专栏首页专知【论文推荐】最新六篇行人再识别(ReID)相关论文—和谐注意力网络、时序残差学习、评估和基准、图像生成、三元组、对抗属性-图像

【论文推荐】最新六篇行人再识别(ReID)相关论文—和谐注意力网络、时序残差学习、评估和基准、图像生成、三元组、对抗属性-图像

【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. Harmonious Attention Network for Person Re-Identification(和谐注意力网络的行人再识别)



作者:Wei Li,Xiatian Zhu,Shaogang Gong

摘要:Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned person images potentially with large human pose variations and unconstrained auto-detection errors. In this work, we show the advantages of jointly learning attention selection and feature representation in a Convolutional Neural Network (CNN) by maximising the complementary information of different levels of visual attention subject to re-id discriminative learning constraints. Specifically, we formulate a novel Harmonious Attention CNN (HA-CNN) model for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Extensive comparative evaluations validate the superiority of this new HA-CNN model for person re-id over a wide variety of state-of-the-art methods on three large-scale benchmarks including CUHK03, Market-1501, and DukeMTMC-ReID.

期刊:arXiv, 2018年2月23日

网址

http://www.zhuanzhi.ai/document/8de7cacc9829744baf6f1f62fc7bdc13

2. Video Person Re-identification by Temporal Residual Learning(基于时序残差学习机制的视频行人再识别)



作者:Ju Dai,Pingping Zhang,Huchuan Lu,Hongyu Wang

摘要:In this paper, we propose a novel feature learning framework for video person re-identification (re-ID). The proposed framework largely aims to exploit the adequate temporal information of video sequences and tackle the poor spatial alignment of moving pedestrians. More specifically, for exploiting the temporal information, we design a temporal residual learning (TRL) module to simultaneously extract the generic and specific features of consecutive frames. The TRL module is equipped with two bi-directional LSTM (BiLSTM), which are respectively responsible to describe a moving person in different aspects, providing complementary information for better feature representations. To deal with the poor spatial alignment in video re-ID datasets, we propose a spatial-temporal transformer network (ST^2N) module. Transformation parameters in the ST^2N module are learned by leveraging the high-level semantic information of the current frame as well as the temporal context knowledge from other frames. The proposed ST^2N module with less learnable parameters allows effective person alignments under significant appearance changes. Extensive experimental results on the large-scale MARS, PRID2011, ILIDS-VID and SDU-VID datasets demonstrate that the proposed method achieves consistently superior performance and outperforms most of the very recent state-of-the-art methods.

期刊:arXiv, 2018年2月22日

网址

http://www.zhuanzhi.ai/document/35e9bad2861c1b00d01a1af4431041ec

3. A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets(行人再识别的系统评估和基准:特性、度量和数据集)



作者:Srikrishna Karanam,Mengran Gou,Ziyan Wu,Angels Rates-Borras,Octavia Camps,Richard J. Radke

摘要:Person re-identification (re-id) is a critical problem in video analytics applications such as security and surveillance. The public release of several datasets and code for vision algorithms has facilitated rapid progress in this area over the last few years. However, directly comparing re-id algorithms reported in the literature has become difficult since a wide variety of features, experimental protocols, and evaluation metrics are employed. In order to address this need, we present an extensive review and performance evaluation of single- and multi-shot re-id algorithms. The experimental protocol incorporates the most recent advances in both feature extraction and metric learning. To ensure a fair comparison, all of the approaches were implemented using a unified code library that includes 11 feature extraction algorithms and 22 metric learning and ranking techniques. All approaches were evaluated using a new large-scale dataset that closely mimics a real-world problem setting, in addition to 16 other publicly available datasets: VIPeR, GRID, CAVIAR, DukeMTMC4ReID, 3DPeS, PRID, V47, WARD, SAIVT-SoftBio, CUHK01, CHUK02, CUHK03, RAiD, iLIDSVID, HDA+ and Market1501. The evaluation codebase and results will be made publicly available for community use.

期刊:arXiv, 2018年2月15日

网址

http://www.zhuanzhi.ai/document/7bf2307d60a318b6c3a5b1f965995a4c

4. Pose-Normalized Image Generation for Person Re-identification(pose归一化图像生成的行人再识别)



作者:Xuelin Qian,Yanwei Fu,Wenxuan Wang,Tao Xiang,Yang Wu,Yu-Gang Jiang,Xiangyang Xue

摘要:Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for synthesizing realistic person images conditional on pose. The model is based on a generative adversarial network (GAN) and used specifically for pose normalization in re-id, thus termed pose-normalization GAN (PN-GAN). With the synthesized images, we can learn a new type of deep re-id feature free of the influence of pose variations. We show that this feature is strong on its own and highly complementary to features learned with the original images. Importantly, we now have a model that generalizes to any new re-id dataset without the need for collecting any training data for model fine-tuning, thus making a deep re-id model truly scalable. Extensive experiments on five benchmarks show that our model outperforms the state-of-the-art models, often significantly. In particular, the features learned on Market-1501 can achieve a Rank-1 accuracy of 68.67% on VIPeR without any model fine-tuning, beating almost all existing models fine-tuned on the dataset.

