2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)最新文献_第3页

Spatiotemporal-Spectral Graph Convolutional Networks For Skeleton-Based Action Recognition 基于骨架的动作识别的时空光谱图卷积网络

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455987

Shuo Chen, Ke Xu, Xinghao Jiang, Tanfeng Sun

引用次数: 2

Topic-Guided Local-Global Graph Neural Network For Image Captioning 主题导向局部-全局图神经网络图像标注

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455991

Jichao Kan, Kun Hu, Zhiyong Wang, Qiuxia Wu, M. Hagenbuchner, A. Tsoi

引用次数: 3

Robust and Efficient Facial Landmark Localization 鲁棒和高效的面部地标定位

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455952

H. Hu, Chen Wang, Tao Jiang, Zhixian Guo, Yonggang Han

{"title":"Robust and Efficient Facial Landmark Localization","authors":"H. Hu, Chen Wang, Tao Jiang, Zhixian Guo, Yonggang Han","doi":"10.1109/ICMEW53276.2021.9455952","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455952","url":null,"abstract":"Facial landmark localization is an essential component for facial recognition which is a vital technology for patients tracking in the situation of a global pandemic of COVID-19. Parameter amount and computation cost are two key factors affecting the application of facial landmark localization. In addition, the intrinsic imbalance of head pose in existing datasets has a great impact on the model generalization. To address these problems, this paper proposed a lightweight model LiteFace with multi-knowledge distillation and a pose-aware resampling strategy. Specifically, we proposed to extract multi-scale features and enhance the receptive filed of network by delicate model design to obtain an efficient architecture and improved the performance of the lightweight model by multi-knowledge distillation which combines knowledge distillation and mutual learning in a two-stage manner. To further improve the model performance and boost the generalization, we proposed a pose-aware re-sampling strategy that generates samples with different head poses and utilized the LaPa dataset to generate masked face images to increase data diversity. We conducted extensive ablation studies on the model design, multi-knowledge distillation and resampling strategy. The proposed method achieves 1.93% and 3.04% NME on the JD-landmark-mask val and test dataset respectively. Finally, LiteFace wins the third place in the 3rd Grand Challenge of 106-Point Facial Landmark Localization.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"35 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120920828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Efficient Face Alignment Network For Masked Face 一种有效的蒙面对齐网络

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9456012

Yuyang Sha, Jie Zhang, Xiao Liu, Zhongqin Wu, S. Shan

引用次数: 4

Tire Pattern Classification Based On Few-Shot Learning 基于少镜头学习的轮胎模式分类

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455988

Jingwen Yan, Yuting Zhu, Zilin Liang, Yisheng Zhu, Keer Wu, Zhinan Lin

引用次数: 2

Enhancing Quality Of Experience For Cloud Virtual Reality Gaming: An Object-Aware Video Encoding 提高云虚拟现实游戏的体验质量:一种对象感知视频编码

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455970

Wenjie Zou, Shixuan Feng, Xionghui Mao, Fuzheng Yang, Zhibin Ma

引用次数: 2

An Ensemble Learning-Based No Reference Qoe Model For User Generated Contents 基于集成学习的用户生成内容无参考质量模型

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455959

Duc V. Nguyen, Huyen T. T. Tran, T. Thang

引用次数: 1

Contrastive Representation For Few-Shot Vehicle Footprint Recognition 基于对比表示的少镜头车辆足迹识别

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455981

Yongxiong Wang, Chuanfei Hu, Guangpeng Wang, Xu Lin

引用次数: 2

Adaptive Multi-Scale Semantic Fusion Network For Zero-Shot Learning 零学习自适应多尺度语义融合网络

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455945

J. Song, Peixi Peng, Yunpeng Zhai, Chong Zhang, Yonghong Tian

{"title":"Adaptive Multi-Scale Semantic Fusion Network For Zero-Shot Learning","authors":"J. Song, Peixi Peng, Yunpeng Zhai, Chong Zhang, Yonghong Tian","doi":"10.1109/ICMEW53276.2021.9455945","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455945","url":null,"abstract":"Zero-shot learning aims at accurately recognizing unseen objects by learning matrices that bridge the gap between visual information and semantic attributes. Existing approaches predominantly focus on learning the proper mapping function for visual-semantic embedding while neglecting the effect of learning discriminative semantic features, which leads to severe semantic ambiguity. We propose a practical Adaptive Multi-scale Semantic Fusion (AMSF) framework to perform object-based multi-scale attribute attention for semantic disambiguation. Considering both low-level visual information and global class-level features that relate to this ambiguity, the proposed method jointly learns cooperative global and local semantic attributes from different scales. Moreover, with the joint supervision of embedding softmax loss and class-center triplet loss, the model is encouraged to learn high discriminative semantic features and visual features with high interclass dispersion and intra-class compactness. The method is evaluated on CUB, AwA2, and SUN datasets, and the experimental results indicate the method achieves state-of-the-art performance.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129970668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Image Quality Assessment Driven Self-Supervised Anomaly Detection 图像质量评估驱动的自监督异常检测

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455946

Zhipeng Wang, Chunping Hou, Yang Liu, Bangbang Ge, Guanghui Yue, Chunying Song

{"title":"Image Quality Assessment Driven Self-Supervised Anomaly Detection","authors":"Zhipeng Wang, Chunping Hou, Yang Liu, Bangbang Ge, Guanghui Yue, Chunying Song","doi":"10.1109/ICMEW53276.2021.9455946","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455946","url":null,"abstract":"Anomaly detection is a challenging task due to the bottleneck of anomalous sample collection. Recently, self-supervised learning has shown great potential for anomaly detection. However, these methods use task-related attributes as self-supervised signals and are suitable for specific application scenarios. In this paper, we propose a more general self-supervised method to detect anomaly which regards image quality as a supervised signal. Specially, we convert anomaly detection task into an image quality restoration task which contains distortion and restoration processing. Firstly, we introduce content distortion which erases hardness blocks in normal image based on no reference quality assessment method. Meanwhile, we introduce resolution distortion which down-samples normal images to low-resolution images preserving the essential appearance information. Then, a restoration network is trained to repair such distortions that encourages the model to learn detail information and the content of hardness regions in normal image. Extensive experiments on public benchmark datasets verify the effectiveness and generality of the proposed method.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130252959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0