A Siamese Long Short-Term Memory Architecture for Human Re-identification

Varior, Rahul Rama; Shuai, Bing; Lu, Jiwen; Xu, Dong; Wang, Gang

doi:10.1007/978-3-319-46478-7_9

Cited by 426 publications

(321 citation statements)

References 59 publications

(124 reference statements)

Supporting

Mentioning

320

Contrasting

Order By: Relevance

“…In this part, we also compare the proposed method and several supervised methods on Market1501. The compared methods include three non-deep-learning-based methods (LOMO + XQDA [72], BoW+Kissme [4] and DNSL [51]) and thirteen deep-learning-based methods (PersonNet [55], Gate S-CNN [56], LSTM S-CNN [57], DGDropout [5], Deep-Embed [59], SpindleNet [18], Part-Aligned [15], PIE [17], JLML [45], MTMCT [58], SVDNet [54], PDC [16] and A 3 M [14]). Particularly, PIE, MTMCT, SVDNet and A 3 M use the same backbone network (i.e., ResNet-50 [64]) with our method.…”

Section: Comparison With Supervised Methodsmentioning

confidence: 99%

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Wang

Huo

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intracamera (within-camera) labels but not inter-camera (crosscamera) labels. In real-world applications, these intra-camera labels can be readily captured by tracking algorithms or few manual annotations, when compared with cross-camera labels. In this case, it is very difficult to explore the relationships between cross-camera persons in the training stage due to the lack of cross-camera label information. To deal with this issue, we propose a novel Progressive Cross-camera Soft-label Learning (PCSL) framework for the semi-supervised person Re-ID task, which can generate cross-camera soft-labels and utilize them to optimize the network. Concretely, we calculate an affinity matrix based on person-level features and adapt them to produce the similarities between cross-camera persons (i.e., cross-camera soft-labels). To exploit these soft-labels to train the network, we investigate the weighted cross-entropy loss and the weighted triplet loss from the classification and discrimination perspectives, respectively. Particularly, the proposed framework alternately generates progressive cross-camera soft-labels and gradually improves feature representations in the whole learning course. Extensive experiments on five large-scale benchmark datasets show that PCSL significantly outperforms the state-of-the-art unsupervised methods that employ labeled source domains or the images generated by the GAN-based models. Furthermore, the proposed method even has a competitive performance with respect to deep supervised Re-ID methods.

show abstract

Section: Comparison With Supervised Methodsmentioning

confidence: 99%

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Wang

Huo

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…In fact, CNNs are able to extract different features from a given image, representing them as a set of output maps avoiding manual effort in fea-ture engineering. Image-based Automatic Person Re-Identification is one of the fields in which CNNs achieved remarkable results [19,20,21,22,23,24].…”

Section: Related Workmentioning

confidence: 99%

Video-Based Convolutional Attention for Person Re-Identification

Zamprogno

Passon

Martinel

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras. We propose a Siamese framework in which video frames of the person to re-identify and of the candidate one are processed by two identical networks which produce a similarity score. We introduce an attention mechanisms to capture the relevant information both at frame level (spatial information) and at video level (temporal information given by the importance of a specific frame within the sequence). One of the novelties of our approach is given by a joint concurrent processing of both frame and video levels, providing in such a way a very simple architecture. Despite this fact, out approach achieves better performance than the state-of-the-art on the challenging iLIDS-VID dataset.

show abstract

“…It is possible to exploit the dependency among local regions by utilizing long short-term memory (LSTM) cells as the constituent components in the conventional Siamese network. Taking this intuition into account, in [33], the authors propose a LSTM-based architecture to process image regions sequentially and enhance the discriminative capability of local feature representation by leveraging contextual information. Following the same pipeline, the authors in [34] proposed a sequential fusion framework that combines the frame-wise appearance information as well as temporal information to generate a robust sequence-level human representation.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Multiple Detections for Person Re-Identification

2018

View full text Add to dashboard Cite

Re-identification systems aim at recognizing the same individuals in multiple cameras, and one of the most relevant problems is that the appearance of same individual varies across cameras due to illumination and viewpoint changes. This paper proposes the use of cumulative weighted brightness transfer functions (CWBTFs) to model these appearance variations. Different from recently proposed methods which only consider pairs of images to learn a brightness transfer function, we exploit such a multiple-frame-based learning approach that leverages consecutive detections of each individual to transfer the appearance. We first present a CWBTF framework for the task of transforming appearance from one camera to another. We then present a re-identification framework where we segment the pedestrian images into meaningful parts and extract features from such parts, as well as from the whole body. Jointly, both of these frameworks contribute to model the appearance variations more robustly. We tested our approach on standard multi-camera surveillance datasets, showing consistent and significant improvements over existing methods on three different datasets without any other additional cost. Our approach is general and can be applied to any appearance-based method.

show abstract

A Siamese Long Short-Term Memory Architecture for Human Re-identification

Cited by 426 publications

References 59 publications

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Progressive Cross-Camera Soft-Label Learning for Semi-Supervised Person Re-Identification

Video-Based Convolutional Attention for Person Re-Identification

Exploiting Multiple Detections for Person Re-Identification

Contact Info

Product

Resources

About