检索结果-内蒙古大学图书馆

Multi-skeleton structures graph convolutional network for action quality assessment in long videos

APPLIED INTELLIGENCE 2023年第19期53卷 21692-21705页

作者： Lei, Qing Li, Huiying Zhang, Hongbo Du, Jixiang Gao, Shangce Huaqiao Univ Dept Comp Sci & Technol Xiamen 361000 Fujian Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361000 Fujian Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361000 Fujian Peoples R China Univ Toyama Fac Engn Toyama 9308555 Japan

In most existing action quality assessment (AQA) methods, how to score simple actions in short-term sport videos has been widely explored. Recently, a few studies have attempted to solve the AQA problem of long-duration activity by extracting dynamic or static information directly from RGB video. However, these methods may ignore specific postures defined by dynamic changes in human body joints, which makes the results inaccurate and unexplainable. In this work, we propose a novel graph convolution network based on multiple skeleton structure modelling to address the problem of effective pose feature learning to improve the performance of AQA in complex activity. Specifically, three kinds of skeleton structures, including the joints' self-connection, the intra-part connection, and the inter-part connection, are defined to model the motion patterns of joints and body parts. Moreover, a temporal attention learning module is designed to extract temporal relations between skeleton subsequences. We evaluate the proposed method on two benchmark datasets, the MIT-skate dataset and the Rhythmic Gymnastics dataset. Extensive experiments are conducted to verify the effectiveness of the proposed method. The experimental results show that our method achieves state-of-the-art performance.

关键词： Action quality assessment Graph convolutional network Long sport videos

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Cross-Modal Anomaly Detection Using Triple-Adaptive Network and Bi-Quintuple Contrastive Learning

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN compUTATIONAL INTELLIGENCE 2024年第1期8卷 697-709页

作者： Peng, Shu-Juan Fan, Ye Cheung, Yiu-ming Liu, Xin Cui, Zhen Li, Taihao Huaqiao Univ Dept Artificial Intelligence Xiamen 361021 Peoples R China Artificial Intelligence Res Inst Zhejiang Lab Hangzhou 311121 Peoples R China Fujian Prov Univ Huaqiao Univ Key Lab Comp Vis & Machine Learning Xiamen 361021 Peoples R China Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen 361021 Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen 361021 Peoples R China Hong Kong Baptist Univ Dept Comp Sci Hong Kong Peoples R China Nanjing Univ Sci & Technol Key Lab Intelligent Percept & Syst High Dimens Inf Minist Educ Nanjing 210094 Peoples R China

Cross-modal anomaly detection is a relatively new and challenging research topic in machine learning field, which aims at identifying the anomalies whose patterns are disparate across different modalities. As far as we know, this topic has yet to be well studied, and existing works often suffer from the incomplete anomalous data detection and low data utilization problems. To alleviate these limitations, this paper proposes an efficient deep cross-modal anomaly detection approach via Triple-adaptive Network and Bi-quintuple Contrastive Learning (TN-BCL), which lies among the earliest attempt to detect various cross-modal anomalies within the heterogeneous multi-modal data. To be specific, a triple-adaptive network is explicitly designed to identify various anomalies, whose patterns are disparate in both single-modal scenario and cross-modal scenario. On the one hand, the top branch network is utilized to adaptively detect the attribute anomalies and part of mixed anomalies in multi-modal data samples. On the other hand, the bottom two-branch network, with shared residual blocks, is leveraged to learn the discriminative cross-modal embeddings. At the same time, an efficient bi-quintuple contrastive learning method is designed to enhance the feature correlation between the same attribute data, while maximally enlarging the feature difference between different attribute data. Besides that, the bidirectional learning scheme is employed to significantly improve the data utilization. Through the joint exploitation of the above, different kinds of anomalous samples can be well detected across different modalities. Extensive experiments show that the proposed framework outperforms the state-of-the-art competing methods, with a large improvement margin.

