no code implementations • 5 May 2024 • Yimin Jiang, Huibing Wang, Jinjia Peng, Xianping Fu, Yang Wang
In SEAS, a Background Modulation Network (BMN) is designed to encode the feature extracted from the detected bounding box into a multi-granularity embedding, which reduces the input of background noise from multiple levels with norm-aware.
no code implementations • 5 May 2024 • Tianxiang Cui, Huibing Wang, Jinjia Peng, Ruoxi Deng, Xianping Fu, Yang Wang
Unsupervised person search aims to localize a particular target person from a gallery set of scene images without annotations, which is extremely challenging due to the unexpected variations of the unlabeled domains.
no code implementations • 20 Jun 2020 • Jinjia Peng, Yang Wang, Huibing Wang, Zhao Zhang, Xianping Fu, Meng Wang
For PAL, a data adaptation module is employed for source domain, which generates the images with similar data distribution to unlabeled target domain as ``pseudo target samples''.
Unsupervised Vehicle Re-Identification Vehicle Re-Identification
no code implementations • 3 May 2020 • Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha, Jiande Jiang, Xinbo Gao, Wen Lu, Jing Liu, Kwangjin Yoon, Taegyun Jeon, Kazutoshi Akita, Takeru Ooba, Norimichi Ukita, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Dongliang He, Wenhao Wu, Yukang Ding, Chao Li, Fu Li, Shilei Wen, Jianwei Li, Fuzhi Yang, Huan Yang, Jianlong Fu, Byung-Hoon Kim, JaeHyun Baek, Jong Chul Ye, Yuchen Fan, Thomas S. Huang, Junyeop Lee, Bokyeung Lee, Jungki Min, Gwantae Kim, Kanghyu Lee, Jaihyun Park, Mykola Mykhailych, Haoyu Zhong, Yukai Shi, Xiaojun Yang, Zhijing Yang, Liang Lin, Tongtong Zhao, Jinjia Peng, Huibing Wang, Zhi Jin, Jiahao Wu, Yifu Chen, Chenming Shang, Huanrong Zhang, Jeongki Min, Hrishikesh P. S, Densen Puthussery, Jiji C. V
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
no code implementations • 16 Mar 2020 • Huibing Wang, Jinjia Peng, Guangqi Jiang, Fengqiang Xu, Xianping Fu
In TCPM, triplet-center loss is introduced to ensure each part of vehicle features extracted has intra-class consistency and inter-class separability.
no code implementations • 12 Jan 2020 • Huibing Wang, Jinjia Peng, Dongyan Chen, Guangqi Jiang, Tongtong Zhao, Xianping Fu
Specially, an attribute-guided module is proposed in AGNet to generate the attribute mask which could inversely guide to select discriminative features for category classification.
no code implementations • 21 Dec 2019 • Jinjia Peng, Guangqi Jiang, Dongyan Chen, Tongtong Zhao, Huibing Wang, Xianping Fu
Vehicle re-identification (reID) often requires recognize a target vehicle in large datasets captured from multi-cameras.
no code implementations • 11 Dec 2019 • Guangqi Jiang, Huibing Wang, Jinjia Peng, Dongyan Chen, Xianping Fu
To address these problems, we propose a novel binary code algorithm for clustering, which adopts graph embedding to preserve the original data structure, called (Graph-based Multi-view Binary Learning) GMBL in this paper.
no code implementations • 10 Jul 2019 • Yuxiao Yan, Yang Yan, Jinjia Peng, Huibing Wang, Xianping Fu
Different from the previous methods, this paper try to purify real image by extracting discriminative and robust features to convert outdoor real images to indoor synthetic images.
no code implementations • 30 Apr 2019 • Jinjia Peng, Huibing Wang, Xianping Fu
To address this problem, this paper proposes a domain adaptation framework for vehicle reID (DAVR), which narrows the cross-domain bias by fully exploiting the labeled data from the source domain to adapt the target domain.
no code implementations • 1 Apr 2019 • Huibing Wang, Jinjia Peng, Xianping Fu
However, facing with features from multiple views, it's difficult for most dimension reduction methods to fully comprehended multi-view features and integrate compatible and complementary information from these features to construct low-dimensional subspace directly.
no code implementations • 19 Mar 2019 • Jinjia Peng, Huibing Wang, Tongtong Zhao, Xianping Fu
Vehicle re-identification (reID) is to identify a target vehicle in different cameras with non-overlapping views.
no code implementations • 19 Mar 2019 • Huibing Wang, Jinjia Peng, Xianping Fu
With the development of multimedia time, one sample can always be described from multiple views which contain compatible and complementary information.
no code implementations • 19 Mar 2019 • Tongtong Zhao, Yuxiao Yan, Jinjia Peng, Huibing Wang, Xianping Fu
To solve this problem, the previous method learned a model to improve the realism of the synthetic images.
no code implementations • 8 Oct 2018 • Tongtong Zhao, Yuxiao Yan, Jinjia Peng, Zetian Mi, Xianping Fu
In an attempt to address this issue, previous method is to improve the realism of synthetic images by learning a model.