检索结果-内蒙古大学图书馆

IEEE Winter Conference on Applications of computer vision (WACV)

作者： Patil, Prashant W. Dudhane, Akshay Murala, Subrahmanyam Indian Inst Technol Ropar Comp Vis & Pattern Recognit Lab Rupnagar India

ISBN: (纸本)9780738142661

Moving object segmentation (MOS) in different practical scenarios like weather degraded, dynamic background, etc. videos is a challenging and high demanding task for various computer vision applications. Existing supervised approaches achieve remarkable performance with complicated training or extensive fine-tuning or inappropriate training-testing data distribution. Also, the generalized effect of existing works with completely unseen data is difficult to identify. In this work, the recurrent feature sharing based generative adversarial network is proposed with unseen video analysis. The proposed network comprises of dilated convolution to extract the spatial features at multiple scales. Along with the temporally sampled multiple frames, previous frame output is considered as input to the network. As the motion is very minute between the two consecutive frames, the previous frame decoder features are shared with encoder features recurrently for current frame foreground segmentation. This recurrent feature sharing of different layers helps the encoder network to learn the hierarchical interactions between the motion and appearance-based features. Also, the learning of the proposed network is concentrated in different ways, like disjoint and global training-testing for MOS. An extensive experimental analysis of the proposed network is carried out on two benchmark video datasets with seen and unseen MOS video. Qualitative and quantitative experimental study shows that the proposed network outperforms the existing methods.

关键词： Training computer vision Convolution Motion segmentation Object segmentation Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

labelWords are Anchors: An Information Flow Perspective for Understanding In-Context Learning

LabelWords are Anchors: An Information Flow Perspective for ...

引用

Conference on Empirical Methods in Natural Language Processing (EMNLP)

作者： Wang, Lean Li, Lei Dai, Damai Che, Deli Zho, Hao Meng, Fandong Zhou, Jie Sun, Xu Peking Univ Sch Comp Sci Natl Key Lab Multimedia Informat Proc Beijing Peoples R China Tencent Inc Pattern Recognit Ctr WeChat AI Beijing Peoples R China

ISBN: (纸本)9798891760608

In-context learning (ICL) emerges as a promising capability of large language models (LLMs) by providing them with demonstration examples to perform diverse tasks. However, the underlying mechanism of how LLMs learn from the provided context remains under-explored. In this paper, we investigate the working mechanism of ICL through an information flow lens. Our findings reveal that label words in the demonstration examples function as anchors: (1) semantic information aggregates into label word representations during the shallow computation layers' processing;(2) the consolidated information in label words serves as a reference for LLMs' final predictions. Based on these in-sights, we introduce an anchor re-weighting method to improve ICL performance, a demonstration compression technique to expedite inference, and an analysis framework for diagnosing ICL errors in GPT2-XL. The promising applications of our findings again validate the uncovered ICL working mechanism and pave the way for future studies.

关键词： Anchors

来源：评论

学校读者我要写书评

暂无评论

Low-light image enhancement with quality-oriented pseudo labels via semi-supervised contrastive learning

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 276卷

作者： Jiang, Nanfeng Cao, Yiwen Zhang, Xu-Yao Wang, Da-Han He, Yifan Wang, Chiming Zhu, Shunzhi Xiamen Univ Technol Sch Comp & Informat Engn Fujian Key Lab Pattern Recognit & Image Understand Xiamen Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Reconova Technol Co Ltd Xiamen Key Lab Visual Percept Technol & Applicat Xiamen Peoples R China

Existing Low-Light Image Enhancement (LLIE) methods exhibit limitations when applied to complex scenes, primarily due to the lack of adaptation to real-world and synthetic images. To address this issue, we introduce a novel approach that leverages the mean-teacher strategy and contrastive regularization within a Contrastive Semi-Learning Network (CSL-Net). Specially, our CSL-Net employs high-quality pseudo labels to significantly improve model robustness and generalization. The novelties of this paper lie in: (1) We utilize a score- pool to store teacher's and student's outputs during training. After that, we propose a monotonic strategy to determine the most reliable Non-Reference Image Quality Assessment (NR-IQA) metric, which provides effective evaluations and determines the optimal output as the pseudo-label. (2) We integrate this selected pseudo-label with a contrastive loss to provide auxiliary information that mitigates overfitting issues and guides student towards generating realistic images. (3) In network design, we incorporate illumination and gradient priors to refine color appearance and detail preservation, facilitated by several elaborated modules, including Contextual Refinement Blocks (CRBs), Non-Local Dynamic Attention (NLDA) and Illumination Perceptual Enhancer (IPE). Experimental results on popular datasets demonstrate that the enhancement quality can be significantly improved by our proposed method.