关键词： Anomaly detection Detectors Behavioral sciences Feature extraction Task analysis Electronic mail computer science Cross-modal anomaly detection triple-adaptive network bi-quintuple contrastive learning shared residual block

来源：评论

学校读者我要写书评

暂无评论

Multi-feature fusion refine network for video captioning

引用

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE 2022年第3期34卷 483-497页

作者： Wang, Guan-Hong Du, Ji-Xiang Zhang, Hong-Bo Huaqiao Univ Dept Comp Sci & Technol Xiamen Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Peoples R China

Describing video content using natural language is an important part of video understanding. It needs to not only understand the spatial information on video, but also capture the motion information. Meanwhile, video captioning is a cross-modal problem between vision and language. Traditional video captioning methods follow the encoder-decoder framework that transfers the video to sentence. But the semantic alignment from sentence to video is ignored. Hence, finding a discriminative visual representation as well as narrowing the semantic gap between video and text has great influence on generating accurate sentences. In this paper, we propose an approach based on multi-feature fusion refine network (MFRN), which can not only capture the spatial information and motion information by exploiting multi-feature fusion, but also can get better semantic aligning of different models by designing a refiner to explore the sentence to video stream. The main novelties and advantages of our method are: (1) multi-feature fusion: Both two-dimension convolutional neural networks and three-dimension convolutional neural networks pre-trained on ImageNet and Kinetic respectively are used to construct spatial information and motion information, and then fused to get better visual representation. (2) Sematic alignment refiner: the refiner is designed to restrain the decoder and reproduce the video features to narrow semantic gap between different modal. Experiments on two widely used datasets demonstrate our approach achieves state-of-the-art performance in terms of BLEU@4, METEOR, ROUGE and CIDEr metrics.

关键词： Video captioning multi-feature fusion refine network semantic alignment

来源：评论

学校读者我要写书评

暂无评论

Improved human-object interaction detection through skeleton-object relations

引用

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE 2022年第1期34卷 41-52页

作者： Zhang, Hong-Bo Zhou, Yi-Zhong Du, Ji-Xiang Huang, Jin-Long Lei, Qing Yang, Lijie Huaqiao Univ Dept Comp Sci & Technol Xiamen Peoples R China Huaqiao Univ Fujian Key Lab Big Data Intelligence & Secur Xiamen Peoples R China Huaqiao Univ Xiamen Key Lab Comp Vis & Pattern Recognit Xiamen Peoples R China

Current methods for human-object interaction detection often use the spatial relation between a human and an object as an interaction pattern. However, this strategy is relatively simple and has low discrimination in similar interactions. To solve this drawback, the spatial relation between skeletons and objects is proposed to model the interaction pattern and improve the detection accuracy. First, the skeleton-object interaction pattern image is extracted for each interaction proposal. Second, a deep neural network is applied to learn the interaction features from these images. Finally, the interaction feature is added to the human-object interaction detection network by a multistream structure. In the experiments, we evaluate the proposed method on the HICO-DET and V-COCO datasets. Experimental results show that the proposed method can achieve the best performance compared with state-of-art methods.

关键词： Human-object interaction interaction pattern spatial relation skeleton-object relation

来源：评论

学校读者我要写书评

暂无评论

RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2022年第10期44卷 7149-7166页

作者： Zhang Wenlong Liu Yihao Dong, Chao Qiao, Yu Chinese Acad Sci Shenzhen Inst Adv Technol ShenZhen Key Lab Comp Vis & Pattern Recognit SIAT SenseTime Joint Lab Beijing 100864 Peoples R China Shanghai AI Lab Shanghai 200232 Peoples R China

Generative Adversarial Networks (GAN) have demonstrated the potential to recover realistic details for single image super-resolution (SISR). To further improve the visual quality of super-resolved results, PIRM2018-SR Challenge employed perceptual metrics to assess the perceptual quality, such as PI, NIQE, and Ma. However, existing methods cannot directly optimize these indifferentiable perceptual metrics, which are shown to be highly correlated with human ratings. To address the problem, we propose Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to optimize generator in the direction of different perceptual metrics. Specifically, we first train a Ranker which can learn the behaviour of perceptual metrics and then introduce a novel rank-content loss to optimize the perceptual quality. The most appealing part is that the proposed method can combine the strengths of different SR methods to generate better results. Furthermore, we extend our method to multiple Rankers to provide multi-dimension constraints for the generator. Extensive experiments show that RankSRGAN achieves visually pleasing results and reaches state-of-the-art performance in perceptual metrics and quality. Project page: https://***/Projects/RankSRGAN .

