检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Shun Fang Zhengqin Xu Shiqian Wu Shoulie Xie School of Information Science and Engineering Wuhan University of Science and Technology China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial Systems Signal Processing RF & Optical Dept. Institute for Infocomm Research A*STAR Singapore

Robust principal component analysis (RPCA) is widely studied in computer vision. Recently an adaptive rank estimate based RPCA has achieved top performance in low-level vision tasks without the prior rank, but both the rank estimate and RPCA optimization algorithm involve singular value decomposition, which requires extremely huge computational resource for large-scale matrices. To address these issues, an efficient RPCA (eRPCA) algorithm is proposed based on block Krylov iteration and CUR decomposition in this paper. Specifically, the Krylov iteration method is employed to approximate the eigenvalue decomposition in the rank estimation, which requires $O(ndrq+n(rq)^{2})$ for an $(n\times d)$ input matrix, in which $q$ is a parameter with a small value, $r$ is the target rank. Based on the estimated rank, CUR decomposition is adopted to replace SVD in updating low-rank matrix component, whose complexity reduces from $O(rnd)$ to $O(r^{2}n)$ per iteration. Experimental results verify the efficiency and effectiveness of the proposed eRPCA over the state-of-the-art methods in various low-level vision applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenge-Aware RGBT Tracking 1

引用

16th European Conference on computer Vision, ECCV 2020

作者： Li, Chenglong Liu, Lei Lu, Andong Ji, Qing Tang, Jin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (数字)9783030585426

ISBN: (纸本)9783030585419

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware neural network to handle the modality-shared challenges (e.g., fast motion, scale variation and occlusion) and the modality-specific ones (e.g., illumination variation and thermal crossover) for RGBT tracking. In particular, we design several parameter-shared branches in each layer to model the target appearance under the modality-shared challenges, and several parameter-independent branches under the modality-specific ones. Based on the observation that the modality-specific cues of different modalities usually contains the complementary advantages, we propose a guidance module to transfer discriminative features from one modality to another one, which could enhance the discriminative ability of some weak modality. Moreover, all branches are aggregated together in an adaptive manner and parallel embedded in the backbone network to efficiently form more discriminative target representations. These challenge-aware branches are able to model the target appearance under certain challenges so that the target representations can be learnt by a few parameters even in the situation of insufficient training data. From the experimental results we will show that our method operates at a real-time speed while performing well against the state-of-the-art methods on three benchmark datasets. © 2020, Springer Nature Switzerland AG.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

RGB-T Saliency Detection via Robust Graph Learning and Collaborative Manifold Ranking 14th

RGB-T Saliency Detection via Robust Graph Learning and Colla...

引用

14th International Conference on Bio-inspired computing: Theories and Applications, BIC-TA 2019

作者： Sun, Dengdi Li, Sheng Ding, Zhuanlian Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China School of Internet Anhui University Hefei230039 China

ISBN: (纸本)9789811534140

Visual saliency detection inspired by brain cognitive mechanisms is an important component of computer vision, aiming at automatically highlight salient visual objects from the image background. In complex real scenarios, integrating multiple different yet complementary feature representations has been proved to be an effective way for boosting saliency detection performance. In this paper, we propose a novel collaborative algorithm for saliency detection by adaptively incorporating information from grayscale and thermal images. Specifically, we first construct an affinity graph model via robust graph learning to characterize the feature similarities and location relationships between two different image patches under each modal. Based on these affinity graphs, a collaborative manifold ranking method cross-modality consistent constraints is designed to effectively and efficiently infer the salient score for each patch. Moreover, we introduce a weight for each modality to describe the reliability, and integrate them into the graph-based manifold ranking scheme to achieve an adaptive weighted fusion of different source data. For optimization, we propose some iterative algorithms to efficiently solve the models with several subproblems. Experiments on the grayscale-thermal datasets demonstrate the superior performance of the new method over the state-of-the-art approaches. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Dual-Graph Regularized Sparse Low-Rank Matrix Recovery for Tag Refinement 14th

Dual-Graph Regularized Sparse Low-Rank Matrix Recovery for T...

