Search Results for author: Qi Ma

Found 9 papers, 6 papers with code

Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains

1 code implementation21 Feb 2024 Steven Wilkins-Reeves, Xu Chen, Qi Ma, Christine Agarwal, Aude Hofleitner

We focus on scenarios where data distributions vary across multiple segments of the entire population and only make local assumptions about the differences between training and test (deployment) distributions within each segment.

Continuous Pose for Monocular Cameras in Neural Implicit Representation

1 code implementation28 Nov 2023 Qi Ma, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool

In this paper, we showcase the effectiveness of optimizing monocular camera poses as a continuous function of time.

Simultaneous Localization and Mapping

Deformable Neural Radiance Fields using RGB and Event Cameras

no code implementations ICCV 2023 Qi Ma, Danda Pani Paudel, Ajad Chhatkuli, Luc van Gool

In this work, we develop a novel method to model the deformable neural radiance fields using RGB and event cameras.

Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture

1 code implementation1 Sep 2023 Shaohua Pan, Qi Ma, Xinyu Yi, Weifeng Hu, Xiong Wang, Xingkang Zhou, Jijunnan Li, Feng Xu

We believe that the combination is complementary and able to solve the inherent difficulties of using one modality input, including occlusions, extreme lighting/texture, and out-of-view for visual mocap and global drifts for inertial mocap.

3D Human Pose Estimation

An Understanding-Oriented Robust Machine Reading Comprehension Model

1 code implementation1 Jul 2022 Feiliang Ren, Yongkang Liu, Bochao Li, Shilei Liu, Bingchao Wang, Jiaqi Wang, Chunchao Liu, Qi Ma

In this paper, we propose an understanding-oriented machine reading comprehension model to address three kinds of robustness issues, which are over sensitivity, over stability and generalization.

Machine Reading Comprehension Multi-Task Learning +1

EMFlow: Data Imputation in Latent Space via EM and Deep Flow Models

no code implementations9 Jun 2021 Qi Ma, Sujit K. Ghosh

The presence of missing values within high-dimensional data is an ubiquitous problem for many applied sciences.


Decoupled Self Attention for Accurate One Stage Object Detection

1 code implementation14 Dec 2020 Kehe WU, Zuge Chen, Qi Ma, Xiaoliang Zhang, Wei Li

When DSA module and object confidence task are applied in RetinaNet together, the detection performances based on ResNet50 and ResNet101 can be increased by 1. 0% AP and 1. 4% AP respectively.

Object object-detection +2

A Non-Iterative Quantile Change Detection Method in Mixture Model with Heavy-Tailed Components

no code implementations19 Jun 2020 Yuantong Li, Qi Ma, Sujit K. Ghosh

Estimating parameters of mixture model has wide applications ranging from classification problems to estimating of complex distributions.

Change Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.