1 code implementation • 17 Feb 2024 • Yulong Shi, Mingwei Sun, Yongshuai Wang, Rui Wang, Hui Sun, Zengqiang Chen
Vision transformers have achieved encouraging progress in various computer vision tasks.
1 code implementation • 11 Feb 2024 • Mengmei Zhang, Mingwei Sun, Peng Wang, Shen Fan, Yanhu Mo, Xiaoxiao Xu, Hong Liu, Cheng Yang, Chuan Shi
Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks.
no code implementations • 3 Feb 2024 • Lu Wang, Li Chang, Ruipeng Zhang, Kexun Li, Yu Wang, Wei Chen, Xuanlin Feng, Mingwei Sun, Qi Wang, Charles Damien Lu, Jun Zeng, Hua Jiang
Excessive energy intake increased mortality rapidly in the early period of the acute phase.
1 code implementation • 10 Oct 2023 • Yulong Shi, Mingwei Sun, Yongshuai Wang, Rui Wang, Hui Sun, Zengqiang Chen
Additionally, a Bionic Eagle Vision (BEV) block based on BFSA is designed in this study.
no code implementations • 20 Sep 2023 • Xuyang Chen, Dong Wang, Konrad Schindler, Mingwei Sun, Yongliang Wang, Nicolo Savioli, Liqiu Meng
Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features.
no code implementations • 28 Jun 2022 • Lei Wang, Min Dai, Jianan He, Jingwei Huang, Mingwei Sun
Then, we convert vector shape prediction, regularization, and topology reconstruction into a unique primitive graph learning problem.
no code implementations • 12 Dec 2021 • Zhihua Hu, Bo Duan, Yanfeng Zhang, Mingwei Sun, Jingwei Huang
We jointly train a layout module to produce an initial layout and a novel MVS module to obtain accurate layout geometry.
2 code implementations • CVPR 2021 • Jingwei Huang, Shan Huang, Mingwei Sun
We propose a novel approach for large-scale nonlinear least squares problems based on deep learning frameworks.
1 code implementation • ICCV 2021 • Jingwei Huang, Yanfeng Zhang, Mingwei Sun
We present PrimitiveNet, a novel approach for high-resolution primitive instance segmentation from point clouds on a large scale.