检索结果-内蒙古大学图书馆

LGMamba: Large-Scale ALS Point Cloud Semantic Segmentation With Local and Global State-Space Model

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2025年 22卷

作者： Li, Dilong Zhao, Jing Chang, Chongkei Chen, Ziyi Du, Jixiang Huaqiao Univ Coll Comp Sci & Technol Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Key Lab Data Secur & Blockchain TechnolFuj Xiamen 361021 Peoples R China

The large scale and extensive coverage of point cloud data make large-scale airborne laser scanning (ALS) point cloud semantic segmentation a highly challenging task. Although transformers have shown impressive performance in large-scale point cloud semantic segmentation task, their quadratic complexity limits the processing capacity. To alleviate this issue, we propose Local and Global Mamba (LGMamba)-a novel state-space model (SSM)-based network for large-scale point cloud semantic segmentation. Specifically, we propose Local Mamba module to extract fine-grained local features by effectively capturing local dependencies. Then, we propose Global Mamba module to refine the learned local features by capturing the global long-distance dependencies of whole scenes. The validation of our method on the DALES datasets was conducted. Extensive experimental results demonstrate the effectiveness of LGMamba, with mean intersection over union (mIoU) of 82.3% and overall accuracy (OA) of 97.7% on DALES.

关键词： Point cloud compression Feature extraction Semantic segmentation Training Three-dimensional displays Convolution Transformers Encoding Indexes Semantics Airborne laser scanning (ALS) Mamba semantic segmentation state-space models (SSMs)

来源：评论

学校读者我要写书评

暂无评论

FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild

引用

INTERNATIONAL JOURNAL OF compUTER visION 2024年第8期132卷 2885-2906页

作者： Liu, Zhi-Song Courant, Robin Kalogeiton, Vicky LUT Univ Comp Vis & Pattern Recognit Lab Lappeenranta Finland Ecole Polytech LIX IP Paris Palaiseau France

Automatically understanding funny moments (i.e., the moments that make people laugh) when watching comedy is challenging, as they relate to various features, such as body language, dialogues and culture. In this paper, we propose FunnyNet-W, a model that relies on cross- and self-attention for visual, audio and text data to predict funny moments in videos. Unlike most methods that rely on ground truth data in the form of subtitles, in this work we exploit modalities that come naturally with videos: (a) video frames as they contain visual information indispensable for scene understanding, (b) audio as it contains higher-level cues associated with funny moments, such as intonation, pitch and pauses and (c) text automatically extracted with a speech-to-text model as it can provide rich information when processed by a Large Language Model. To acquire labels for training, we propose an unsupervised approach that spots and labels funny audio moments. We provide experiments on five datasets: the sitcoms TBBT, MHD, MUStARD, Friends, and the TED talk UR-Funny. Extensive experiments and analysis show that FunnyNet-W successfully exploits visual, auditory and textual cues to identify funny moments, while our findings reveal FunnyNet-W's ability to predict funny moments in the wild. FunnyNet-W sets the new state of the art for funny moment detection with multimodal cues on all datasets with and without using ground truth information.

关键词： Multimodal learning vision plus language Video understanding Humor detection

来源：评论

学校读者我要写书评

暂无评论

Local tangent space transfer and alignment for incomplete data

引用

KNOWLEDGE-BASED SYSTEMS 2025年 309卷

作者： Zheng, Yue Wang, Jing Huaqiao Univ Sch Comp Sci & Technol Xiamen 361021 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China

Discovering the intrinsic structure of incomplete data is a significant challenge in machine learning. When data incompleteness results in high sparsity levels and samples exhibiting varying degrees of missing data, traditional data processing methods are often insufficient. We propose Local Tangent Space Transfer and Alignment, a method combining transfer learning and manifold learning. This method aims to discover local information that remains usable even under high levels of data sparsity to facilitate the learning of nonlinear characteristics in regions with high sparsity. The method initially employs a combined strategy of cosine similarity and expected squared Euclidean distance to measure and select neighbors for each sample point. Existing nuclear norm regularization (NNR) methods are utilized to establish the local coordinate system for sample neighborhoods with lower sparsity. By contrast, we introduce a novel NNR model for highly sparse neighborhoods. This model aids in learning nonlinear features through the local tangent space of transferred neighborhoods, thereby enhancing the accuracy of determining the local coordinate system of incomplete data. By aligning the local coordinates, the global coordinates of the incomplete data are ultimately obtained. We demonstrate the effectiveness of this method on simulated and real-world datasets.

