【论文推荐】最新六篇行人再识别相关论文—特定视角、多目标、双注意匹配网络、联合属性-身份、迁移学习、多通道金字塔型

【导读】专知内容组整理了最近六篇行人再识别(Person Re-Identification)相关文章,为大家进行介绍,欢迎查看!

1. Learning View-Specific Deep Networks for Person Re-Identification(学习特定视角深度网络的行人再识别)



作者:Zhanxiang Feng,Jianhuang Lai,Xiaohua Xie

摘要:In recent years, a growing body of research has focused on the problem of person re-identification (re-id). The re-id techniques attempt to match the images of pedestrians from disjoint non-overlapping camera views. A major challenge of re-id is the serious intra-class variations caused by changing viewpoints. To overcome this challenge, we propose a deep neural network-based framework which utilizes the view information in the feature extraction stage. The proposed framework learns a view-specific network for each camera view with a cross-view Euclidean constraint (CV-EC) and a cross-view center loss (CV-CL). We utilize CV-EC to decrease the margin of the features between diverse views and extend the center loss metric to a view-specific version to better adapt the re-id problem. Moreover, we propose an iterative algorithm to optimize the parameters of the view-specific networks from coarse to fine. The experiments demonstrate that our approach significantly improves the performance of the existing deep networks and outperforms the state-of-the-art methods on the VIPeR, CUHK01, CUHK03, SYSU-mReId, and Market-1501 benchmarks.

期刊:arXiv, 2018年3月30日

网址

http://www.zhuanzhi.ai/document/daa50570436444908cc84b6e4ac4b373

2. Features for Multi-Target Multi-Camera Tracking and Re-Identification(多目标多摄像头跟踪和行人再识别的特征)



作者:Ergys Ristani,Carlo Tomasi

机构:Duke University

摘要:Multi-Target Multi-Camera Tracking (MTMCT) tracks many people through video taken from several cameras. Person Re-Identification (Re-ID) retrieves from a gallery images of people similar to a person query image. We learn good features for both MTMCT and Re-ID with a convolutional neural network. Our contributions include an adaptive weighted triplet loss for training and a new technique for hard-identity mining. Our method outperforms the state of the art both on the DukeMTMC benchmarks for tracking, and on the Market-1501 and DukeMTMC-ReID benchmarks for Re-ID. We examine the correlation between good Re-ID and good MTMCT scores, and perform ablation studies to elucidate the contributions of the main components of our system. Code is available.

期刊:arXiv, 2018年3月29日

网址

http://www.zhuanzhi.ai/document/6e80d20c9524dd130519189922488a10

3. Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identification(基于上下文感知特征序列行人再识别的双注意匹配网络)



作者:Jianlou Si,Honggang Zhang,Chun-Guang Li,Jason Kuen,Xiangfei Kong,Alex C. Kot,Gang Wang

机构:Beijing University of Posts and Telecommunications, Beijing

摘要:Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods based on a single feature vector are not sufficient enough to overcome visual ambiguity, which frequently occurs in real scenario. In this paper, we propose a novel end-to-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comparison simultaneously. The core component of our DuATM framework is a dual attention mechanism, in which both intra-sequence and inter-sequence attention strategies are used for feature refinement and feature-pair alignment, respectively. Thus, detailed visual cues contained in the intermediate feature sequences can be automatically exploited and properly compared. We train the proposed DuATM network as a siamese network via a triplet loss assisted with a de-correlation loss and a cross-entropy loss. We conduct extensive experiments on both image and video based ReID benchmark datasets. Experimental results demonstrate the significant advantages of our approach compared to the state-of-the-art methods.

期刊:arXiv, 2018年3月27日

网址

http://www.zhuanzhi.ai/document/5a1030689db1d3a1e07a6baae2ec604a

4. Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification(基于可转移的联合属性-身份深度学习的无监督行人重识别



作者:Jingya Wang,Xiatian Zhu,Shaogang Gong,Wei Li

机构:Queen Mary University of London

摘要:Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair. This significantly limits their scalability and usability in real-world large scale deployments with the need for performing re-id across many camera views. To address this scalability problem, we develop a novel deep learning method for transferring the labelled information of an existing dataset to a new unseen (unlabelled) target domain for person re-id without any supervised learning in the target domain. Specifically, we introduce an Transferable Joint Attribute-Identity Deep Learning (TJ-AIDL) for simultaneously learning an attribute-semantic and identitydiscriminative feature representation space transferrable to any new (unseen) target domain for re-id tasks without the need for collecting new labelled training data from the target domain (i.e. unsupervised learning in the target domain). Extensive comparative evaluations validate the superiority of this new TJ-AIDL model for unsupervised person re-id over a wide range of state-of-the-art methods on four challenging benchmarks including VIPeR, PRID, Market-1501, and DukeMTMC-ReID.

