中文
相关论文

相关论文: SBSGAN: Suppression of Inter-Domain Background Shi…

200 篇论文

Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a…

计算机视觉与模式识别 · 计算机科学 2017-10-19 Dangwei Li , Xiaotang Chen , Zhang Zhang , Kaiqi Huang

In this paper, we focus on model generalization and adaptation for cross-domain person re-identification (Re-ID). Unlike existing cross-domain Re-ID methods, leveraging the auxiliary information of those unlabeled target-domain data, we aim…

计算机视觉与模式识别 · 计算机科学 2019-05-31 Haijun Liu , Jian Cheng , Shiguang Wang , Wen Wang

The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. Hence learning a feature representation that can adaptively…

计算机视觉与模式识别 · 计算机科学 2021-12-01 Sanping Zhou , Jinjun Wang , Deyu Meng , Yudong Liang , Yihong Gong , Nanning Zheng

Due to the deteriorated conditions of \mbox{illumination} lack and uneven lighting, nighttime images have lower contrast and higher noise than their daytime counterparts of the same scene, which limits seriously the performances of…

计算机视觉与模式识别 · 计算机科学 2020-04-14 Zhenfeng Zhu , Yingying Meng , Deqiang Kong , Xingxing Zhang , Yandong Guo , Yao Zhao

Background subtraction is a fundamental task in computer vision with numerous real-world applications, ranging from object tracking to video surveillance. Dynamic backgrounds poses a significant challenge here. Supervised deep…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Fateme Bahri , Nilanjan Ray

Recent adversarial learning research has achieved very impressive progress for modelling cross-domain data shifts in appearance space but its counterpart in modelling cross-domain shifts in geometry space lags far behind. This paper…

计算机视觉与模式识别 · 计算机科学 2019-07-24 Fangneng Zhan , Chuhui Xue , Shijian Lu

Recent studies on multi-domain facial image translation have achieved impressive results. The existing methods generally provide a discriminator with an auxiliary classifier to impose domain translation. However, these methods neglect…

计算机视觉与模式识别 · 计算机科学 2021-11-30 Xiaokang Zhang , Yuanlue Zhu , Wenting Chen , Wenshuang Liu , Linlin Shen

Unsupervised foreground-background segmentation aims at extracting salient objects from cluttered backgrounds, where Generative Adversarial Network (GAN) approaches, especially layered GANs, show great promise. However, without human…

计算机视觉与模式识别 · 计算机科学 2023-10-10 Qiran Zou , Yu Yang , Wing Yin Cheung , Chang Liu , Xiangyang Ji

Drastic variations in illumination across surveillance cameras make the person re-identification problem extremely challenging. Current large scale re-identification datasets have a significant number of training subjects, but lack…

计算机视觉与模式识别 · 计算机科学 2018-04-27 Slawomir Bak , Peter Carr , Jean-Francois Lalonde

Image generation has raised tremendous attention in both academic and industrial areas, especially for the conditional and target-oriented image generation, such as criminal portrait and fashion design. Although the current studies have…

计算机视觉与模式识别 · 计算机科学 2021-12-07 Songyao Jiang , Hongfu Liu , Yue Wu , Yun Fu

Cross-domain transfer learning (CDTL) is an extremely challenging task for the person re-identification (ReID). Given a source domain with annotations and a target domain without annotations, CDTL seeks an effective method to transfer the…

计算机视觉与模式识别 · 计算机科学 2018-11-12 Wenqi Liang , Guangcong Wang , Jianhuang Lai , Junyong Zhu

Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed versions) of an input. In this paper, we incorporate a…

计算机视觉与模式识别 · 计算机科学 2021-03-31 Hao Chen , Yaohui Wang , Benoit Lagadec , Antitza Dantcheva , Francois Bremond

Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other…

计算机视觉与模式识别 · 计算机科学 2019-07-15 Kirthi Shankar Sivamani

Visible-Infrared person re-identification (VI-ReID) is a challenging matching problem due to large modality varitions between visible and infrared images. Existing approaches usually bridge the modality gap with only feature-level…

计算机视觉与模式识别 · 计算机科学 2021-02-25 Haojie Liu , Shun Ma , Daoxun Xia , Shaozi Li

This paper proposes a novel self-supervised based Cut-and-Paste GAN to perform foreground object segmentation and generate realistic composite images without manual annotations. We accomplish this goal by a simple yet effective…

计算机视觉与模式识别 · 计算机科学 2023-04-06 Kunal Chaturvedi , Ali Braytee , Jun Li , Mukesh Prasad

This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a…

计算机视觉与模式识别 · 计算机科学 2023-01-03 Hao Chen , Yaohui Wang , Benoit Lagadec , Antitza Dantcheva , Francois Bremond

Recently, the cycle-consistent generative adversarial networks (CycleGAN) has been widely used for synthesis of multi-domain medical images. The domain-specific nonlinear deformations captured by CycleGAN make the synthesized images…

计算机视觉与模式识别 · 计算机科学 2018-08-14 Chengjia Wang , Gillian Macnaught , Giorgos Papanastasiou , Tom MacGillivray , David Newby

Generative Adversarial Networks (GANs) have facilitated a new direction to tackle the image-to-image transformation problem. Different GANs use generator and discriminator networks with different losses in the objective function. Still…

计算机视觉与模式识别 · 计算机科学 2021-11-30 Kancharagunta Kishan Babu , Shiv Ram Dubey

In recent years, cross-spectral iris recognition has emerged as a promising biometric approach to establish the identity of individuals. However, matching iris images acquired at different spectral bands (i.e., matching a visible (VIS) iris…

计算机视觉与模式识别 · 计算机科学 2021-08-21 Moktari Mostofa , Salman Mohamadi , Jeremy Dawson , Nasser M. Nasrabadi

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for…

计算机视觉与模式识别 · 计算机科学 2021-04-02 Junhui Yin , Jiayan Qiu , Siqing Zhang , Jiyang Xie , Zhanyu Ma , Jun Guo