2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)最新文献_第2页

Unsupervised 3D Animal Canonical Pose Estimation with Geometric Self-Supervision 基于几何自监督的无监督三维动物典型姿态估计

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042785

Xiaowei Dai, Shuiwang Li, Qijun Zhao, Hongyu Yang

{"title":"Unsupervised 3D Animal Canonical Pose Estimation with Geometric Self-Supervision","authors":"Xiaowei Dai, Shuiwang Li, Qijun Zhao, Hongyu Yang","doi":"10.1109/FG57933.2023.10042785","DOIUrl":"https://doi.org/10.1109/FG57933.2023.10042785","url":null,"abstract":"Although analyzing animal shape and pose has potential applications in many fields, there is little work on 3D animal pose estimation. This can be attributed to two aspects: the lack of large-scale well-annotated datasets, and perspective ambiguities which make it difficult to map 2D space to 3D space. To address data scarcity, we propose an unsupervised method to estimate 3D animal pose, given only 2D poses. To deal with perspective ambiguities, we introduce a canonical consistency loss and a camera consistency loss to impose geometric priors in the training process, and combine the reprojection loss and the 2D pose discriminator to enable self-supervised learning. Specifically, given a 2D pose, the pose generator network generates a corresponding 3D pose and the camera network estimates a camera rotation. During training, the generated 3D pose is randomly reprojected onto camera viewpoints to synthesize a new 2D pose. The synthesized 2D pose is decomposed into a 3D pose and a camera rotation, based on which consistency losses are imposed in both 3D canonical poses and camera rotations for self-supervised training. We evaluate the proposed method on real and synthetic datasets, i.e., SMAL and AcinoSet. The experimental results demonstrate the effectiveness of the proposed method and we achieve state-of-the-art performance among unsupervised algorithms for 3D animal canonical pose estimation.","PeriodicalId":318766,"journal":{"name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123584100","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: 1

Learning Effective Global Receptive Field for Facial Expression Recognition 学习面部表情识别的有效全局接受野

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042628

Jiayi Han, Ang Li, Donghong Han, Jianfeng Feng

引用次数: 0

Zero-Shot Style Transfer for Multimodal Data-Driven Gesture Synthesis 多模态数据驱动手势合成的零镜头风格转移

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042658

Mireille Fares, C. Pelachaud, Nicolas Obin

引用次数: 2

Casual chatter or speaking up? Adjusting articulatory effort in generation of speech and animation for conversational characters 随便闲聊还是大声说话?在会话角色的语音和动画生成中调整发音努力

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042520

Joakim Gustafson, Éva Székely, Simon Alexandersson, J. Beskow

引用次数: 0

Adversarial 3D Face Disentanglement of Identity and Expression 身份与表情的对抗三维人脸解纠结

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042602

Yajie Gu, Nick E. Pears, Hao Sun

引用次数: 0

Laplacian ICP for Progressive Registration of 3D Human Head Meshes 三维人体头部网格渐进配准的拉普拉斯ICP

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042743

Nick E. Pears, H. Dai, William Smith, Haobo Sun

引用次数: 0

Human Pose Estimation with Shape Aware Loss 基于形状感知损失的人体姿态估计

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042691

Lin Fang, Shangfei Wang

{"title":"Human Pose Estimation with Shape Aware Loss","authors":"Lin Fang, Shangfei Wang","doi":"10.1109/FG57933.2023.10042691","DOIUrl":"https://doi.org/10.1109/FG57933.2023.10042691","url":null,"abstract":"Although the mean square error (mse) of heatmap is an intuitive loss for heatmap-based human pose estimation, the joints localization accuracy may not be improved when heatmap mse reduces. In this paper, we show that a great cause for such misalignment is the unnecessary requirement from heatmap mse on the irrelevant Gaussian parameter, i.e. maximum. The coordinate prediction is precise as long as the probability distribution held by the predicted heatmap is a well-shaped Gaussian distribution and has the same center as the ground truth. However, heatmap mse unnecessarily requires the Gaussian distribution to hold the same maximum as the ground truth. Correspondingly, we introduce mse on the image gradients of the target and predicted heatmap (referred to as gradmap mse) to focus on the shape of the heatmap. Combining heatmap and gradmap mse, we propose a simple yet effective Shape Aware Loss (SAL) method. Being model-agnostic, our method can benefit various existing models. We apply SAL to the three latest network architectures and obtain performance improvements for all of them. Comparisons of the visualized predicted heatmaps further prove the effectiveness of the proposed method.","PeriodicalId":318766,"journal":{"name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114840394","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

Adversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction 基于语义正交空间的对抗深度多任务学习及其在面部属性预测中的应用

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042750

Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kévin Bailly

{"title":"Adversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction","authors":"Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kévin Bailly","doi":"10.1109/FG57933.2023.10042750","DOIUrl":"https://doi.org/10.1109/FG57933.2023.10042750","url":null,"abstract":"Deep learning-based multi-task approaches usually rely on factorizing representation layers up to a certain point, where the network splits into several heads, each one addressing a specific task. Depending on the inter-task correlation, such naive model may or may not allow the tasks to benefit from each others. In this paper, we propose a novel Semantic Orthogonality Spaces (SOS) method for multi-task problems, where each task is predicted using the information from a common subspace that factorizes information among all tasks, as well as a task-specific subspace. We enforce orthogonality between these tasks by applying soft orthogonality constraints, as well as adversarially-learned semantic orthogonality objectives that ensures that predicting one task requires the specific information related to that task. We demonstrate the effectiveness of SOS on synthetic data, as well as for large-scale facial attributes prediction. In particular, we use SOS to craft a lightweight architecture that provides high-end accuracies on CelebA database.","PeriodicalId":318766,"journal":{"name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124833411","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

Controllable Facial Micro-element Synthesis using Segmentation Maps 基于分割图的可控面部微元素合成

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042571

Yujin Kim, I. Park

{"title":"Controllable Facial Micro-element Synthesis using Segmentation Maps","authors":"Yujin Kim, I. Park","doi":"10.1109/FG57933.2023.10042571","DOIUrl":"https://doi.org/10.1109/FG57933.2023.10042571","url":null,"abstract":"In facial image synthesis, the style of the source image is converted using a reference image, or images with different styles are synthesized by each attribute using a facial attribute segmentation map. However, previous works cannot deal with the fine areas because the style is changed mostly in large areas such as hair, eyes, and mouth. To overcome the limitation, we propose a novel method of synthesizing a facial image with micro-level facial elements. A deep learning-based high-resolution image synthesis model is employed after generating a label image from the face RGB image through skin micro-element segmentation and face attribute segmentation. In the process of generating a label image for synthesizing skin micro-elements, we propose a technique for controlling skin micro-elements, enabling the generation of various label images from a single face label image. Throughout the proposed method, the areas of skin micro-elements can be edited and different skin types can be simulated. The experimental results show that the generated face is significantly improved by applying the proposed method. Moreover, various faces can be synthesized by changing the types and stages of skin micro-elements.","PeriodicalId":318766,"journal":{"name":"2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133258389","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

Acceptability and Trustworthiness of Virtual Agents by Effects of Theory of Mind and Social Skills Training 心理理论与社交技能训练对虚拟代理人可接受性与可信度的影响

2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) Pub Date : 2023-01-05 DOI: 10.1109/FG57933.2023.10042781

Hiroki Tanaka, Takeshi Saga, Kota Iwauchi, Satoshi Nakamura

引用次数: 1