期刊:arXiv, 2018年3月27日

网址

http://www.zhuanzhi.ai/document/65b5a31db67109a0eb6f215e977beafa

5. Unsupervised Cross-dataset Person Re-identification by Transfer Learning of Spatial-Temporal Patterns(通过迁移学习时空模式进行无监督跨数据集的行人再识别)



作者:Jianming Lv,Weihang Chen,Qing Li,Can Yang

机构:South China University of Technology,City University of Hongkongy

摘要:Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting. It is challenging to incrementally optimize the models by using the abundant unlabeled data collected from the target domain. To address this challenge, we propose an unsupervised incremental learning algorithm, TFusion, which is aided by the transfer learning of the pedestrians' spatio-temporal patterns in the target domain. Specifically, the algorithm firstly transfers the visual classifier trained from small labeled source dataset to the unlabeled target dataset so as to learn the pedestrians' spatial-temporal patterns. Secondly, a Bayesian fusion model is proposed to combine the learned spatio-temporal patterns with visual features to achieve a significantly improved classifier. Finally, we propose a learning-to-rank based mutual promotion procedure to incrementally optimize the classifiers based on the unlabeled data in the target domain. Comprehensive experiments based on multiple real surveillance datasets are conducted, and the results show that our algorithm gains significant improvement compared with the state-of-art cross-dataset unsupervised person re-identification algorithms.

期刊:arXiv, 2018年3月20日

网址

http://www.zhuanzhi.ai/document/0522841c63093f56ebca3f6847d4368b

6. Multi-Channel Pyramid Person Matching Network for Person Re-Identification(利用多通道金字塔型行人匹配网络进行行人再识别)



作者:Chaojie Mao,Yingming Li,Yaqing Zhang,Zhongfei Zhang,Xi Li

机构:Zhejiang University

摘要:In this work, we present a Multi-Channel deep convolutional Pyramid Person Matching Network (MC-PPMN) based on the combination of the semantic-components and the color-texture distributions to address the problem of person re-identification. In particular, we learn separate deep representations for semantic-components and color-texture distributions from two person images and then employ pyramid person matching network (PPMN) to obtain correspondence representations. These correspondence representations are fused to perform the re-identification task. Further, the proposed framework is optimized via a unified end-to-end deep learning scheme. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our approach against the state-of-the-art literature, especially on the rank-1 recognition rate.

期刊:arXiv, 2018年3月7日

网址

http://www.zhuanzhi.ai/document/2a28452f9dad43cbba6c3ef5dc8e6729

原文发布于微信公众号 - 专知(Quan_Zhuanzhi)

原文发表时间:2018-04-13

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

发表于

我来说两句

0 条评论
登录 后参与评论

相关文章

来自专栏专知

【论文推荐】最新5篇知识图谱相关论文—强化学习、习知识图谱的表示、词义消除歧义、并行翻译嵌入、图数据库

【导读】专知内容组整理了最近五篇知识图谱(Knowledge Graph)相关文章,为大家进行介绍,欢迎查看! 1. DeepPath: A Reinforce...

4524
来自专栏专知

【论文推荐】最新六篇视频分类相关论文—层次标签推断、知识图谱、CNNs、DAiSEE、表观和关系网络、转移学习

【导读】专知内容组整理了最近六篇视频分类(Video Classification)相关文章,为大家进行介绍,欢迎查看! 1. Hierarchical Lab...

5325
来自专栏CVer

谷歌CVPR 2018最全总结:45篇论文,Ian Goodfellow GAN演讲PPT下载

谷歌在今年的CVPR上表现强势,有超过200名谷歌员工将在大会上展示论文或被邀请演讲,45篇论文被接收。在计算机视觉领域,生成对抗网络GAN无疑是最受关注的主题...

4733
来自专栏专知

【论文推荐】最新八篇行人再识别相关论文—多级高斯模型、密度自适应、注意力感知组成网络、图像-图像域适应、自适应采样

2402
来自专栏专知

【干货】Python大数据处理库PySpark实战——使用PySpark处理文本多分类问题

【导读】近日,多伦多数据科学家Susan Li发表一篇博文,讲解利用PySpark处理文本多分类问题的详情。我们知道,Apache Spark在处理实时数据方面...

12K9
来自专栏专知

【论文推荐】最新八篇网络节点表示相关论文—可扩展嵌入、对抗自编码器、图划分、异构信息、显式矩阵分解、深度高斯、图、随机游走

【导读】专知内容组整理了最近八篇网络节点表示(Network Embedding)相关文章,为大家进行介绍,欢迎查看! 1.SIGNet: Scalable E...

7556
来自专栏大数据挖掘DT机器学习

机器学习&数据挖掘知识点大总结

Basis(基础): MSE(Mean Square Error 均方误差), LMS(LeastMean Square 最小均方), LSM(L...

42114
来自专栏专知

【论文推荐】最新七篇行人再识别相关论文—深度排序、风格自适应、对抗、重排序、多层次相似性、深度空间特征重构、图对应迁移

【导读】既昨天推出六篇行人再识别文章,专知内容组今天又推出最近七篇行人再识别(Person Re-Identification)相关文章,为大家进行介绍,欢迎查...

7177
来自专栏PPV课数据科学社区

【学习】常用的机器学习&数据挖掘知识点

Basis(基础): MSE(Mean Square Error 均方误差),LMS(LeastMean Square 最小均方),LSM(Least Squa...

36412
来自专栏专知

【论文推荐】最新十二篇情感分析相关论文—自然语言推理框架、网络事件、多任务学习、实时情感变化检测、多因素分析、深度语境词表示

2426

扫码关注云+社区

领取腾讯云代金券