no code implementations • 10 Aug 2023 • Pan Liang, Danwei Ye, Zihao Zhu, Yunchao Wang, Wang Xia, Ronghua Liang, Guodao Sun
Large language models (LLMs), such as ChatGPT, have demonstrated outstanding performance in various fields, particularly in natural language understanding and generation tasks.
1 code implementation • 28 Jun 2023 • Guoyu Yang, Jie Lei, Zhikuan Zhu, Siyu Cheng, Zunlei Feng, Ronghua Liang
Multi-scale features are of great importance in encoding objects with scale variance in object detection tasks.
no code implementations • 20 Mar 2023 • Haohao Sun, Yilong Zhang, Peng Chen, Haixia Wang, Ronghua Liang
As a non-invasive optical imaging technique, optical coherence tomography (OCT) has proven promising for automatic fingerprint recognition system (AFRS) applications.
no code implementations • 21 Feb 2023 • Binwei Xu, Haoran Liang, Weihua Gong, Ronghua Liang, Peng Chen
Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels.
no code implementations • 20 Feb 2023 • Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai, Xiaofei He, Ronghua Liang
Compared to 2D images, 3D point clouds are much more sensitive to rotations.
no code implementations • 4 Dec 2022 • Binwei Xu, Haoran Liang, Ronghua Liang, Peng Chen
BAB aims to help predict accurate boundaries, whose input is the synthetic image.
1 code implementation • 1 Aug 2022 • Xing Zhao, Haoran Liang, Peipei Li, Guodao Sun, Dongdong Zhao, Ronghua Liang, Xiaofei He
Moreover, inspired by the boundary supervision commonly used in image salient object detection (ISOD), we design a motion-aware loss for predicting object boundary motion and simultaneously perform multitask learning for VSOD and object motion prediction, which can further facilitate the model to extract spatiotemporal features accurately and maintain the object integrity.
no code implementations • 11 Jun 2022 • Sujia Zhu, Yue Shen, Zihao Zhu, Wang Xia, Baofeng Chang, Ronghua Liang, Guodao Sun
To fill the absence of combined causes discovery on temporal event sequence data, eliminating and recruiting principles are defined to balance the effectiveness and controllability on cause combinations.
1 code implementation • 26 May 2022 • Baofeng Chang, Sujia Zhu, Qi Jiang, Wang Xia, Jingwei Tang, Lvhan Pan, Ronghua Liang, Guodao Sun
To provide an effective analysis method for this type of dynamic graph data, we propose a snapshot generation algorithm involving Human-In-Loop to help users divide the dynamic graphs into multi-granularity and hierarchical snapshots for further analysis.
1 code implementation • 5 Apr 2022 • Binwei Xu, Haoran Liang, Wentian Ni, Weihua Gong, Ronghua Liang, Peng Chen
Recent deep learning-based video salient object detection (VSOD) has achieved some breakthrough, but these methods rely on expensive annotated videos with pixel-wise annotations, weak annotations, or part of the pixel-wise annotations.
no code implementations • 18 Dec 2021 • Jiazhou Chen, Yanghui Xu, Shufang Lu, Ronghua Liang, Liangliang Nan
Based on these global masks, 3D roof instances are segmented out by mask back-projections and extended to the entire building instances through a Markov random field optimization.
no code implementations • 13 Oct 2020 • Chaoqing Xu, Tyson Neuroth, Takanori Fujiwara, Ronghua Liang, Kwan-Liu Ma
Diffusion tensor imaging (DTI) has been used to study the effects of neurodegenerative diseases on neural pathways, which may lead to more reliable and early diagnosis of these diseases as well as a better understanding of how they affect the brain.