no code implementations • 8 May 2025 • Mingliang Xiong, Qingwen Liu, Hao Deng, Gang Wang, Gang Li, Bin He
We also demonstrate the trade-off among the reflectivities of the cavity mirrors in the CSDR.
no code implementations • 17 Apr 2025 • Hao Deng, Haibo Xing, Kanefumi Matsuyama, Moyu Zhang, Jinxin Hu, Hong Wen, Yu Zhang, Xiaoyi Zeng, Jing Zhang
Multi-objective embedding-based retrieval (EBR) has become increasingly critical due to the growing complexity of user behaviors and commercial objectives.
no code implementations • 13 Mar 2025 • Xueting Luo, Hao Deng, Jihong Yang, Yao Shen, Huanhuan Guo, Zhiyuan Sun, Mingqing Liu, Jiming Wei, Shengjie Zhao
The necessity of achieving an effective balance between minimizing the losses associated with restricting human mobility and ensuring hospital capacity has gained significant attention in the aftermath of COVID-19.
Multi-agent Reinforcement Learning
Reinforcement Learning (RL)
no code implementations • 3 Mar 2025 • Hao Deng, Haibo Xing, Kanefumi Matsuyama, Yulei Huang, Jinxin Hu, Hong Wen, Jia Xu, Zulong Chen, Yu Zhang, Xiaoyi Zeng, Jing Zhang
Recent studies have attempted to integrate user-side heterogeneous features into item representation sequences, but item-side heterogeneous features, which are vital for performance, remain excluded.
no code implementations • 25 Feb 2025 • Zelin Tao, Hao Deng, Mingqing Liu, Lijun Zhang, Shengjie Zhao
Online continual learning (OCL), which enables AI systems to adaptively learn from non-stationary data streams, is commonly achieved using experience replay (ER)-based methods that retain knowledge by replaying stored past during training.
1 code implementation • 23 Feb 2025 • Kaibin Zhou, Shengjie Zhao, Hao Deng, Lin Zhang
However, these methods are essential for synthesizing large-scale high-quality paired rainy-clean image datasets, which can train deep learning-based single image rain removal models capable of generalizing to various illumination conditions.
no code implementations • 22 Feb 2025 • Haibo Xing, Kanefumi Matsuyama, Hao Deng, Jinxin Hu, Yu Zhang, Xiaoyi Zeng
Industrial recommendation systems typically involve a two-stage process: retrieval and ranking, which aims to match users with millions of items.
no code implementations • CVPR 2025 • Shengzhi Wang, Yingkang Zhong, Jiangchuan Mu, Kai Wu, Mingliang Xiong, Wen Fang, Mingqing Liu, Hao Deng, Bin He, Gang Li, Qingwen Liu
To address this problem, we propose Align-A-Video, a video editing pipeline that incorporates human feedback through reward fine-tuning.
no code implementations • 16 Dec 2024 • Xiaozhe Li, Kai Wu, Siyi Yang, YiZhan Qu, Guohua. Zhang, Zhiyu Chen, Jiayao Li, Jiangchuan Mu, Xiaobin Hu, Wen Fang, Mingliang Xiong, Hao Deng, Qingwen Liu, Gang Li, Bin He
Recent advancements in text-to-video (T2V) generation have leveraged diffusion models to enhance visual coherence in videos synthesized from textual descriptions.
no code implementations • 11 Sep 2024 • Xiaoye Wang, Nicole Xi Zhang, Hongyu He, Trang Nguyen, Kun-Hsing Yu, Hao Deng, Cynthia Brandt, Danielle S. Bitterman, Ling Pan, Ching-Yu Cheng, James Zou, Dianbo Liu
These concerns about AI safety have emerged as the most significant obstacles to the adoption of AI in medicine.
1 code implementation • 25 Jun 2024 • Guanghao Zhu, Lin Liu, Yuhao Hu, Haixin Sun, Fang Liu, Xiaohui Du, Ruqian Hao, Juanxiu Liu, Yong liu, Hao Deng, Jing Zhang
Secondly, we employ efficient channel attention modules in the local-spatial stream to make the network focus on facial regions that are highly relevant to micro-expressions.
Micro Expression Recognition
Micro-Expression Recognition
+2
no code implementations • 6 Nov 2023 • Peiyuan Zhu, Fengxia Han, Hao Deng
Trajectory prediction plays a vital role in automotive radar systems, facilitating precise tracking and decision-making in autonomous driving.
no code implementations • 6 Sep 2023 • Yang Zheng, Hao Deng, Ruisheng Wang, Jingjie Wu
This study presents a novel multimodal fusion model for three-dimensional mineral prospectivity mapping (3D MPM), effectively integrating structural and fluid information through a deep network architecture.
no code implementations • 16 Feb 2023 • Zhihua Li, Alexander Nagrebetsky, Sylvia Ranjeva, Nan Bi, Dianbo Liu, Marcos F. Vidal Melo, Timothy Houle, Lijun Yin, Hao Deng
We hypothesized that available intraoperative mechanical ventilation and physiological time-series data combined with other clinical events could be used to accurately predict missing start and end times of OLV.
1 code implementation • 2 Sep 2021 • Hao Deng, Yang Zheng, Jin Chen, Shuyan Yu, Keyan Xiao, Xiancheng Mao
The three-dimensional (3D) geological models are the typical and key data source in the 3D mineral prospecitivity modeling.
no code implementations • 10 Jun 2021 • Wen Fang, Hao Deng, Qingwen Liu, Mingqing Liu, Mengyuan Xu, Liuqing Yang, Georgios B. Giannakis
Integrating the wireless power transfer (WPT) technology into the wireless communication system has been important for operational cost saving and power-hungry problem solving of electronic devices.
no code implementations • 30 Jan 2021 • Mingliang Xiong, Mingqing Liu, Qingwei Jiang, Jie zhou, Qingwen Liu, Hao Deng
Optical wireless communications (OWC) utilizing infrared or visible light as the carrier attracts great attention in 6G research.
no code implementations • 25 Dec 2019 • Jianfei Cui, He Zhu, Hao Deng, Ziwei Chen, Dianbo Liu
Sometimes electrical medical records are restricted and difficult to centralize for machine learning, which could only be trained in distributed manner that involved many institutions in the process.
no code implementations • 30 Nov 2018 • Li Huang, Yifeng Yin, Zeng Fu, Shifa Zhang, Hao Deng, Dianbo Liu
One challenge in applying federated machine learning is the possibly different distributions of data from diverse sources.
no code implementations • 3 Feb 2018 • Mingqing Liu, Qingwen Liu, Mingliang Xiong, Hao Deng, Xinhe Wang
We propose here the next generation of power delivery network -- mobile power network (MPN) for wireless power transfer within a mobile range from several meters to tens of meters.
no code implementations • 27 Oct 2016 • Peixin Hou, Hao Deng, Jiguang Yue, Shuguang Liu
Experiments show that parameters $\sigma_v$ and $\alpha$ make the clustering process more easy to control, and main features of PCM and APCM are unified in this new clustering framework (UPCM).