Filters








16,301 Hits in 10.5 sec

Hard-Aware Point-to-Set Deep Metric for Person Re-identification [article]

Rui Yu, Zhiyong Dou, Song Bai, Zhaoxiang Zhang, Yongchao Xu, Xiang Bai
2018 arXiv   pre-print
To solve this problem, we propose a Hard-Aware Point-to-Set (HAP2S) loss with a soft hard-mining scheme.  ...  Deep metric learning provides a satisfactory solution to person re-ID by training a deep network under supervision of metric loss, e.g., triplet loss.  ...  We propose a Hard-Aware Point-to-Set (HAP2S) loss for person re-ID in the main paper, and show that it consistently achieves higher re-ID accuracies than other losses on three large-scale datasets.  ... 
arXiv:1807.11206v1 fatcat:jahihklmqrhpbiva2w7rhmgd5a

Hard-Aware Point-to-Set Deep Metric for Person Re-identification [chapter]

Rui Yu, Zhiyong Dou, Song Bai, Zhaoxiang Zhang, Yongchao Xu, Xiang Bai
2018 Lecture Notes in Computer Science  
To solve this problem, we propose a Hard-Aware Point-to-Set (HAP2S) loss with a soft hard-mining scheme.  ...  Deep metric learning provides a satisfactory solution to person re-ID by training a deep network under supervision of metric loss, e.g., triplet loss.  ...  We would also like to thank the reviewers for their helpful comments.  ... 
doi:10.1007/978-3-030-01270-0_12 fatcat:xdz6rgwo6fgfjp6zuqdfqqau5m

Deep Camera-Aware Metric Learning for Person Reidentification

Wei Liu, Ping Liang, Lei Liu, Zhiqiang Hao, Xin Xu, Zhili Zhou
2021 Wireless Communications and Mobile Computing  
In this paper, we propose a deep camera-aware metric learning (DCAML) model, where images on the identity-level spaces are further projected into different camera-level subspaces, which can explore the  ...  Person reidentification (re-id) suffers from a challenging issue due to the significant inconsistency of the camera network, including position, view, and brands.  ...  Camera-Aware Person Re-Id. Metric learning is widely studied for person re-id.  ... 
doi:10.1155/2021/8859088 fatcat:t27cv37qtbbrbdagqsh6olhxzu

Set Augmented Triplet Loss for Video Person Re-Identification [article]

Pengfei Fang, Pan Ji, Lars Petersson, Mehrtash Harandi
2020 arXiv   pre-print
Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss.  ...  Apart from the commonly-used set distance metrics (e.g., ordinary distance and Hausdorff distance), we further propose a hybrid distance metric, tailored for the set-aware triplet loss.  ...  Person Re-identification Most popular solutions for person re-ID mainly focus on learning an appearance-discriminative representation [43] .  ... 
arXiv:2011.00774v2 fatcat:xmkxgxidbrgpvgz4zzbytxst24

On Learning Density Aware Embeddings [article]

Soumyadeep Ghosh, Richa Singh, Mayank Vatsa
2019 arXiv   pre-print
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes.  ...  The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class.  ...  [12] proposed the triplet center loss where the center of the set of anchors and the center of the nearest negative cluster were utilized in the loss function of the triplet loss, for person re-identification  ... 
arXiv:1904.03911v1 fatcat:izztuyi74beitnq6ipawawcrfq

On Learning Density Aware Embeddings

Soumyadeep Ghosh, Richa Singh, Mayank Vatsa
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes.  ...  The proposed method, termed as Density Aware Metric Learning, enforces the model to learn embeddings that are pulled towards the most dense region of the clusters for each class.  ...  [12] proposed the triplet center loss where the center of the set of anchors and the center of the nearest negative cluster were utilized in the loss function of the triplet loss, for person re-identification  ... 
doi:10.1109/cvpr.2019.00502 dblp:conf/cvpr/Ghosh0V19 fatcat:azpqszdysbdtrkvpaxmq75qbhq

Deep Metric Learning by Online Soft Mining and Class-Aware Attention

Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Neil M. Robertson
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points.  ...  Extensive experiments on two fine-grained visual categorisation datasets and two video-based person re-identification benchmarks show that our method significantly outperforms the state-of-the-art.  ...  For fine-grained categorisation, we set c = 8 and k = 7 for each mini-batch, while c = 3 and k = 18 for video-based person re-identification.  ... 
doi:10.1609/aaai.v33i01.33015361 fatcat:wklvfundbjd25lb2pthegegzam

Deep Metric Learning by Online Soft Mining and Class-Aware Attention [article]

Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Neil M. Robertson
2019 arXiv   pre-print
Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points.  ...  Extensive experiments on two fine-grained visual categorisation datasets and two video-based person re-identification benchmarks show that our method significantly outperforms the state-of-the-art.  ...  For fine-grained categorisation, we set c = 8 and k = 7 for each mini-batch, while c = 3 and k = 18 for video-based person re-identification.  ... 
arXiv:1811.01459v3 fatcat:ntm2v4vjcfdfhmlhhjjkle7y7u

Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification [article]

Zhiyuan Chen, Annan Li, Shilu Jiang, Yunhong Wang
2020 arXiv   pre-print
Video-based person re-identification (Re-ID) is an important computer vision task.  ...  In this paper, we address this issue by introducing a new metric learning method called Attribute-aware Identity-hard Triplet Loss (AITL), which reduces the intra-class variation among positive samples  ...  Metric Learning for Person Re-ID Except for the batch-hard triplet loss [13] , some other metric learning methods are also applied to handle the person Re-ID task, such as Quadruplet loss [3] and Margin  ... 
arXiv:2006.07597v1 fatcat:rrgd624rxzb75cmo6pwwzs6vty

Deep Learning for Person Re-identification: A Survey and Outlook [article]

Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, Steven C. H. Hoi
2021 arXiv   pre-print
Meanwhile, we introduce a new evaluation metric (mINP) for person Re-ID, indicating the cost for finding all the correct matches, which provides an additional criteria to evaluate the Re-ID system for  ...  Person re-identification (Re-ID) aims at retrieving a person of interest across multiple non-overlapping cameras.  ...  A hard-aware point-to-set deep metric learning [155] is designed to mine the informative hard triplets based on the point to set similarity.  ... 
arXiv:2001.04193v2 fatcat:4d3thmsr3va2tnu72nawlu2wxy

Distribution Context Aware Loss for Person Re-identification [article]

Zhigang Chang, Qin Zhou, Mingyang Yu, Shibao Zheng, Hua Yang, Tai-Pang Wu
2019 arXiv   pre-print
To learn the optimal similarity function between probe and gallery images in Person re-identification, effective deep metric learning methods have been extensively explored to obtain discriminative feature  ...  In this paper, we propose a novel Distribution Context Aware (DCA) loss based on triplet loss to combine both numerical similarity and relation similarity in feature space for better clustering.  ...  INTRODUCTION Person re-identification (Re-ID) is a challenging problem.  ... 
arXiv:1911.07273v1 fatcat:y3lfoj2h3ba6bo5vq7zevyo7fi

Context-Aware Graph Convolution Network for Target Re-identification [article]

Deyi Ji, Haoran Wang, Hanzhe Hu, Weihao Gan, Wei Wu, Junjie Yan
2021 arXiv   pre-print
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks.  ...  with low computation complexity.Experiments show that the proposed method achieves state-of-the-art performance on both person and vehicle re-identification datasets in a plug and play fashion with limited  ...  Related Work Re-identification. Re-identification (Re-ID) tasks focus on both person and vehicle, and have been extensively studied in the passed few years.  ... 
arXiv:2012.04298v3 fatcat:2ylhyvu3qne6xgbbz7f2khd7u4

Resource Aware Person Re-identification across Multiple Resolutions [article]

Yan Wang, Lequn Wang, Yurong You, Xu Zou, Vincent Chen, Serena Li, Gao Huang, Bharath Hariharan, Kilian Q. Weinberger
2018 arXiv   pre-print
However, prevailing person re-identification(re-ID) methods use one-size-fits-all high-level embeddings from deep convolutional networks for all cases.  ...  To remedy this, we present a new person re-ID model that combines effective embeddings built on multiple convolutional network layers, trained with deep-supervision.  ...  Current person re-identification(re-ID) systems treat both persons the same way. Both images would be run through deep convolutional neural networks (CNNs).  ... 
arXiv:1805.08805v3 fatcat:lk2xgddpujerfivs4qejz5izbe

Attribute-Aware Attention Model for Fine-grained Representation Learning [article]

Kai Han, Jianyuan Guo, Chao Zhang, Mingjian Zhu
2019 arXiv   pre-print
How to learn a discriminative fine-grained representation is a key point in many computer vision applications, such as person re-identification, fine-grained classification, fine-grained image retrieval  ...  Most of the previous methods focus on learning metrics or ensemble to derive better global representation, which are usually lack of local information.  ...  to help select key features for person re-identification and fine-grained recognition.  ... 
arXiv:1901.00392v2 fatcat:b6e3jwho2jhsnk5bohm32tnbo4

Open-world person re-identification with RGBD camera in top-view configuration for Retail Applications

Massimo Martini, Marina Paolanti, Emanuele Frontoni
2020 IEEE Access  
This paper presents the first attempt to solve a more realistic re-ID setting, designed to face these important issues called Top-View Open-World (TVOW) person re-id.  ...  Person re-identification (re-ID) is currently a notably topic in the computer vision and pattern recognition communities.  ...  ACKNOWLEDGMENT The authors would like to thank R. Pietrini, M Contigiani, and L Di Bello for their support.  ... 
doi:10.1109/access.2020.2985985 fatcat:eunbtjmhvncrddmqnlv7bcqwo4
« Previous Showing results 1 — 15 out of 16,301 results