关键词： Low-light image enhancement Semi-supervised learning Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Multiple Source Translation Micro-CT Improves Both Field-of-View and Spatial Resolution

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Yu, Haijun Ni, Song Thies, Mareike Wagner, Fabian Huang, Yixing Liu, Fengling Maier, Andreas Chongqing Univ Key Lab Optoelect Technol & Syst Minist Educ Chongqing 400044 Peoples R China Friedrich Alexander Univ Erlangen Nuremberg Dept Comp Sci Pattern Recognit Lab D-91058 Erlangen Germany Friedrich Alexander Univ Erlangen Nuremberg Univ Hosp Erlangen Dept Radiat Oncol D-91054 Erlangen Germany

Object rotation is a classical data acquisition mode in microcomputed tomography (micro-CT) to capture radiographs from different angles for high-resolution 3-D reconstruction. However, this mode encounters two primary limitations: first, an undesired tradeoff arises between the field-of-view (FOV) and the spatial resolution;second, the spatial resolution is compromised due to insufficient radial sampling in the frequency domain. In this article, we present a novel acquisition paradigm called multiple Source Translations micro-CT (mSTCT) to simultaneously improve FOV and spatial resolution. In mSTCT, the FOV is enlarged by extending the source translation distance and the spatial resolution is enhanced by refining the source sample spacing to increase the radial sampling in the frequency domain. Theoretically, mSTCT can enhance the FOV and spatial resolution to their physical limits. We formulate a central slice theorem for mSTCT to elucidate its fundamental principle. Subsequently, we derive a corresponding analytical algorithm without projection rebinning or stitching for reconstruction. The physical experiments conducted in this work validate the efficacy of mSTCT in terms of FOV extension and spatial resolution enhancement. As mSTCT is trivial to implement, it holds considerable promise for diverse scenarios demanding high-resolution and large FOV in nondestructive testing (NDT) applications.

关键词： Spatial resolution Detectors Geometry Fourier transforms Frequency-domain analysis computed tomography Trajectory Data sampling field-of-view (FOV) microcomputed tomography (micro-CT) scanning mode spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Text-Video Knowledge Guided Prompting for Weakly Supervised Temporal Action Localization

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第5期35卷 4184-4197页

作者： Shao, Yuxiang Zhang, Feifei Xu, Changsheng Tianjin Univ Technol Sch Comp Sci & Engn Tianjin 300384 Peoples R China Tianjin Univ Technol Sch Comp Sci & Engn Minist Educ Tianjin 300384 Peoples R China Tianjin Univ Technol Key Lab Comp Vis & Syst Minist Educ Tianjin 300384 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peng Cheng Lab Shenzhen 518066 Peoples R China

Weakly supervised temporal action localization (WTAL) aims to localize action instances with only video-level labels for supervision. Recent methods convert category labels to natural language through prompting and utilize pre-trained vision-language models to generate text representation from natural language for supervision. This is because natural language can provide more prosperous and generalized semantic supervision to compensate for the lack of supervision in weakly supervised scenarios. However, it should be noted that current prompting methods face limitations in generating dynamic prompts that adapt to each video, which leads to difficulties in accurately aligning text and video representations. In this work, we propose a novel Text-Video Knowledge Guided Prompting (TVKP) framework for WTAL, which generates video-aware prompts based on text-video knowledge to enhance semantic alignment between text and video representations and introduce more video-related external category labels to enrich semantic supervision. We introduce the video-aware prompting (VAP) module to learn text-video knowledge from the joint distribution of text and video representations to generate video-aware text representation. Meanwhile, to make VAP more effectively learn text-video knowledge, a text-video contrastive loss is proposed to ensure semantic consistency between text and video representations. In addition, we propose the external knowledge prompting (EKP) module to introduce more video-related text labels from an external knowledge base to enrich prompts for accurate semantic alignment. Extensive experiments are conducted on three public datasets, THUMOS14, ActivityNet1.2, and ActivityNet1.3, demonstrating that our approach outperforms state-of-the-art methods.

关键词： Semantics visualization Location awareness Knowledge based systems Annotations Circuits and systems Training Probabilistic logic Natural languages Measurement Weakly-supervised temporal action localization prompting external knowledge

来源：评论

学校读者我要写书评

暂无评论

ES6D: A computation Efficient and Symmetry-Aware 6D Pose Regression Framework

ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Reg...