引用

14th International Conference on Bio-inspired computing: Theories and Applications, BIC-TA 2019

作者： Sun, Dengdi Bao, Yuanyuan Ge, Meiling Ding, Zhuanlian Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China School of Internet Anhui University Hefei230039 China

ISBN: (纸本)9789811534140

In recent years, extremely large amounts of images with manual tags are easily available in many social websites such as Twitter, Flickr, and Instagram. However, these user-provided tags are often imprecise and incomplete, which inevitably limits the performances of image retrieval and other related applications. To this end, tag refitment technology aims at improving the quality of images tags automatically, and has been a fundamental challenge in Internet era. In this paper, we propose a novel dual-graph regularized sparse low-rank matrix recovery method, referred to as DGSLR briefly, to infer and improve the manual tags. Specifically, our DGSLR model first suppress the sparse noisy tags by norm, and decompose simultaneously the residual low-rank matrix to learning the low-dimensional vector representations of images and tags. Moreover, the visual similarities and the tag pairwise correlation are fully exploited to smooth the decomposition results by using the dual lapalcian graph regularization terms. For optimization, an improved alternative iteration strategy is designed to solve the resulting objective function. Extensive experiments on the tasks of tag refinement demonstrate the superior performance of the proposed algorithms over several representative methods, especially when the manual tag data is highly noisy and sparse. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Zijian Zhu Yichi Zhang Hai Chen Yinpeng Dong Shu Zhao Wenbo Ding Jiachen Zhong Shibao Zheng Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Dept. of Comp. Sci. and Tech. THBI Lab Institute for AI Tsinghua University BNRist Center Zhongguancun Laboratory Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province School of Computer Science and Technology Anhui University SAIC Motor AI Lab

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DMNER: Biomedical Named Entity Recognition by Detection and Matching

DMNER: Biomedical Named Entity Recognition by Detection and ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Junyi Bian Rongze Jiang Weiqi Zhai Tianyang Huang Xiaodi Huang Hong Zhou Shanfeng Zhu School of Computer Science Fudan University Shanghai China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China School of Computing Mathematics and Engineering Charles Sturt University New South Wales Australia Atypon Systems LLC UK Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Zhangjiang Fudan International Innovation Center Fudan University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Biomedical Named Entity Recognition (NER) is a crucial task in extracting information from biomedical texts. However, the diversity of professional terminology, semantic complexity, and the widespread presence of synonyms pose significant challenges. Traditional methods that rely on sequence labeling training datasets often struggle to handle these complexities. To address this, we introduce a novel framework for BioNER, termed DMNER, which leverages external knowledge and operates in two steps: entity boundary detection and entity category identification through matching. The core of DMNER is its second step, which determines the entity category by retrieving similar entities and their categories from a knowledge dictionary using semantic similarity matching. Our experiments on 10 biomedical datasets demonstrate that DMNER outperforms baselines across these tasks, proving its effectiveness and adaptability. DMNER is versatile and can be applied to various NER tasks, including supervised NER, distantly supervised NER, and NER on multiple datasets with disjoint label sets. The DMNER code is publicly available 1 .

关键词： Training Dictionaries Codes Semantics Named entity recognition Complexity theory labeling Data mining Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Learning Sequence Descriptor based on Spatio-Temporal Attention for Visual Place Recognition

arXiv

引用

arXiv 2023年

作者： Zhao, Junqiao Zhang, Fenglin Cai, Yingfeng Tian, Gengxuan Mu, Wenjie Ye, Chen Feng, Tiantian Department of Computer Science and Technology School of Electronics and Information Engineering Tongji University Shanghai China The MOE Key Lab of Embedded System and Service Computing Tongji University Shanghai China Institute of Intelligent Vehicles Tongji University Shanghai China School of Surveying and Geo-Informatics Tongji University Shanghai China

