2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)最新文献_第4页

Light Weight Facial Landmark Detection With Weakly Supervised Learning 基于弱监督学习的轻权重人脸标记检测

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455973

Shenqi Lai, Lei Liu, Z. Chai, Xiaolin Wei

{"title":"Light Weight Facial Landmark Detection With Weakly Supervised Learning","authors":"Shenqi Lai, Lei Liu, Z. Chai, Xiaolin Wei","doi":"10.1109/ICMEW53276.2021.9455973","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455973","url":null,"abstract":"A robust facial landmark detection framework is proposed in this paper, which can be trained in an end-to-end fashion and has achieved promising detection accuracy in the 3rd Grand Challenge of 106-Point Facial Landmark Localization. Firstly, the upper bound of computational complexity is 100MFLOPs and the model size is 2MB, we design a new model named ShuffleNeXt to be the backbone. Based on ShuffleNetV2, groupwise convolution layer is used to replace the standard depthwise convolution layer. Swish function is also used to replace ReLU function. What is more, we design a single layer coordinate attention module to capture spatial and channel information, which is better than the coordinate attention and squeeze-and-excitation module. In order to prevent the accuracy loss by the coordinates quantization, dual soft argmax is used for mapping the heatmap response to coordinates. Besides, a coarse localization regulation is also proposed to improve the performance. In the end, we introduce weakly supervised learning to increase training samples. We train the model and re-label the large scale CelebA dataset. Original CelebA only has 5 points annotations, so we calculate the NME on these 5 points. We set the threshold of NME to 1% and find 162,731 face images fit the bill. So the number of training set is expanded from 20,384 to 183,115, which is 800% larger than original dataset. The best result 79.38% for AUC is achieved on the validation set.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"66 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":"116745801","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

Depth Map Video Compression Performance Evaluation For Ieee 1857.9 Ieee 1857.9深度图视频压缩性能评价

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455977

Yangang Cai, Ronggang Wang, Ke Qiu, Rui Peng, Zhipeng Cheng, Qi Wang

{"title":"Depth Map Video Compression Performance Evaluation For Ieee 1857.9","authors":"Yangang Cai, Ronggang Wang, Ke Qiu, Rui Peng, Zhipeng Cheng, Qi Wang","doi":"10.1109/ICMEW53276.2021.9455977","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455977","url":null,"abstract":"In 6 Degrees of Freedom (6DoF) Video, it provides 360 video considering both user’s head and body movement. In IEEE 1857.9 6DoF video expression, synthesizing the virtual view in accordance with the user’s movement is required. During the view synthesis process, the reference software provided by IEEE 1857.9 requires a depth map as auxiliary information. In order to reuse existing video coding standards and quickly apply them to the industry, IEEE 1857.9 provides four depth map compression interfaces for AVC, HEVC, AVS2, and AVS3(First stage HPM4.0). In addition, the depth information is never directly shown to the user. Thus, new comparison methods have to be developed that are adapted to the depth maps compression. In this paper, we investigate the depth video compression performance of the software encoders of H.264/AVC, H.265/HEVC, and AVS3 respectively. To ensure fair analysis, we evaluate the performance of the encoder by comparing the objective quality of the virtual synthetic view. We use the reference software of IEEE 1857.9 for synthesizing the virtual view. Regarding coding performance evaluation, PSNR and SSIM are used as objective quality metrics. According to the experimental results, which were obtained by using similar configurations for all examined representative encoders, the AVS3 reference software implementation provides significant average bit-rate savings of 63% and 19% compared to H.264/AVC and H.265/HEVC respectively.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"2 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":"126499949","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: 2

Multi-Style Artistic Portrait Drawing Generation 多风格的艺术肖像绘画生成

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455949

Ran Yi, Yong-Jin Liu

引用次数: 0

Open-Source: Attention-Based Neural Networks For Chroma Intra Prediction In Video Coding 基于注意力的神经网络用于视频编码中的色度内预测

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455958

M. G. Blanch, Saverio G. Blasi, A. Smeaton, N. O’Connor, M. Mrak

引用次数: 0

The 3rd Grand Challenge of Lightweight 106-Point Facial Landmark Localization on Masked Faces 蒙面上轻量化106点面部地标定位的第三次大挑战

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455953

Ming Xiang, Yinglu Liu, Tingting Liao, Xiangyu Zhu, Can Yang, Wu Liu, Hailin Shi

{"title":"The 3rd Grand Challenge of Lightweight 106-Point Facial Landmark Localization on Masked Faces","authors":"Ming Xiang, Yinglu Liu, Tingting Liao, Xiangyu Zhu, Can Yang, Wu Liu, Hailin Shi","doi":"10.1109/ICMEW53276.2021.9455953","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455953","url":null,"abstract":"Facial landmark localization is a fundamental component in various face related applications, such as face recognition, 3D face reconstruction, facial pose estimation, face synthesis and forensics, etc. However, due to the global pandemic of COVID-19, the facial mask has become a common way to suppress the transmission of the virus. This apparently makes conventional facial landmark localization unfaithful and inefficient because of occlusion. To lead the cutting-edge algorithms on masked faces, we host the 3rd grand challenge of lightweight 106-point facial landmark localization in conjunction with ICME 2021, aiming to improve the accuracy and robustness of facial landmark localization in real-world situations, especially on masked faces. Specifically, we construct a new dataset, named JD-landmark-mask, on the basis of the previous two competitions. It contains about 27,000 face images of two kinds, with real and virtual masks, which are largely varied in identity, head pose, facial expression, and occlusion. Besides, the strict limitations of model size (2M) and computational complexity (100M Flops) are set up for the lightweight model. Finally, more than 80 worldwide universities and research institutes took part in the competition. We will briefly introduce the information of the competition, as well as algorithms and results of the top three teams in this paper.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"6 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":"130440310","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: 4

