no code implementations • COLING 2022 • Weidong Tian, Haodong Li, Zhong-Qiu Zhao
The attention mechanism can highlight fine-grained features with critical information, thus ensuring that feature extraction emphasizes the objects related to the questions.
no code implementations • 19 May 2024 • Zejun Gu, Zhong-Qiu Zhao, Hao Shen, Zhao Zhang
Furthermore, we design a Coarse-grained Information Interaction (CII) module to adequately leverage human body structural information.
no code implementations • 19 May 2024 • Zejun Gu, Zhong-Qiu Zhao, Henghui Ding, Hao Shen, Zhao Zhang, De-Shuang Huang
In this framework, we construct a scale-adaptive projector ensemble (SAPE) module to spatially align feature maps between models of varying input resolutions.
1 code implementation • 14 Aug 2023 • Hao Shen, Zhong-Qiu Zhao, Yulun Zhang, Zhao Zhang
Multi-stage architectures have exhibited efficacy in image dehazing, which usually decomposes a challenging task into multiple more tractable sub-tasks and progressively estimates latent hazy-free images.
1 code implementation • 22 Nov 2022 • Hao Shen, Zhong-Qiu Zhao, Wandi Zhang
To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features.
no code implementations • 19 Nov 2022 • Yi Yang, Zhong-Qiu Zhao, Quan Bai, Qing Liu, Weihua Li
Due to the dynamic nature, the proposed algorithms can also estimate true labels online without re-visiting historical data.
no code implementations • 21 Apr 2021 • Zhong-Qiu Zhao, Yao Gao, Yuchen Ge, Weidong Tian
Experimental results on COCO and OCHuman keypoints datasets show that our proposed ODKD can improve the performance of different lightweight models by a large margin, and HRNet-W16 equipped with ODKD achieves state-of-the-art performance for lightweight human pose estimation.
no code implementations • 15 Jul 2018 • Zhong-Qiu Zhao, Peng Zheng, Shou-tao Xu, Xindong Wu
Traditional object detection methods are built on handcrafted features and shallow trainable architectures.
no code implementations • 21 Aug 2016 • Jing Wang, Meng Wang, Pei-Pei Li, Luoqi Liu, Zhong-Qiu Zhao, Xuegang Hu, Xindong Wu
The problem assumes that features are generated individually but there are group structure in the feature stream.
1 code implementation • 27 Apr 2014 • Can-Yi Lu, Hai Min, Zhong-Qiu Zhao, Lin Zhu, De-Shuang Huang, Shuicheng Yan
If the subspaces from which the data drawn are independent or orthogonal, they are able to obtain a block diagonal affinity matrix, which usually leads to a correct segmentation.