关键词： Image super resolution generative adversarial network learning to rank

来源：评论

学校读者我要写书评

暂无评论

Hierarchical local global transformer for point clouds analysis

引用

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 2024年 129卷

作者： Li, Dilong Zheng, Shenghong Chen, Ziyi Li, Xiang Wang, Lanying Du, Jixiang Huaqiao Univ Coll Comp Sci & Technol Fujian Key Lab Big Data Intelligence & Secur Xiamen Key Lab Comp Vis & Pattern RecognitXiamen Xiamen 361021 Peoples R China Huaqiao Univ Sch Econ & Finance Quanzhou 362021 Peoples R China Univ Waterloo Dept Geog & Environm Management Waterloo ON N2L 3G1 Canada

Transformer networks have demonstrated remarkable performance in point cloud analysis. However, achieving a balance between local regional context and global long-range context learning remains a significant challenge. In this paper, we propose a Hierarchical Local Global Transformer Network (LGTNet), designed to capture local and global contexts in a hierarchical manner. Specifically, we employ serial local and global Transformers to learn the inner-group and cross-group self-attention, respectively. Besides, we propose a geometric moment-based position encoding for local Transformer, enabling the embedding of comprehensive local geometric relationship. Additionally, we also introduce a global feature pooling module that extracts the global features from each encoder layers. Extensive experimental results demonstrate that LGTNet achieves state-of-the-art performance on ShapeNetPart and ScanObjectNN datasets. This approach effectively enhances the understanding of point cloud scenes, thereby facilitating the use of point cloud data in remote sensing applications.

关键词： Point cloud analysis Transformer Geometric moment

来源：评论

学校读者我要写书评

暂无评论

Multiscale 3D-Shift Graph Convolution Network for Emotion recognition From Human Actions

引用

IEEE INTELLIGENT SYSTEMS 2022年第4期37卷 103-110页

作者： Shi, Henglin Peng, Wei Chen, Haoyu Liu, Xin Zhao, Guoying Univ Oulu Ctr Machine Vis & Signal Anal FIN-90570 Oulu Finland Lappeenranta Lahti Univ Technol LUT Sch Engn Sci Comp Vis & Pattern Recognit Lab Lappeenranta 53850 Finland

Emotion recognition from body gestures is challenging since similar emotions can be expressed by arbitrary spatial configurations of joints, which results in relying on modeling spatial-temporal patterns from a more global level. However, most recent powerful graph convolution networks (GCNs) separate the spatial and temporal modeling into isolated processes, where GCN models spatial interactions using partially fixed adjacent matrices and 1D convolution captures temporal dynamics, which is insufficient for emotion recognition. In this work, we propose the 3D-Shift GCN, which enables interactions of joints within a spatial-temporal volume for global feature extraction. Besides, we further develop a multiscale architecture, the MS-Shift GCN, to fuse features captured under different temporal ranges for modeling richer dynamics. After conducting evaluation on two regular action recognition benchmarks and two gesture based emotion recognition datasets, the results show that the proposed method outperforms several state-of-the-art methods.

关键词： Emotion recognition Convolutional Neural Networks Gesture recognition Biological System Modeling Benchmark Testing Feature Extraction Graph Neural Networks

来源：评论

学校读者我要写书评

暂无评论

DCD-Net: Weakly supervised decomposition learning for real-world image dehazing

引用

SIGNAL PROCESSING 2025年 230卷

作者： Huang, Yi Dong, Yu Huang, Jiancheng Yan, Mingfu Chen, Shifeng Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Key Lab Comp Vis & Pattern Recognit Shenzhen 518055 Peoples R China Univ Chinese Acad Sci Beijing Peoples R China China Mobile GBA Greater Bay Area Innovat Inst Guangzhou Peoples R China Shenzhen Univ Adv Technol Shenzhen Peoples R China