关键词： Manifold learning Incomplete data Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Species-Agnostic patterned Animal Re-identification by Aggregating Deep Local Features

引用

INTERNATIONAL JOURNAL OF compUTER visION 2024年第9期132卷 4003-4018页

作者： Nepovinnykh, Ekaterina Chelak, Ilia Eerola, Tuomas Immonen, Veikka Kalviainen, Heikki Kholiavchenko, Maksim Stewart, Charles V. Lappeenranta Lahti Univ Technol LUT Comp Vis & Pattern Recognit Lab Dept Computat Engn Comp Vis & Pattern Recognit Lab POB 20 Lappeenranta 53851 Finland Univ Helsinki Fac Sci Dept Comp Sci POB 4 Helsinki 00100 Finland Rensselaer Polytech Inst Dept Comp Sci Troy NY 12180 USA

Access to large image volumes through camera traps and crowdsourcing provides novel possibilities for animal monitoring and conservation. It calls for automatic methods for analysis, in particular, when re-identifying individual animals from the images. Most existing re-identification methods rely on either hand-crafted local features or end-to-end learning of fur pattern similarity. The former does not need labeled training data, while the latter, although very data-hungry typically outperforms the former when enough training data is available. We propose a novel re-identification pipeline that combines the strengths of both approaches by utilizing modern learnable local features and feature aggregation. This creates representative pattern feature embeddings that provide high re-identification accuracy while allowing us to apply the method to small datasets by using pre-trained feature descriptors. We report a comprehensive comparison of different modern local features and demonstrate the advantages of the proposed pipeline on two very different species.

关键词： computer vision Image processing Animal biometrics Re-identification Ringed seals Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Micro Gesture recognition for Emotion Understanding via Context-Aware visual-Text Contrastive Learning

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 1309-1313页

作者： Li, Deng Xing, Bohao Liu, Xin Lappeenranta Lahti Univ Technol LUT Comp Vis & Pattern Recognit Lab Lappeenranta 53850 Finland Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Lappeenranta Lahti Univ Technol LUT Comp Vis & Pattern Recognit Lab Lappeenranta 53850 Finland

Psychological studies have shown that Micro Gestures (MG) are closely linked to human emotions. MG-based emotion understanding has attracted much attention because it allows for emotion understanding through nonverbal body gestures without relying on identity information (e.g., facial and electrocardiogram data). Therefore, it is essential to recognize MG effectively for advanced emotion understanding. However, existing Micro Gesture recognition (MGR) methods utilize only a single modality (e.g., RGB or skeleton) while overlooking crucial textual information. In this letter, we propose a simple but effective visual-text contrastive learning solution that utilizes text information for MGR. In addition, instead of using handcrafted prompts for visual-text contrastive learning, we propose a novel module called Adaptive prompting to generate context-aware prompts. The experimental results show that the proposed method achieves state-of-the-art performance on two public datasets. Furthermore, based on an empirical study utilizing the results of MGR for emotion understanding, we demonstrate that using the textual results of MGR significantly improves performance by 6%+ compared to directly using video as input.

