-scale Attention-based Feature Pyramid Networks (MAFPN), to fully exploit spatial and channel information and generate a better feature representation for each level from multi-scale features. Taking scale, spatial and channel information into consideration at the same time, MAFPN can process multi-scale input more comprehensively than most conventional methods. The experimental results show that our MAFPN can improve the detection performance of both two-stage and one-stage detectors with an acceptable increase of inference cost. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 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

ThiNet Based Pruning Method for GAN Based Steganography Framework UT-GAN 15

ThiNet Based Pruning Method for GAN Based Steganography Fram...

引用

15th International Symposium on Signals, Circuits and Systems, ISSCS 2021

作者： Li, Qifen Li, Sili Tan, Shunquan Li, Bin Shenzhen University College of Computer Science and Software Engineering Shenzhen Key Laboratory of Media Security Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China

ISBN: (纸本)9781665449427

With the application of deep-learning framework, both the steganography and steganalysis gain superior performance than before, which has been testified by the previous researchers through experiments. Though the deep-learning models bring the excellent performance, they also result in the over-parameterized models and redundancy in computation and memory storage which make it hard for them to deploy. In this paper, we propose a ThiNet based scheme to prune the state-of the-Art steganographic model based on GAN-UTGAN. We evaluate and sort the significance of the channels of a layer according to the output of the next layer by using the greedy algorithm and obtain the channels which have the similar impact on the next layer compared with all the channels before pruning. The experimental results conducted on SZUBase, BOSSBase, and BOWS2 dataset demonstrate that our proposed ThiNet based method could compact the original UT-GAN model effectively with about only two percent of parameters of the original model and have about only a little decline in detection error rate when analyzed by SRM with ensemble classifier, which has outperformed the ASDL-GAN method. © 2021 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

HCF-Net: Hybrid Coarse-to-Fine Network for Forgery Reconstruction

HCF-Net: Hybrid Coarse-to-Fine Network for Forgery Reconstru...

引用

2021 International Workshop on Safety and Security of Deep Learning, SSDL 2021

作者： Zhuo, Long Tan, Shunquan Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen Institute of Artificial Intelligence and Robotics for Society China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Due to the ubiquity of photo editing software, it is convenient and prevalent to create fake images which may cause terrible misunderstandings. To address this issue, we introduce forgery reconstruction, a novel image reconstruction that automatically reconstructs a forged image into its original appearance. To achieve this, we present a new two-phase system, including a forgery localization phase and a reconstruction phase, where we first localize forged regions and then inpaint the natural texture. The proposed approach, called HCF-Net, is a hybrid two coarse-to-fine networks. Unlike the existing solutions of image reconstruction that relies on the prior knowledge of the areas to be recovered, our proposed system is free from the mask information. To guide the reconstruction, we propose a new strategy for extracting noise features in the forgery localization phase, which leverages the relationships among the image channels and localizes the tampered regions more precisely. For better performance, we equip a dual attention module in the reconstruction phase. Our automatic system is applicable to localize the tampered areas and reconstruct the missing part in a single pass. The extensive experiments demonstrate that our system achieves state-of-the-art performance in forgery localization and generates higher-quality and more flexible results than traditional inpainting methods. © 2021 CEUR-WS. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

SwitchGAN for multi-domain facial image translation

SwitchGAN for multi-domain facial image translation

引用

2019 IEEE International Conference on Multimedia and Expo, ICME 2019

作者： Zhu, Yuanlue Bai, Mengchao Shen, Linlin Wen, Zhiwei Computer Vision Institute College of Computer Science and Software Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China

ISBN: (纸本)9781538695524

Recent studies for multi-domain facial image translation have achieved an impressive performance. However, the existing methods still have limitations for some tasks, such as translating a facial image into different age groups, or translating a facial expression into other expressions. To address this problem, we propose a Switch Generative Adversarial Network (SwitchGAN) to perform delicate image translation among multiple domains. A feature switching operation is proposed to achieve features selection and fusion in our conditional modules. Experiments on Morph, RaFD and CelebA databases show that our SwitchGAN can achieve visually better translation effects than StarGAN. The attribute classification results using the trained ResNet-18 classifier also quantitatively suggest that the face images generated by SwitchGAN achieved much higher accuracy than that generated by StarGAN. © 2019 IEEE.

关键词： Generative adversarial networks

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：