no code implementations • 22 May 2024 • Senmao Tian, Haoyu Gao, Gangyi Hong, Shuyun Wang, JingJie Wang, Xin Yu, Shunli Zhang
Minor variations in silhouette sequences can be diminished in the network's intermediate layers due to the accumulation of quantization errors.
no code implementations • 27 Feb 2024 • Junzhe Chen, Qiao Yang, Senmao Tian, Shunli Zhang
It is critical to deploy complicated neural network models on hardware with limited resources.
no code implementations • 1 Jan 2024 • Beibei Lin, Yeying Jin, Wending Yan, Wei Ye, Yuan Yuan, Shunli Zhang, Robby Tan
However, the intricacies of the real world, particularly with the presence of light effects and low-light regions affected by noise, create significant domain gaps, hampering synthetic-trained models in removing rain streaks properly and leading to over-saturation and color shifts.
Ranked #2 on
Rain Removal
on Nightrain
no code implementations • 26 Sep 2023 • Qiao Yang, Yu Zhang, Zijing Zhao, Jian Zhang, Shunli Zhang
Infrared and visible image fusion (IVIF) is used to generate fusion images with comprehensive features of both images, which is beneficial for downstream vision tasks.
no code implementations • 26 Sep 2023 • Qiao Yang, Yu Zhang, Jian Zhang, Zijing Zhao, Shunli Zhang, Jinqiao Wang, Junzhe Chen
Most existing learning-based infrared and visible image fusion (IVIF) methods exhibit massive redundant information in the fusion images, i. e., yielding edge-blurring effect or unrecognizable for object detectors.
no code implementations • 6 May 2023 • XIAOYU GUO, Xiang Wei, Qi Su, Huiqin Zhao, Shunli Zhang
Semantic segmentation in rainy scenes is a challenging task due to the complex environment, class distribution imbalance, and limited annotated data.
no code implementations • 13 Apr 2023 • Huicheng Pi, Senmao Tian, Ming Lu, Jiaming Liu, Yandong Guo, Shunli Zhang
In these works, omnidirectional frames are projected from the 3D sphere to a 2D plane by Equi-Rectangular Projection (ERP).
1 code implementation • CVPR 2023 • Senmao Tian, Ming Lu, Jiaming Liu, Yandong Guo, Yurong Chen, Shunli Zhang
Therefore, we design a strategy to build an Edge-to-Bit lookup table that maps the edge score of a patch to the bit of each layer during inference.
no code implementations • ICCV 2023 • Ming Wang, Xianda Guo, Beibei Lin, Tian Yang, Zheng Zhu, Lincheng Li, Shunli Zhang, Xin Yu
This is the first framework on gait recognition that is designed to focus on the extraction of dynamic features.
no code implementations • 15 Nov 2022 • Heming Du, Chen Liu, Ming Wang, Lincheng Li, Shunli Zhang, Xin Yu
We measure the uncertainty and predict the match status of the recognition results, and thus determine whether the probe is an OOG query. To the best of our knowledge, our method is the first attempt to tackle OOG queries in gait recognition.
2 code implementations • 2 Aug 2022 • Beibei Lin, Shunli Zhang, Ming Wang, Lincheng Li, Xin Yu
GFR extractor aims to extract contextual information, e. g., the relationship among various body parts, and the mask-based LFR extractor is presented to exploit the detailed posture changes of local regions.
no code implementations • 8 Mar 2022 • Chuanfu Shen, Beibei Lin, Shunli Zhang, George Q. Huang, Shiqi Yu, Xin Yu
Also, we design an Inception-like ReverseMask Block, which has three branches composed of a global branch, a feature dropping branch, and a feature scaling branch.
Ranked #4 on
Gait Recognition
on OUMVLP
1 code implementation • 8 Mar 2022 • Ming Wang, Beibei Lin, Xianda Guo, Lincheng Li, Zheng Zhu, Jiande Sun, Shunli Zhang, Xin Yu
ECM consists of the Spatial-Temporal feature extractor (ST), the Frame-Level feature extractor (FL) and SPB, and has two obvious advantages: First, each branch focuses on a specific representation, which can be used to improve the robustness of the network.
no code implementations • ICCV 2021 • Beibei Lin, Shunli Zhang, Xin Yu
Towards this goal, we take advantage of both global visual information and local region details and develop a Global and Local Feature Extractor (GLFE).