关键词： Emotion understanding micro gesture recognition multimodality learning

来源：评论

学校读者我要写书评

暂无评论

(MLE²A²U)-Net: Image Super-Resolution via Multi-Level Edge Embedding and Aggregated Attentive Upsampler Network

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN compUTATIONAL INTELLIGENCE 2023年第2期7卷 523-536页

作者： Mehta, Nancy Murala, Subrahmanyam IIT Ropar Dept Elect Engn Comp Vis & Pattern Recognit Lab Rupnagar 140001 Punjab India

Given a degraded low-resolution input image, super-resolution (SR) aims at restoring the lost textures and structures and generating high-resolution image content. Significant advances in image super-resolution have been made lately, dominated by convolutional neural networks (CNNs). The top performing CNN-based SR networks typically employ very deep models for embracing the benefits of generating spatially precise results, but at the cost of loss of long-term contextual information. Additionally, state-of-the-art (SOTA) methods generally lack in maintaining the balance between spatial details and contextual information, which is the basic requirement for exhibiting superior performance in SR task. For restoration application like SR, the overall network generally demands efficient preservation of low-frequency information and reconstruction of high-frequency details. Thus, our work presents a novel architecture with the holistic objective of maintaining spatially-precise representation by collecting contextual content and restoring multi-frequency information throughout the network. Our proposed model learns an enriched set of features, that besides combining contextual information from multiple scales simultaneously preserves the high-resolution spatial details. The core of our approach is a novel non-local and local attention (NLLA) block which focuses on (1) learning enriched features by collecting information from multiple scales, (2) simultaneously handling the different frequency information, and (3) effectively fusing the relevant low-frequency and high-frequency information by ignoring the redundant features. Additionally, for effectively mapping the low-resolution features to high-resolution, we propose a novel aggregated attentive up-sampler (AAU) block that attentively learns the weights to up-sample the refined low-resolution feature maps to high-resolution output. Extensive experiments on the benchmark SR datasets demonstrate that the proposed method a

关键词： Aggregated up-sampling Edge embedding Feature refinement Image super-resolution Multi-scale feature learning

来源：评论

学校读者我要写书评

暂无评论

A deep spatiotemporal network for forecasting the risk of traffic accidents in low-risk regions

引用

NEURAL compUTING & APPLICATIONS 2023年第7期35卷 5207-5220页

作者： Zheng, Junjie Wang, Jing Lai, Zhilin Wang, Cheng Zhang, Huizhen Huaqiao Univ Sch Comp Sci & Technol Xiamen Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Peoples R China

It is admirably significant to forecast real-time traffic risks in the future, which protects people's lives and improves the safety of the road. Most previous work uses the grid method to divide the entire city, which destroys the city's inherent geospatial attributes and may lead to invalid prediction results. On the issue of sparse accidents, although previous studies have considered the imbalance in the number of accidents and normal events, the imbalance in the number of accidents between different regions caused by inner-city heterogeneity is ignored, resulting in unsatisfactory predictions for low-risk regions. Moreover, such a model is not suitable for citywide traffic accident prediction. To solve the above problems, firstly, we combine taxi division map, census track partition map and road network to divide the entire city, which retains the geographical spatial attributes, makes the regional division more reasonable and interpretable, and avoids the possible invalid prediction caused by grid method. Secondly, we propose the concept of double imbalance in traffic accident data, which is addressed by an improved cost-sensitive loss function, enabling the model to better predict accidents in low-risk regions. Finally, a deep spatiotemporal network that fuses local and global features (DSTFLG) based on a self-attention mechanism is proposed to forecast traffic accident risk. Extensive experiments on two real-world datasets demonstrate that the proposed framework improves the prediction accuracy over baseline approaches.

关键词： Double imbalance data Spatial-temporal model Traffic accident risk prediction

来源：评论

学校读者我要写书评

暂无评论

Re-identification of patterned animals by multi-image feature aggregation and geometric similarity

引用

IET compUTER visION 2025年第1期19卷

作者： Nepovinnykh, Ekaterina Immonen, Veikka Eerola, Tuomas Stewart, Charles V. Kalviainen, Heikki Lappeenranta Lahti Univ Technol LUT Dept Computat Engn Comp Vis & Pattern Recognit Lab Lappeenranta Finland Rensselaer Polytech Inst Dept Comp Sci Troy NY 12180 USA

