no code implementations • CCL 2020 • Xinxin Zhang, Xiaoming Liu, Guan Yang, Fangfang Li
In spite of the success of pre-trained language model in many NLP tasks, the learned text representation only contains the correlation among the words in the sentence itself and ignores the implicit relationship between arbitrary tokens in the sequence.
no code implementations • 16 Dec 2023 • Jun Sun, Xinxin Zhang, Shoukang Han, Yu-Ping Ruan, Taihao Li
Multimodal learning is susceptible to modality missing, which poses a major obstacle for its practical applications and, thus, invigorates increasing research interest.
no code implementations • 31 Mar 2023 • Xinxin Zhang, Dike Li, Jianqin Zhu, Zhi Tao, Lu Qiu
Digital twin is a modern technology for many advanced applications.
no code implementations • 21 Feb 2023 • Baihan Lin, Xinxin Zhang
Our approach considers speaker diarization as a fully online learning problem of the speaker recognition task, where the agent receives no pretraining from any training set before deployment, and learns to detect speaker identity on the fly through reward feedbacks.
no code implementations • 13 Jul 2022 • Yiting Lu, Jun Fu, Xin Li, Wei Zhou, Sen Liu, Xinxin Zhang, Congfu Jia, Ying Liu, Zhibo Chen
Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA.
no code implementations • 21 Jun 2022 • Marcin B. Kaczmarek, Xinxin Zhang, S. Hassan HosseinNia
In this paper, we introduce a new representation for open-loop reset systems.
no code implementations • 1 Jun 2022 • Xinxin Zhang, Marcin B Kaczmarek, S. Hassan HosseinNia
In this paper, a new analytical technique for reset controllers is proposed to break the limitations.
no code implementations • 16 Aug 2020 • Da Chen, Jian Zhu, Xinxin Zhang, Ming-Lei Shu, Laurent D. Cohen
Minimal paths are regarded as a powerful and efficient tool for boundary detection and image segmentation due to its global optimality and the well-established numerical solutions such as fast marching method.
1 code implementation • 8 Jun 2020 • Baihan Lin, Xinxin Zhang
We proposed a novel machine learning framework to conduct real-time multi-speaker diarization and recognition without prior registration and pretraining in a fully online learning setting.
1 code implementation • 18 Nov 2019 • Xinlei Wang, Minchen Li, Yu Fang, Xinxin Zhang, Ming Gao, Min Tang, Danny M. Kaufman, Chenfanfu Jiang
We propose Hierarchical Optimization Time Integration (HOT) for efficient implicit time-stepping of the Material Point Method (MPM) irrespective of simulated materials and conditions.
Graphics
no code implementations • 23 Jan 2019 • Zhihao Cao, Xinxin Zhang
Mount Tai has abundant sunshine, abundant rainfall and favorable climatic conditions, forming dense vegetation with various kinds of trees.