引用

IEEE/CVF Conference on computer vision and pattern recognition (CVPR)

作者： Mo, Ningkai Gan, Wanshui Yokoya, Naoto Chen, Shifeng Chinese Acad Sci Shenzhen Inst Adv Technol ShenZhen Key Lab Comp Vis & Pattern Recognit Shenzhen Peoples R China Univ Tokyo Tokyo Japan RIKEN Tokyo Japan

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

In this paper, a computation efficient regression framework is presented for estimating the 6D pose of rigid objects from a single RGB-D image, which is applicable to handling symmetric objects. This framework is designed in a simple architecture that efficiently extracts point-wise features from RGB-D data using a fully convolutional network, called XYZNet, and directly regresses the 6D pose without any post refinement. In the case of symmetric object, one object has multiple ground-truth poses, and this one-to-many relationship may lead to estimation ambiguity. In order to solve this ambiguity problem, we design a symmetry-invariant pose distance metric, called average (maximum) grouped primitives distance or A(M)GPD. The proposed A(M)GPD loss can make the regression network converge to the correct state, i.e., all minima in the A(M)GPD loss surface are mapped to the correct poses. Extensive experiments on YCB-Video and TLESS datasets demonstrate the proposed framework's substantially superior performance in top accuracy and low computational cost. The relevant code is available in https://***/GANWANSHUI/***.

关键词： Convolutional codes Measurement computer vision Pose estimation Robot vision systems Data visualization computer architecture

来源：评论

学校读者我要写书评

暂无评论

Pose attention and object semantic representation-based human-object interaction detection network

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第27期81卷 39453-39470页

作者： Deng, Wei-Mo Zhang, Hong-Bo Lei, Qing Du, Ji-Xiang Huang, Min Huaqiao Univ Sch Comp Sci & Technol Xiamen 361000 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361000 Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361000 Peoples R China Xiamen Univ Coll Humanities Xiamen 361000 Peoples R China

Human-object interaction (HOI) detection is a core problem in human-centric scene understanding, which is devoted to inferring triplets between humans and objects. Previous works mainly determine the interaction of e... 详细信息

Human-object interaction (HOI) detection is a core problem in human-centric scene understanding, which is devoted to inferring triplets < human, verb, object > between humans and objects. Previous works mainly determine the interaction of each human-object pair by performing joint inference based on multiple features. In this paper, we design more discriminative representation of the human-object pair and a more effective HOI detection model. On the one hand, we use human poses as an attention mechanism to strengthen features, which is a novel way to deal with human poses in HOI detection. On the other hand, for a more effective representation of objects, a word vector is used to encode objects, and the relation features of humans and objects are captured by a graph convolution network based on object word vectors and human appearance features. These relation features are also strengthened by a human pose attention mechanism. Our model yields favorable results compared to the state-of-the-art HOI detection algorithms on two large-scale benchmark datasets, V-COCO and HICO-DET.

关键词： Human-object interaction detection Pose attention Object semantic Relation feature

来源：评论

学校读者我要写书评

暂无评论

Relation-Aggregated Cross-Graph Correlation Learning for Fine-Grained Image-Text Retrieval

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第2期35卷 2194-2207页

作者： Peng, Shu-Juan He, Yi Liu, Xin Cheung, Yiu-ming Xu, Xing Cui, Zhen Huaqiao Univ Dept Artificial Intelligence Xiamen 361021 Peoples R China Key Lab Pattern Recognit & Comp Vis Xiamen 361021 Peoples R China Huaqiao Univ Fujian Prov Univ Key Lab Comp Vis & Machine Learning Xiamen 361021 Peoples R China Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Peoples R China Huaqiao Univ Dept Comp Sci Xiamen 361021 Peoples R China Zhejiang Lab Artificial Intelligence Res Inst Hangzhou 311121 Peoples R China Hong Kong Baptist Univ Dept Comp Sci Hong Kong Peoples R China Univ Elect Sci & Technol China Ctr Future Multimedia Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China