Image-based re-identification of animal individuals allows gathering of information such as population size and migration patterns of the animals over time. This, together with large image volumes collected using camera traps and crowdsourcing, opens novel possibilities to study animal populations. For many species, the re-identification can be done by analysing the permanent fur, feather, or skin patterns that are unique to each individual. In this paper, the authors study pattern feature aggregation based re-identification and consider two ways of improving accuracy: (1) aggregating pattern image features over multiple images and (2) combining the pattern appearance similarity obtained by feature aggregation and geometric pattern similarity. Aggregation over multiple database images of the same individual allows to obtain more comprehensive and robust descriptors while reducing the computation time. On the other hand, combining the two similarity measures allows to efficiently utilise both the local and global pattern features, providing a general re-identification approach that can be applied to a wide variety of different pattern types. In the experimental part of the work, the authors demonstrate that the proposed method achieves promising re-identification accuracies for Saimaa ringed seals and whale sharks without species-specific training or fine-tuning.

关键词： computer vision convolutional neural nets image retrieval pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A deep convolution neural network fusing of color feature and spatio-temporal feature for smoke detection

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第8期83卷 22173-22187页

作者： Ye, Mengqi Luo, Yanmin Huaqiao Univ Coll Comp Sci & Technol Xiamen 361021 Peoples R China Huaqiao Univ Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China

The spatial characteristics, movement characteristics and color characteristics of smoke are important features that distinguish them to other objects. In order to make full use of these three features, we proposed a deep convolutional network called Full High Resolution Network(FHRNet).This network consists of two parts: Spatio-Temporal-aware Sub-network (STS) and Color-aware Sub-network (CS). We build high -resolution residual symmetrical units and embed the two sub-networks to ensure the integrity of two dimensional *** the STS, the residual symmetrical unit extracts the spatial semantic characteristics of smoke from every frame, and combine them into a feature sequence, then the spatio-temporal perceptron is used to extract the spatio-temporal characteristics of smoke to further improve the characteristic expression. In the CS, the color feature of picture is converted into color feature matrix, which is easier to make the residual symmetrical unit to extract the color feature of smoke. We constructed a smoke vedio datasets which have a diverse background to avoid producing over-fitting *** experimental results show that mthod we proposed can effectively extract the color features and the spatio-temporal features of smoke and our method can effectively detect smoke.

关键词： smoke detection color feature matrix spatio-temporal features full high resolution

来源：评论

学校读者我要写书评

暂无评论

SA-GCN: structure-aware graph convolutional networks for crowd pose estimation

引用

JOURNAL OF SUPERcompUTING 2023年第9期79卷 10046-10062页

作者： Wang, Jia Luo, Yanmin Huaqiao Univ Coll Comp Sci & Technol Xiamen 361021 Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China

In this paper, we aim to capture the structure dependency of human joints and improve the localization accuracy of invisible joints. We propose a novel framework: Structure-aware Graph Convolutional Network (SA-GCN) for crowd pose estimation, which can be divided into two components: Sample Pose Net and Refined Pose Net. Firstly, Sample Pose Net includes a multi-scale feature fusion module, which uses multi-scale features to capture small-scale characters and extract the global "rough" pose as much as possible. Secondly, channel and spatial attention are injected into the multi-scale feature fusion module to strengthen the characteristics of small-scale characters. Finally, graph convolution obtained by the disentangled several parallel sub-graph convolution modules in Refined Pose Net. Global and structural advantages of graph convolution are more conducive to predicting difficult points in sample Pose. In addition, SA-GCN obtains lower parameters compared with the popular pose estimation networks. By which, we apply a novel framework SA-GCN to get feature maps for proposal and refinement, respectively. comprehensive experiments demonstrate that the proposed method achieves superior pose estimation results on two benchmark datasets, CrowdPose and MSCOCO. Moreover, SA-GCN significantly outperforms state-of-the-art performance on CrowdPose and almost always generates plausible human pose predictions.

关键词： Human pose estimation keypoint heatmap Graph convolutional networks (GCN) Structure-aware (SA)

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：