期刊:arXiv, 2018年2月13日

网址

http://www.zhuanzhi.ai/document/d7ba094688fc85c5f1b958023d1adfe9

5. Triplet-based Deep Similarity Learning for Person Re-Identification(基于三元组的深度相似性学习的行人再识别)



作者:Wentong Liao,Michael Ying Yang,Ni Zhan,Bodo Rosenhahn

摘要:In recent years, person re-identification (re-id) catches great attention in both computer vision community and industry. In this paper, we propose a new framework for person re-identification with a triplet-based deep similarity learning using convolutional neural networks (CNNs). The network is trained with triplet input: two of them have the same class labels and the other one is different. It aims to learn the deep feature representation, with which the distance within the same class is decreased, while the distance between the different classes is increased as much as possible. Moreover, we trained the model jointly on six different datasets, which differs from common practice - one model is just trained on one dataset and tested also on the same one. However, the enormous number of possible triplet data among the large number of training samples makes the training impossible. To address this challenge, a double-sampling scheme is proposed to generate triplets of images as effective as possible. The proposed framework is evaluated on several benchmark datasets. The experimental results show that, our method is effective for the task of person re-identification and it is comparable or even outperforms the state-of-the-art methods.

期刊:arXiv, 2018年2月9日

网址

http://www.zhuanzhi.ai/document/84a25d8af361247b4a3bc487ee56493f

6. Adversarial Attribute-Image Person Re-identification(基于对抗属性-图像的行人再识别)



作者:Zhou Yin,Wei-Shi Zheng,Ancong Wu,Hong-Xing Yu,Hai Wang,Jianhuang Lai

摘要:While attributes have been widely used for person re-identification (Re-ID) that matches the same person images across disjoint camera views, they are used either as extra features or for performing multi-task learning to assist the image-image person matching task. However, how to find a set of person images according to a given attribute description, which is very practical in many surveillance applications, remains a rarely investigated cross-modal matching problem in Person Re-ID. In this work, we present this challenge and employ adversarial learning to formulate the attribute-image cross-modal person Re-ID model. By imposing the regularization on the semantic consistency constraint across modalities, the adversarial learning enables generating image-analogous concepts for query attributes and getting it matched with image in both global level and semantic ID level. We conducted extensive experiments on three attribute datasets and demonstrated that the adversarial modelling is so far the most effective for the attributeimage cross-modal person Re-ID problem.

期刊:arXiv, 2018年2月6日

网址

http://www.zhuanzhi.ai/document/d6697d1a774afd59e7e8a218d8f4c36a

本文分享自微信公众号 - 专知(Quan_Zhuanzhi),作者:专知内容组

原文出处及转载信息见文内详细说明,如有侵权,请联系 yunjia_community@tencent.com 删除。

原始发表时间:2018-03-01

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。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • 【论文推荐】最新六篇图像分割相关论文—控制、全卷积网络、子空间表示、多模态图像分割

    【导读】专知内容组整理了最近六篇图像分割(Image Segmentation)相关文章,为大家进行介绍,欢迎查看! 1.Virtual-to-Real: Le...

    WZEARW
  • 【论文推荐】最新5篇目标跟踪(Object Tracking)相关论文—并行跟踪和验证、光流、自动跟踪、相关滤波集成、CFNet

    【导读】专知内容组整理了最近五篇目标跟踪(Object Tracking)相关文章,为大家进行介绍,欢迎查看! 1. Parallel Tracking and...

    WZEARW
  • 【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...

    WZEARW
  • 【CCF-CV特别活动】“CCF-腾讯犀牛鸟沙龙”走进腾讯优图

    中国计算机学会计算机视觉专委会走进企业系列交流会 CCF-CV@Industry 腾讯优图·上海 主题:图像识别和多媒体分析技术前沿 时间:2016年5月13日...

    腾讯高校合作
  • SCI闪电速递-快速发表论文杂志整理

    每到年底,都是大家最愁文章的时候。对于毕业了,已经参加工作的,过了年就要交国自然基金的标书,而自己的标书还没有扎实的工作基础;对于没毕业的,过年就意味着交毕业论...

    用户6317549
  • 高级知识评估:基于结果分析,重新设计基于药学专业的网络考试(CS CAS)

    各地信息技术的使用导致对新的教育方式有需求。现代化的电子学习环境将学生的学习知识和技能的教学,学习和评估带入了一个新时代,且考虑到学生的电子学习动机。高等数学课...

    时代在召唤
  • 亚马逊提出:用于人群计数的尺度感知注意力网络

    最近出了真的很多论文,各种SOTA。比如前天po的商汤等提出:统一多目标跟踪框架,今天po的人群计数(Crowd Counting),又称人群密度估计。下次应该...

    Amusi
  • 【论文推荐】最新5篇目标跟踪(Object Tracking)相关论文—并行跟踪和验证、光流、自动跟踪、相关滤波集成、CFNet

    【导读】专知内容组整理了最近五篇目标跟踪(Object Tracking)相关文章,为大家进行介绍,欢迎查看! 1. Parallel Tracking and...

    WZEARW
  • 【世界读书日】2018版十大引用数最高的深度学习论文集合

    量化投资与机器学习微信公众号
  • Auto-Encoding GAN

    Mihaela Rosca, Balaji Lakshminarayanan, David Warde-Farley, Shakir Mohamed

    用户1908973

扫码关注云+社区

领取腾讯云代金券