检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Li, Haiyang Li, Meng Qi, Xiaozhi Yang, Yuanyuan Hu, Ying Shenyang Aerospace University China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Harbin Institute of Technology China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

ISBN: (纸本)9781665481090

To optimize the operation ability of the autonomous robot under the background of complex surgery, this paper extracted the state features of milling video sequence images to realize bone layer perception and improve the perception ability of the spinal robot. The bone layer sensing algorithm mainly consists of four parts: improved moving object detection algorithm, moving object tracking algorithm, state feature extraction algorithm and bone layer recognition algorithm. Aiming at the shortcomings of the existing moving target detection methods, this paper proposes an improved moving target detection algorithm based on the existing Background Subtractor MOG algorithm, which is suitable for milling video sequences. The grinding machine state obtained by the improved algorithm is used as the input of the moving target tracking algorithm, and the kernel correlation filter (KCF) is used to realize the target tracking. According to the tracking of the moving target, the state features of the milling area are extracted and the bone layer is identified, so as to realize the bone layer perception in the milling process. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

IMPROVING WEAKLY SUPERVISED OBJECT LOCALIZATION BY UNCERTAINTY ESTIMATION OF PSEUDO SUPERVISION

IMPROVING WEAKLY SUPERVISED OBJECT LOCALIZATION BY UNCERTAIN...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Chen, Xi Ma, Andy J. Guo, Nanxi Chen, Jiajia School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781665438643

Pseudo bounding box supervision is a promising approach for weakly supervised object localization (WSOL) with only image-level labels. However, the generated pseudo bounding boxes may be inaccurate or even completely non-overlapped with the objects of interest. In this paper, we propose to estimate the uncertainty of pseudo bounding boxes such that the negative impact caused by inaccurate estimation of pseudo supervision could be alleviated for better WSOL. The refined bounding boxes and corresponding variance uncertainties are learned by training a neural network regressor to penalize the erroneous estimations. To the best of our knowledge, this is the first work to incorporate uncertainty information of pseudo bounding boxes for WSOL. Experimental results show that our method not only outperforms previous state-of-the-art methods in CUB-200-2011 and ILSVRC datasets but also gives more precise bounding box prediction when the IoU threshold is higher. © 2021 IEEE

关键词： Uncertainty analysis

来源：评论

学校读者我要写书评

暂无评论

Human-Centric Transformer for Domain Adaptive Action Recognition

arXiv

引用

arXiv 2024年

作者： Lin, Kun-Yu Zhou, Jiaming Zheng, Wei-Shi The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510275 China The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou510275 China The Guangdong Province Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou510275 China The Peng Cheng Laboratory Shenzhen518005 China

We study the domain adaptation task for action recognition, namely domain adaptive action recognition, which aims to effectively transfer action recognition power from a label-sufficient source domain to a label-free target domain. Since actions are performed by humans, it is crucial to exploit human cues in videos when recognizing actions across domains. However, existing methods are prone to losing human cues but prefer to exploit the correlation between non-human contexts and associated actions for recognition, and the contexts of interest agnostic to actions would reduce recognition performance in the target domain. To overcome this problem, we focus on uncovering human-centric action cues for domain adaptive action recognition, and our conception is to investigate two aspects of human-centric action cues, namely human cues and human-context interaction cues. Accordingly, our proposed Human-Centric Transformer (HCTransformer) develops a decoupled human-centric learning paradigm to explicitly concentrate on human-centric action cues in domain-variant video feature learning. Our HCTransformer first conducts human-aware temporal modeling by a human encoder, aiming to avoid a loss of human cues during domain-invariant video feature learning. Then, by a Transformer-like architecture, HCTransformer exploits domain-invariant and action-correlated contexts by a context encoder, and further models domain-invariant interaction between humans and action-correlated contexts. We conduct extensive experiments on three benchmarks, namely UCF-HMDB, Kinetics-NecDrone and EPIC-Kitchens-UDA, and the state-of-the-art performance demonstrates the effectiveness of our proposed HCTransformer. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

When Prompt-based Incremental Learning Does Not Meet Strong Pretraining

When Prompt-based Incremental Learning Does Not Meet Strong ...

