1 code implementation • 21 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.
1 code implementation • 9 Jan 2024 • Jiaqi Wang, Yuying Chang, Zhong Li, Ning An, Qi Ma, Lei Hei, Haibo Luo, Yifei Lu, Feiliang Ren
Large language models have exhibited robust performance across diverse natural language processing tasks.
1 code implementation • 28 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.
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.
1 code implementation • 1 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.
Ranked #1 on 3D Human Pose Estimation on AIST++
1 code implementation • 1 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.
no code implementations • 9 Jun 2021 • Qi Ma, Sujit K. Ghosh
The presence of missing values within high-dimensional data is an ubiquitous problem for many applied sciences.
1 code implementation • 14 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.
no code implementations • 19 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.