In this paper, we introduce a new large-scale face dataset named VGGFace2. The dataset contains 3.31 million images of 9131 subjects, with an average of 362.6 images for each subject. Images are downloaded from Google Image Search and have large variations in pose, age, illumination, ethnicity and profession (e.g. actors, athletes, politicians). The dataset was collected with three goals in mind: (i) to have both a large number of identities and also a large number of images for each identity; (ii) to cover a large range of pose, age and ethnicity; and (iii) to minimize the label noise. We describe how the dataset was collected, in particular the automated and manual filtering stages to ensure a high accuracy for the images of each identity. To assess face recognition performance using the new dataset, we train ResNet-50 (with and without Squeeze-and-Excitation blocks) Convolutional Neural Networks on VGGFace2, on MS- Celeb-1M, and on their union, and show that training on VGGFace2 leads to improved recognition performance over pose and age. Finally, using the models trained on these datasets, we demonstrate state-of-the-art performance on all the IARPA Janus face recognition benchmarks, e.g. IJB-A, IJB-B and IJB-C, exceeding the previous state-of-the-art by a large margin. Datasets and models are publicly available.
Exploring object-centric and scene-centric CNN features and their complementarity for human rights violations recognition in images
School of Computer Science and Electronic Engineering, University of Essex, UK(埃塞克斯大学计算机科学与电子工程学院,英国);School of Computer Science, University of Birmingham, UK(伯明翰大学计算机科学学院,英国)
AgentPose: Progressive Distribution Alignment via Feature Agent for Human Pose Distillation
Nanjing University of Posts and Telecommunications(南京邮电大学);Surrey Institute for People-Centred Artificial Intelligence, University of Surrey(萨里大学以人为本人工智能研究所)
Real-time Facial Expression Recognition "In The Wild'' by Disentangling 3D Expression from Identity
College of Engineering, Mathematics and Physical Sciences, University of Exeter(埃克塞特大学工程、数学与物理科学学院);Institute of Computer Science (ICS), Foundation for Research and Technology - Hellas (FORTH)(希腊研究与技术基金会计算机科学研究所)
Robust Fetal Pose Estimation across Gestational Ages via Cross-Population Augmentation
Computer Science \& Artificial Intelligence Laboratory, MIT, Cambridge, USA Research Laboratory of Electronics, MIT, Cambridge, USA Inria, Epione team, Sophia-Antipolis, France Harvard Medical School, Boston, USA Massachusetts General Hospital, Boston, USA Boston Children's Hospital, Boston, USA
Age-Inclusive 3D Human Mesh Recovery for Action-Preserving Data Anonymization
School of ECE, National Technical University of Athens(电子工程学院,国家技术大学雅典分校);Robotics Institute, Athena RC(机器人研究所,雅典RC);HERON - Hellenic Robotics Center of Excellence(HERON - 希腊机器人 excellence 中心);The University of Texas at Austin(德克萨斯大学奥斯汀分校)