In the dehazing task, most of the current learning-based models are trained on synthetic data sets due to the lack of labels in real haze images. Such datasets are primarily synthesized using idealized parameters of physical scattering models, overlooking the complexity and unpredictability of real-world haze. This leads to a marked discrepancy between synthetic hazy images and their real-world counterparts, significantly impacting the model generalization in real hazy scenes. In this work, we redefine hazing processing, viewing it as an interplay between haze-free images under organic illumination and an illumination map shaped by haze absorption and scattering. As a direct result, we introduce the novel Retinex-based decomposed cycle dehazing network (DCD-Net). This model is exclusively trained on authentic haze-free and unmatched hazy images sourced from our comprehensive Unpaired Real-world Dehazing (URD) dataset. Extensive experimentation has demonstrated that our approach markedly improves model generalization, yielding more realistic and visually appealing results in real-world world.

关键词： Weakly supervision Decomposition Retinex dehazing Model generalization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Ensemble Teacher-Student Distillation Framework for Light-Weight Fake Audio Detection

引用

IEEE SIGNAL PROCESSING LETTERS 2024年 31卷 2305-2309页

作者： Xue, Jun Fan, Cunhang Yi, Jiangyan Zhou, Jian Lv, Zhao 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 065001 Peoples R China

In recent years, fake audio detection (FAD) has made great progress, and lightweight is important to achieve fast and reliable audio authenticity verification on resource-limited devices. However, most of the researchers ignore lightweight when improving the performance of FAD. To develop the application of FAD for small-end devices, this paper proposes a novel light-weight network named Light-ECA2Net. Given that networks with different depths have different abilities in capturing fake speech artifacts, this paper proposes a dynamic ensemble teacher-student distillation framework to fully transfer distillation knowledge. The dynamic ensemble distillation is divided into two aspects. First, we adopt one-to-one feature mapping to perceive the multidimensional feature knowledge and dynamically adjust every dimension feature weight by using ground truth labels, which can enable students to receive feature knowledge efficiently. Secondly, different network layers also have their strengths of predicting, further dynamically predicting weight can improve the learning ability of the student. Experimental results on the ASVspoof 2019 LA and PA datasets show that compared to the baseline, our system further improves performance by reducing the model complexity by 45%.

关键词： Training Predictive models Feature extraction computational modeling Performance evaluation Neural networks Knowledge engineering Dynamic ensemble distillation ECA2Net fake audio detection

来源：评论

学校读者我要写书评

暂无评论

DEFORMATION ROBUST TEXT SPOTTING WITH GEOMETRIC PRIOR 30

DEFORMATION ROBUST TEXT SPOTTING WITH GEOMETRIC PRIOR

引用

30th IEEE International Conference on Image Processing (ICIP)

作者： Hao, Xixuan Zhang, Aozhong Meng, Xianze Fu, Bin Chinese Acad Sci Shenzhen Inst Adv Technol ShenZhen Key Lab Comp Vis & Pattern Recognit Beijing Peoples R China Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781728198354

The goal of text spotting is to perform text detection and recognition simultaneously. Although the diversity of luminosity and orientation in scene texts has been widely studied, the font diversity and shape variance of the same character are ignored in recent works, since most characters in natural images are rendered in standard fonts. To solve this problem, we present a Chinese Artistic Dataset, termed as ARText, which contains 33, 000 artistic images with rich shape deformation and font diversity. Based on this database, we develop a deformation robust text spotting method (DR TextSpotter) to solve the recognition problem of complex deformation of characters in different fonts. Specifically, we propose a geometric prior module to highlight the important features based on the unsupervised landmark detection sub-network. A graph convolution network is further constructed to fuse the character features and landmark features, and then performs semantic reasoning to enhance the discrimination for different characters. The experiments are conducted on ARText and IC19-ReCTS datasets. Our results demonstrate the effectiveness of our proposed method. The datasets and models will become publicly available after publication.

关键词： Scene Text Spotting Geometric Prior Graph Convolution Network Text Spotting Dataset

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：