1 code implementation • 20 Jul 2022 • Guangcheng Chen, Li He, Yisheng Guan, Hong Zhang
Current polarimetric 3D reconstruction methods, including those in the well-established shape from polarization literature, are all developed under the orthographic projection assumption.
1 code implementation • 15 Apr 2022 • Hanjing Ye, Weinan Chen, Jingwen Yu, Li He, Yisheng Guan, Hong Zhang
We employ a high-level layer of a pre-trained CNN to generate features, and train a CAE to map the features to a low-dimensional space to improve the condition invariance property of the descriptor and reduce its dimension at the same time.
2 code implementations • 16 Oct 2020 • Jiancong Huang, Juan Rojas, Matthieu Zimmer, Hongmin Wu, Yisheng Guan, Paul Weng
Insufficient learning (due to convergence to local optima) results in under-performing policies whilst redundant learning wastes time and resources.
1 code implementation • 5 Aug 2020 • Zhijun Liang, Junfa Liu, Yisheng Guan, Juan Rojas
We contribute a Pose-based Modular Network (PMN) which explores the absolute pose features and relative spatial pose features to improve HOI detection and is fully compatible with existing networks.
Ranked #23 on Human-Object Interaction Detection on V-COCO
1 code implementation • 11 Mar 2020 • Junfa Liu, Juan Rojas, Zhijun Liang, Yihui Li, Yisheng Guan
Spatio-temporal information is key to resolve occlusion and depth ambiguity in 3D pose estimation.
Ranked #11 on 3D Human Pose Estimation on HumanEva-I
3 code implementations • 7 Jan 2020 • Zhijun Liang, Juan Rojas, Junfa Liu, Yisheng Guan
Few works have studied the disambiguating contribution of subsidiary relations made available via graph networks.
no code implementations • 17 Dec 2019 • Jiajie Ye, Yisheng Guan, Junfa Liu, Xinghong Huang, Hong Zhang
Person identification (P-ID) under real unconstrained noisy environments is a huge challenge.
1 code implementation • 24 Sep 2019 • Yijiong Lin, Jiancong Huang, Matthieu Zimmer, Yisheng Guan, Juan Rojas, Paul Weng
Our work demonstrates that invariant transformations on RL trajectories are a promising methodology to speed up learning in deep RL.
no code implementations • 11 Sep 2018 • Hongmin Wu, Shuangqi Luo, Longxin Chen, Shuangda Duan, Sakmongkon Chumkamon, Dong Liu, Yisheng Guan, Juan Rojas
Robot manipulation is increasingly poised to interact with humans in co-shared workspaces.
no code implementations • 11 Mar 2017 • Ruotao He, Juan Rojas, Yisheng Guan
This paper proposes a robust 3D object detection and pose estimation pipeline based on RGB-D images, which can detect multiple objects simultaneously while reducing false positives.