Visual Place Recognition (VPR) aims to retrieve frames from a geotagged database that are located at the same place as the query frame. To improve the robustness of VPR in perceptually aliasing scenarios, sequence-based VPR methods are proposed. These methods are either based on matching between frame sequences or extracting sequence descriptors for direct retrieval. However, the former is usually based on the assumption of constant velocity, which is difficult to hold in practice, and is computationally expensive and subject to sequence length. Although the latter overcomes these problems, existing sequence descriptors are constructed by aggregating features of multiple frames only, without interaction on temporal information, and thus cannot obtain descriptors with spatio-temporal discrimination. In this paper, we propose a sequence descriptor that effectively incorporates spatio-temporal information. Specifically, spatial attention within the same frame is utilized to learn spatial feature patterns, while attention in corresponding local regions of different frames is utilized to learn the persistence or change of features over time. We use a sliding window to control the temporal range of attention and use relative positional encoding to construct sequential relationships between different features. This allows our descriptors to capture the intrinsic dynamics in a sequence of frames. Comprehensive experiments on challenging benchmark datasets show that the proposed approach outperforms recent state-of-the-art methods. The code is available at https://***/tiev-tongji/Spatio-Temporal-SeqVPR. Copyright © 2023, The Authors. All rights reserved.

关键词： Query processing

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird’s-Eye-View Representations in Autonomous Driving

arXiv

引用

arXiv 2023年

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province China SAIC Motor AI Lab China Zhongguancun Laboratory China

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDAR fusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. Code available at https: //***/zzj403/BEV_Robust. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Global-Local Attention Network for Semantic Segmentation in Aerial Images

Global-Local Attention Network for Semantic Segmentation in ...

引用

International Conference on Pattern Recognition

作者： Minglong Li Lianlei Shan Xiaobin Li Yang Bai Dengji Zhou Weiqiang Wang Ke Lv Bin Luo Si-Bao Chen University of Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Science Beijing China MOE Key Lab of Signal Processing and Intelligent Computing School of Computer Science and Technology Anhui University Hefei China

Errors in semantic segmentation could be classified into two types: the large area misclassification and inaccurate local boundaries. Previously attention-based methods typically capture rich global contextual information, which benefits the large area classification but cannot address the local errors of boundaries. In this paper, we propose a Global-Local Attention Network (GLANet) which can simultaneously consider the global context and local details. Specifically, our GLANet consists of two branches: (1) the global attention branch and (2) local attention branch. Furthermore, three different modules are embedded in GLANet for respectively modelling the semantic interdependencies in spatial, channel and boundary dimension. Lastly, we merge the outputs of different branches to enhance the feature representation further, resulting in more precise segmentation. Overall, the proposed method achieves the competitive segmentation accuracy on two public aerial image datasets, bringing significant improvements over the existing baselines.

关键词： Image segmentation Image color analysis Image edge detection Semantics Vegetation mapping Vegetation Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity Recognition

arXiv

引用

arXiv 2024年

作者： Bian, Junyi Zhai, Weiqi Huang, Xiaodi Zheng, Jiaxuan Zhu, Shanfeng School of Computer Science Fudan University Shanghai200433 China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University China Ministry of Education Shanghai200433 China MOE Frontiers Center for Brain Science Fudan University Shanghai200433 China Zhangjiang Fudan International Innovation Center Shanghai200433 China Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai200433 China School of Computing and Mathematics Charles Sturt University AlburyNSW2640 Australia

Prevalent solution for BioNER involves using representation learning techniques coupled with sequence labeling. However, such methods are inherently task-specific, demonstrate poor generalizability, and often require dedicated model for each dataset. To leverage the versatile capabilities of recently remarkable large language models (LLMs), several endeavors have explored generative approaches to entity extraction. Yet, these approaches often fall short of the effectiveness of previouly sequence labeling approaches. In this paper, we utilize the open-sourced LLM LLaMA2 as the backbone model, and design specific instructions to distinguish between different types of entities and datasets. By combining the LLM’s understanding of instructions with sequence labeling techniques, we use mix of datasets to train a model capable of extracting various types of entities. Given that the backbone LLMs lacks specialized medical knowledge, we also integrate external entity knowledge bases and employ instruction tuning to compel the model to densely recognize carefully curated entities. Our model VANER, trained with a small partition of parameters, significantly outperforms previous LLMs-based models and, for the first time, as a model based on LLM, surpasses the majority of conventional state-of-the-art BioNER systems, achieving the highest F1 scores across three datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational linguistics

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：