Hero Section


Welcome to the NEC Labs America blog, where we cover important topics related to our research in a more informal medium than a research paper.

Project Card Grid

Media Analytics Research at CVPR 2020

August 9, 2020: CVPR is a highly rated conference for computer vision, a virtual version of which was held during June 2020. The MA team from NEC Labs America presented four papers at the conference. These papers covered a range of topics, including outdoor and indoor 3D scene understanding, learning universal representations for face recognition in the wild and practical methods for differential privacy that achieve high levels of theoretical guarantee and accuracy even with limited data.Priva…


AI Solutions With a Guarantee of Privacy

August 17, 2020: We review our recent work on differential privacy, which appeared in CVPR 2020 as "Private-kNN: Practical Differential Privacy for Computer Vision" by Yuqing Zhu, Xiang Yu, Manmohan Chandraker and Yu-Xiang Wang.SummaryWith increasing ethical and legal concerns about privacy for deep models in visual recognition, differential privacy has emerged as a mechanism to disguise membership of sensitive data in training datasets. Previous methods, like private aggregation of t…


Understanding Road Scenes in Videos

August 24, 2020: We review our recent work on 3D scene understanding, which appeared in CVPR 2020 as "Understanding Road Layout in Videos as a Whole" by Buyu Liu, Bingbing Zhuang, Samuel Schulter, Pan Ji and Manmohan Chandraker.SummaryGiven a video of a complex scene, we represent various elements of the scene in a way that is both interpretable and accurate. This allows explainable decision-making for downstream application and intuitive visualization for human-machine interaction. F…


Privacy-Aware AI Models

January 6, 2021: We developed two types of technologies for privacy-aware AI models: differential privacy and differentially-private federated learning. These technologies prevent attackers from using model outputs to decipher data, either in stand-alone training or in combined training across multiple stakeholders. Furthermore, our privacy-aware AI models achieve high privacy and accuracy with less data required compared to competitors. For example, Google needs much larger data than us, so it…


Universal Representations for Responsible and Robust AI

January 6, 2021: Responsible AI systems for surveillance, healthcare and biometrics applications that focus on people need to satisfy legal and social requirements. Moreover, robust AI engines need to achieve accuracy in new and unexpected situations for applications such as mobility, insurance, construction and factories. To enable both responsible and robust AI systems while reducing the cost of data collection and annotation, we present a URLearning framework to learn universal representatio…


Camera Motion Estimation by Learning Uncertainty-Aware Fusion

June 21, 2020: We review our recent work on camera motion estimation, which has been accepted by CVPR 2021 as an oral paper entitled "Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty" by Bingbing Zhuang and Manmohan Chandraker.SummaryHumans and autonomous agents always move in a 3D environment rather than on a 2D image plane, making 3D motion perception a fundamental capability for any intelligent system. As such, estimating relative camera p…


Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction

June 21, 2020: In this post, we review our recent CVPR 2021 paper (oral) "Divide and Conquer for Lane Aware Diverse Trajectory Prediction" by Sriram Narayanan, Ramin Moslemi, Francesco Pittaluga and Buyu Liu.SummaryTrajectory prediction is a safety-critical tool for autonomous vehicles to plan and execute actions. Our work addresses two key challenges in trajectory prediction: (i) learning multimodal outputs and (ii) improving predictions by imposing constraints using driving knowledg…


Cross-Domain Similarity Learning for Face Recognition in Unseen Domains

June 21, 2020: In this post, we review our recent CVPR 2021 paper "Cross-Domain Similarity Learning for Face Recognition in Unseen Domains" by Masoud Faraki, Xiang Yu, Yi-Hsuan Tsai, Yumin Suh and Manmohan Chandraker.SummaryFacial recognition (FR)-based systems continue to be the preferred approach for many applications such as biometric technologies and emotion analysis. That is mainly because FR is the most natural way to meet these types of demands with no physical interaction with…