Fine-grained image-text retrieval has been a hot research topic to bridge the vision and languages, and its main challenge is how to learn the semantic correspondence across different modalities. The existing methods mainly focus on learning the global semantic correspondence or intramodal relation correspondence in separate data representations, but which rarely consider the intermodal relation that interactively provide complementary hints for fine-grained semantic correlation learning. To address this issue, we propose a relation-aggregated cross-graph (RACG) model to explicitly learn the fine-grained semantic correspondence by aggregating both intramodal and intermodal relations, which can be well utilized to guide the feature correspondence learning process. More specifically, we first build semantic-embedded graph to explore both fine-grained objects and their relations of different media types, which aim not only to characterize the object appearance in each modality, but also to capture the intrinsic relation information to differentiate intramodal discrepancies. Then, a cross-graph relation encoder is newly designed to explore the intermodal relation across different modalities, which can mutually boost the cross-modal correlations to learn more precise intermodal dependencies. Besides, the feature reconstruction module and multihead similarity alignment are efficiently leveraged to optimize the node-level semantic correspondence, whereby the relation-aggregated cross-modal embeddings between image and text are discriminatively obtained to benefit various image-text retrieval tasks with high retrieval performance. Extensive experiments evaluated on benchmark datasets quantitatively and qualitatively verify the advantages of the proposed framework for fine-grained image-text retrieval and show its competitive performance with the state of the arts.

关键词： Semantics Correlation visualization Electronic mail Task analysis Media Feature extraction Cross-graph relation encoder fine-grained correspondence image-text retrieval intermodal relation

来源：评论

学校读者我要写书评

暂无评论

Illumination Distillation Framework for Nighttime Person Re-Identification and a New Benchmark

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 406-419页

作者： Lu, Andong Zhang, Zhang Huang, Yan Zhang, Yifan Li, Chenglong Tang, Jin Wang, Liang Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Anhui Univ Sch Artificial Intelligence Informat Mat & Intelligent Sensing Lab Anhui Prov Anhui Prov Key Lab Multimodal Cognit Computat Hefei 230601 Peoples R China

Nighttime person Re-ID (person re-identification in the nighttime) is a very important and challenging task for visual surveillance but it has not been thoroughly investigated. Under the low illumination condition, the performance of person Re-ID methods usually sharply deteriorates. To address the low illumination challenge in nighttime person Re-ID, this article proposes an Illumination Distillation Framework (IDF), which utilizes illumination enhancement and illumination distillation schemes to promote the learning of Re-ID models. Specifically, IDF consists of a master branch, an illumination enhancement branch, and an illumination distillation module. The master branch is used to extract the features from a nighttime image. The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features. However, nighttime and enhanced features usually contain data noise due to unstable lighting conditions and enhancement failures. To fully exploit the complementary benefits of nighttime and enhanced features while suppressing data noise, we propose an illumination distillation module. In particular, the illumination distillation module fuses the features from two branches through a bottleneck fusion model and then uses the fused features to guide the learning of both branches in a distillation manner. In addition, we build a real-world nighttime person Re-ID dataset, named Night600, which contains 600 identities captured from different viewpoints and nighttime illumination conditions under complex outdoor environments. Experimental results demonstrate that our IDF can achieve state-of-the-art performance on two nighttime person Re-ID datasets (i.e., Night600 and Knight).

关键词： Bottleneck fusion computer vision illumination distillation image enhancement person re-identification

来源：评论

学校读者我要写书评

暂无评论

Attribute graph clustering via transformer and graph attention autoencoder

引用

INTELLIGENT DATA ANALYSIS 2025年第2期29卷 306-319页

作者： Weng, Wei Hou, Fengxia Gong, Shengchao Chen, Fen Lin, Dongsheng Xiamen Univ Technol Coll Comp & Informat Engn 600 Ligong Rd Xiamen 361024 Peoples R China Xiamen Univ Technol Fujian Key Lab Pattern Recognit & Image Understand Xiamen Peoples R China Xiamen Fuyun Informat Tech Co Xiamen Peoples R China

Graph clustering is a crucial technique for partitioning graph data. Recent research has concentrated on integrating topology and attribute information from attribute graphs to generate node embeddings, which are subsequently clustered using classical algorithms. However, these methods have some limitations, such as insufficient information inheritance in shallow networks or inadequate quality of reconstructed nodes, leading to suboptimal clustering performance. To tackle these challenges, we introduce two normalization techniques within the graph attention autoencoder framework, coupled with an MSE loss, to facilitate node embedding learning. Furthermore, we integrate Transformers into the self-optimization module to refine node embeddings and clustering outcomes. Our model can induce appropriate node embeddings for graph clustering in a shallow network. Our experimental results demonstrate that our proposed approach outperforms the state-of-the-art in graph clustering over multiple benchmark datasets. In particular, we achieved 76.3% accuracy on the Pubmed dataset, an improvement of at least 7% compared to other methods.

关键词： Attribute graph clustering transformer autoencoder node embedding

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：