no code implementations • 16 Jan 2024 • Fei Guo, Yikang Wang, Han Qi, Wenping Jin, Li Zhu
In each view, we fuse the prompt embedding as consistent information with visual and the global or local temporal context to overcome the overlapping distribution of classes and outliers.
1 code implementation • 12 Dec 2023 • Han Qi, Fei Guo, Li Zhu
This paper aims to design a multi-armed bandit algorithm that can be implemented without using information about the reward distribution while still achieving substantial regret upper bounds.
no code implementations • 2 Dec 2023 • Fei Guo, Li Zhu, Yikang Wang, Han Qi
Although some multi-modal works use labels as supplementary to construct prototypes of support videos, they can not use this information for query videos.
1 code implementation • 5 Jul 2023 • Fei Guo, Li Zhu, YiWang Wang, Jing Sun
The second module (MLT) focuses on the Multiple-level feature of the support prototype and query sample to mine more information for the alignment, which operates on different level features.
1 code implementation • 30 Mar 2023 • Wenping Jin, Fei Guo, Li Zhu
In the subsequent stage, we apply pixel-level data augmentation techniques to generate corrupted normal images and their corresponding pixel labels.
no code implementations • 8 Mar 2023 • Junkai Fan, Fei Guo, Jianjun Qian, Xiang Li, Jun Li, Jian Yang
In particular, we explore a non-alignment scenario that a clear reference image, unaligned with the input hazy image, is utilized to supervise the dehazing network.
no code implementations • 19 Aug 2022 • Shiqiang Ma, Xuejian Li, Jijun Tang, Fei Guo
However, segmentation networks pay too much attention to the main visual difference between foreground and background, and ignores the detailed edge information, which leads to a reduction in the accuracy of edge segmentation.
no code implementations • 26 Apr 2022 • Xuejian Li, Shiqiang Ma, Jijun Tang, Fei Guo
These differences will affect the results of the automatic segmentation methods.
1 code implementation • CVPR 2022 • Jinchao Yang, Fei Guo, Shuo Chen, Jun Li, Jian Yang
Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product.
no code implementations • 9 Mar 2020 • Liaojun Pang, Jiong Chen, Fei Guo, Zhicheng Cao, Heng Zhao
Detecting the singular point accurately and efficiently is one of the most important tasks for fingerprint recognition.