Multi-Modal Fusion Enhanced Model For Driver’s Facial Expression Recognition 驾驶员面部表情识别的多模态融合增强模型

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455983

Jianrong Chen, Sujit Dey, Lei Wang, Ning Bi, Peng Liu

{"title":"Multi-Modal Fusion Enhanced Model For Driver’s Facial Expression Recognition","authors":"Jianrong Chen, Sujit Dey, Lei Wang, Ning Bi, Peng Liu","doi":"10.1109/ICMEW53276.2021.9455983","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9455983","url":null,"abstract":"Facial expression recognition (FER) for monitoring a driver’s emotional state has become an increasing need for advanced driver assistant systems (ADAS). Though state-of-art results of recognition accuracy have been achieved in FER with the development of deep neural networks (DNNs) in recent years, FER in real-world is still challenging due to illumination and head pose variation. In this work, we propose a multi-modal fusion based FER model capable of recognizing facial expressions accurately regardless of the lighting conditions and head poses, using a structured-light imaging camera which provides three modalities of images - RGB, Near-infrared (NIR), and Depth Maps. The model is implemented in two phases, where the first phase extracts feature from single modalities separately using 3D ResNet while the second phase combines the multi-modal features and classifies expressions. The model is trained and tested with a novel facial expression dataset with the three image modalities, with varying lighting conditions and head poses. The experimental results show that combining different modalities improves the model performance and robustness. A recognition accuracy of over 90% has been obtained in the usage scenario of FER for drivers.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"34 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":"133935089","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

An Improved Coarse-To-Fine Motion Estimation Scheme For Lidar Point Cloud Geometry Compression 激光雷达点云几何压缩中一种改进的粗到精运动估计方案

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9456018

Jiamin Jin, Ge Li, Yiting Shao, Fei Song, Ruonan Zhang

{"title":"An Improved Coarse-To-Fine Motion Estimation Scheme For Lidar Point Cloud Geometry Compression","authors":"Jiamin Jin, Ge Li, Yiting Shao, Fei Song, Ruonan Zhang","doi":"10.1109/ICMEW53276.2021.9456018","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9456018","url":null,"abstract":"Light detection and ranging (LiDAR) plays a vital role in autonomous driving applications. Due to the enormous volume of point cloud data from LiDAR acquisition, LiDAR point cloud compression schemes are desirable under limited storage and transmission bandwidth. This paper proposes an improved coarse-to-fine motion estimation scheme to significantly reduce the spatial redundancy among LiDAR point clouds, combining registration-based global motion estimation and block-based local motion estimation. First, in the global motion estimation process, an efficient scheme is introduced to segment ground level and object level from original point clouds. Then we use an ICP-based registration method for extracted object point cloud to estimate global motion transformation. Second, an irregular prediction unit (PU) partition method is introduced in the block-based local motion estimation part, which provides more flexibility to estimate complex motions. Experimental results have shown significant gains of our proposed model over the state-of-the-art test model (TMC13) of MPEG Geometry-based PCC (GPCC) standard. For the dynamically acquired point clouds, average coding gains of 8.0% and 1.2% are obtained respectively in lossy and lossless geometric coding.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"22 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":"131865156","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: 4

Self-Supervised Learning for Human Pose Estimation in Sports 运动中人体姿态估计的自监督学习

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9456000

K. Ludwig, S. Scherer, Moritz Einfalt, R. Lienhart

引用次数: 11

Multimodal Feature Fusion Model For Rgb-D Action Recognition Rgb-D动作识别的多模态特征融合模型

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9455975

Weiyao Xu, Muqing Wu, Min Zhao, Xiao Ting

引用次数: 1

Full-Reference And No-Reference Quality Assessment For Compressed User-Generated Content Videos 压缩用户生成内容视频的全参考和无参考质量评估

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW) Pub Date : 2021-07-05 DOI: 10.1109/ICMEW53276.2021.9456013

Yang Li, Longtao Feng, Jingwen Xu, Tao Zhang, Yiting Liao, Junlin Li

{"title":"Full-Reference And No-Reference Quality Assessment For Compressed User-Generated Content Videos","authors":"Yang Li, Longtao Feng, Jingwen Xu, Tao Zhang, Yiting Liao, Junlin Li","doi":"10.1109/ICMEW53276.2021.9456013","DOIUrl":"https://doi.org/10.1109/ICMEW53276.2021.9456013","url":null,"abstract":"With the development of video capture devices and network technology, recent years have witnessed an exponential increase of user-generated content (UGC) videos in various sharing platforms. Comparing to professionally generated content (PGC) videos, these UGC videos are generally captured by amateurs using smartphone cameras in various life scenes and contains various in-capture distortions. Besides, these videos undergo multi stages that may affect the perceptual quality before finally viewed by end-users. Complex and diverse distortion types bring difficulties to objective quality assessment. In this paper, we present a data-driven video quality assessment (VQA) method for UGC videos based on a convolutional neural network (CNN) and a Transformer. Specifically, the CNN backbone is used to extract features from frames and the output is fed to the Transformer encoder for the prediction of quality score. The proposed method can be used for both full-reference (FR) and no-reference (NR) VQA with slight adaptations. Our method ranks first and second in MOS track and DMOS track of the challenge on quality assessment of compressed UGC videos [1], respectively.","PeriodicalId":228350,"journal":{"name":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","volume":"34 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":"123534849","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: 4