no code implementations • 28 Mar 2024 • Chongkai Gao, Zhengrong Xue, Shuying Deng, Tianhai Liang, Siqi Yang, Lin Shao, Huazhe Xu
RiEMann learns a manipulation task from scratch with 5 to 10 demonstrations, generalizes to unseen SE(3) transformations and instances of target objects, resists visual interference of distracting objects, and follows the near real-time pose change of the target object.
no code implementations • 23 Aug 2023 • Siqi Yang, Zejun Yang, Zhisheng Wang
To address this, we design a conditional diffusion model, LongDanceDiff, for this sequence-to-sequence long-term dance generation, addressing the challenges of temporal coherency and spatial constraint.
no code implementations • CVPR 2023 • Siqi Yang, Xuanning Cui, Yongjie Zhu, Jiajun Tang, Si Li, Zhaofei Yu, Boxin Shi
Relighting an outdoor scene is challenging due to the diverse illuminations and salient cast shadows.
no code implementations • 3 Feb 2020 • Siqi Yang, Lin Wu, Arnold Wiliem, Brian C. Lovell
To achieve gradient alignment, we propose Forward-Backward Cyclic Adaptation, which iteratively computes adaptation from source to target via backward hopping and from target to source via forward passing.
no code implementations • ECCV 2018 • Siqi Yang, Arnold Wiliem, Shaokang Chen, Brian C. Lovell
We show that existing adversarial perturbation methods are not effective to perform such an attack, especially when there are multiple faces in the input image.
2 code implementations • 7 Dec 2017 • Teng Zhang, Arnold Wiliem, Siqi Yang, Brian C. Lovell
While it can greatly increase the scope and benefits of the current security surveillance systems, performing such a task using thermal images is a challenging problem compared to face recognition task in the Visible Light Domain (VLD).