引用

International Conference on Computer Vision (ICCV)

作者： Yu-Ming Tang Yi-Xing Peng Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Peng Cheng Laboratory Shenzhen China

Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based methods adopt a fixed backbone to sequential tasks by learning task-specific prompts. However, existing prompt-based methods heavily rely on strong pretraining (typically trained on ImageNet-21k), and we find that their models could be trapped if the potential gap between the pretraining task and unknown future tasks is large. In this work, we develop a learnable Adaptive Prompt Generator (APG). The key is to unify the prompt retrieval and prompt learning processes into a learnable prompt generator. Hence, the whole prompting process can be optimized to reduce the negative effects of the gap between tasks effectively. To make our APG avoid learning ineffective knowledge, we maintain a knowledge pool to regularize APG with the feature distribution of each class. Extensive experiments show that our method significantly outperforms advanced methods in exemplar-free incremental learning without (strong) pretraining. Besides, under strong pretraining, our method also has comparable performance to existing prompt-based models, showing that our method can still benefit from pretraining. Codes can be found at https://***/TOM-tym/APG

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Neuroinspired Contrast Mechanism Enables Few-Shot Object Detection

SSRN

引用

SSRN 2023年

作者： Yang, Lingxiao Chen, Dapeng Chen, Yifei Peng, Wei Xie, Xiaohua School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China Huawei Technlogies Shenzhen China

Object detectors based on deep neural networks often require a large number of annotated images for training. In the most realistic scenario, only a few training data are available;thus, Few-Shot Object Detection (FSOD) has become an attractive research topic. In this problem setting, two-stage proposal-based Faster R-CNN detectors are widely used in multiple previous studies, while its performance still lags far behind the one trained with lots of data. We identify the main bottleneck of training a detector in the few-shot scenario as the insufficient number of samples for discovering robust comparison-based relationships (e.g., proposal-level and category-level relationships). Moreover, we found that existing methods explore these relationships only during the training phase. It is interesting to investigate whether we can effectively incorporate such relationships during model training and testing to improve FSOD. To this end, we borrow the idea of "contrast" from neuroscience studies, and propose a simple yet effective architecture, named Residual Contrast Faster R-CNN (RcFRCN). Our RcFRCN extends the existing state-of-the-art FSOD detector by introducing two newly designed contrast blocks, i.e., a Residual Spatial Contrast Block and a Residual Proposal Contrast Block. The former block mainly explores cross-spatial contrast information in a feature map extracted by the backbone network, and the latter block discovers contrast cues across proposal features outputted by the RPN module. As a result, these blocks store differences and commodities in different perspectives and are used in both training and test phases, thus enhancing the ability of transfer learning. Extensive experiments demonstrate the effectiveness of our RcFRCN. Moreover, our method also helps the detector to retain more previous knowledge and obtains better performance in the detection of base classes. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Depth Knowledge Distillation for Cloth-Changing Person Re-identification

Fine-Grained Depth Knowledge Distillation for Cloth-Changing...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yuhan Yao Jiawei Feng Ancong Wu Jiangqun Ni Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China School of Cyber Science and Technology Sun Yat-sen University Shenzhen China Department of New Networks Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Key Laboratory of Information Security Technology China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The mission of cloth-changing person re-identification (CC-ReID) is to discover cloth-invariant and identity-related cues, while traditional person ReID methods rely on appearance features that are biased to cloth-related cues. To tackle this cloth-biased problem, many CC-ReID methods introduced auxiliary body shape information to extract cloth-invariant features, such as 2D sketch images or the 3D Skinned Multi-Person Linear (SMPL) model. However, 2D auxiliary information lacks 3D spatial features, while the 3D SMPL model encounters challenges in capturing features at a finer granularity due to manually defined parameters. To extract fine-grained 3D shape features, we estimate depth maps that contain richer shape information and propose a Fine-grained Depth feature Mining and Distillation (FDMD) framework. We introduce a depth branch and design a fine-grained local feature interaction module to mine fine-grained 3D body shape knowledge from estimated depth maps by exploring the context of semantic-aware local body-part features. To integrate cloth-invariant depth knowledge into the appearance features, the fine-grained 3D shape features are transferred to an appearance branch by feature-space-aligned distillation. Extensive experiments demonstrate that FDMD can achieve state-of-the-art performance on three widely used CC-ReID benchmarks PRCC, Celeb-reID and LaST.

关键词： Solid modeling Three-dimensional displays Shape Neural networks Benchmark testing Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

Resampling Factor Estimation via Dual-Stream Convolutional Neural Network

引用

Computers, Materials & Continua 2021年第1期66卷 647-657页

作者： Shangjun Luo Junwei Luo Wei Lu Yanmei Fang Jinhua Zeng Shaopei Shi Yue Zhang School of Data and Computer Science Guangdong Province Key Laboratory of Information Security TechnologyMinistry of Education Key Laboratory of Machine Intelligence and Advanced ComputingSun Yat-sen UniversityGuangzhou510006China Academy of Forensic Science Shanghai200063China College of Information Science and Technology Jinan UniversityGuangzhou510632China Department of Computer Science University of Massachusetts LowellLowellMA 01854USA

The estimation of image resampling factors is an important problem in image *** all the resampling factor estimation methods,spectrumbased methods are one of the most widely used methods and have attracted a lot of research ***,because of inherent ambiguity,spectrum-based methods fail to discriminate upscale and downscale operations without any prior *** general,the application of resampling leaves detectable traces in both spatial domain and frequency domain of a resampled ***,the resampling process will introduce correlations between neighboring *** this case,a set of periodic pixels that are correlated to their neighbors can be found in a resampled ***,the resampled image has distinct and strong peaks on spectrum while the spectrum of original image has no clear ***,in this paper,we propose a dual-stream convolutional neural network for image resampling factors *** of the two streams is gray stream whose purpose is to extract resampling traces features directly from the rescaled *** other is frequency stream that discovers the differences of spectrum between rescaled and original *** features from two streams are then fused to construct a feature representation including the resampling traces left in spatial and frequency domain,which is later fed into softmax layer for resampling factor *** results show that the proposed method is effective on resampling factor estimation and outperforms some CNN-based methods.

关键词： Image forensics image resampling detection parameter estimation convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Mixture of Online and Offline Experts for Non-Stationary Time Series 39

Mixture of Online and Offline Experts for Non-Stationary Tim...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Zhao, Zhilin Cao, Longbing Wan, Yuanyu School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Computing Macquarie University Sydney Australia Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China School of Software Technology Zhejiang University Ningbo China

ISBN: (纸本)157735897X

We consider a general and realistic scenario involving nonstationary time series, consisting of several offline intervals with different distributions within a fixed offline time horizon, and an online interval that continuously receives new samples. For non-stationary time series, the data distribution in the current online interval may have appeared in previous offline intervals. We theoretically explore the feasibility of applying knowledge from offline intervals to the current online interval. To this end, we propose the Mixture of Online and Offline Experts (MOOE). MOOE learns static offline experts from offline intervals and maintains a dynamic online expert for the current online interval. It then adaptively combines the offline and online experts using a meta expert to make predictions for the samples received in the online interval. Specifically, we focus on theoretical analysis, deriving parameter convergence, regret bounds, and generalization error bounds to prove the effectiveness of the algorithm. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Halftone Image Steganography Based on Maximizing Visual Similarity of Block Units 7th

Halftone Image Steganography Based on Maximizing Visual Sim...

引用

7th International Conference on Artificial intelligence and Security, ICAIS 2021

作者： Yin, Xiaolin Yu, Mujian Chen, Lili Wang, Ke Lu, Wei School of Computer Science and Engineering Guangdong Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China Guangdong Science and Technology Innovation Monitoring and Research Center Guangzhou510033 China

ISBN: (纸本)9783030786113

Steganography focuses on imperceptibility of both the human eyes but also to potential analyzers. Based on the human visual system (HVS) of halftone image, most previous visual quality measurements for multi-tone images can not be adopted to design the steganographic schemes. In this paper, we propose a halftone image steganographic scheme based on the maximizing visual similarity of block units aiming at improving the statistical security but also the image visual quality. First, the halftone HVS model is discussed. The similarity of a pixel and its neighboring regions (which are called block units) is an important factor for human eyes. Then the distortion score is designed based on the visual similarity for each pixel in an image. Several visual similarity scores owned by a pixel are obtained in different block units. In general, the maximal visual similarity score means that this pixel is optimal to embed data. Finally, these visual similarity scores are combined with a weight matrix, and the distortion score that measures the embedding distortion is sent into syndrome-trellis code (STC) to minimize the distortion. Experimental results demonstrate the proposed scheme preserves the visual quality and improves the statistical security. © 2021, Springer Nature Switzerland AG.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Halftone Image Steganography Based on Minimizing Distortion with Pixel Density Transition 7th

Halftone Image Steganography Based on Minimizing Distortion...

引用

7th International Conference on Artificial intelligence and Security, ICAIS 2021

作者： Yu, Mujian Luo, Junwei Xu, Bozhi Chen, Guoliang Lu, Wei School of Computer Science and Engineering Guangdong Key Laboratory of Information Security Technology Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Guangzhou510006 China Guangdong Science and Technology Innovation Monitoring and Research Center Guangzhou510033 China

ISBN: (纸本)9783030786113

Many advanced halftone steganographic schemes focus only on the distortion of human visual perception or the distortion according to statistics. In this paper, a halftone image steganography based on minimizing distortion with density transition is proposed which aims at utilizing the entropy model and pixel density to resist potential steganalysis. First, the entropy model is established on the image database to describe the texture content and transformed to the preliminary distortion score map. Because the form of texture presentation is distinct between halftone images and ordinary binary images, the feature of pixel density is introduced to represent the local intensity in images. Then the pixel density transition adjustment based on the entropy model is presented, which makes the distortion score more reliable. The final additive distortion map is generated by combining the entropy model and the strategy of density transition. To play the advantage of distortion measurement, syndrome-trellis code (STC) is applied with the distortion map to minimize the embedding distortions. Experimental results demonstrate that compared with other halftone steganographic schemes, the proposed method achieves high statistical security and great visual quality with considerable embedding capacity. © 2021, Springer Nature Switzerland AG.

关键词： Pixels

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：