An improved deep learning architecture for person re-identification

Ahmed, Ejaz; Jones, Michael; Marks, Tim K.

doi:10.1109/cvpr.2015.7299016

Cited by 1,177 publications

(1,047 citation statements)

References 19 publications

Supporting

Mentioning

1,039

Contrasting

Unclassified

Order By: Relevance

“…Li et al [14] learned a unified deep filter by introducing a patch matching layer and a max-out grouping layer for person re-identification. Ahmed et al [15] presented a deep convolutional architecture that captured local relationships between person images based on mid-level features. Generally, deep learning is usually utilized to learn feature representations by using deep convolutional features [14][15][16][17] or from the fully connected features [18][19][20] in person re-identification works.…”

Section: Related Workmentioning

confidence: 99%

“…Unsupervised/semisupervised approaches include SDALF [10], eSDC [13], TSR [36], SSCDL [37], Null-semi [38], and fully supervised baselines including KISSME [24], kLDFA [39], DeepNN [15], Null Space [38], and XQDA [40]. Semisupervised person reidentification usually assumes the availability of one-third of the training set, while the whole training set of fully supervised approaches is labelled and adopted in learning procedure.…”

Section: Experiments On Vipermentioning

confidence: 99%

“…(i) Feature construction and learning aim at designing or studying discriminative appearance descriptions [8][9][10][11][12][13][14][15][16][17][18][19][20] that are robust for distinguishing different pedestrians across arbitrary cameras. However, handcrafted feature construction is extremely challenging due to miscellaneous and complicated variations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Co-Metric Learning for Person Re-Identification

Leng

2018

Advances in Multimedia

View full text Add to dashboard Cite

Person re-identification, aiming to identify the same pedestrian images across disjoint camera views, is a key technique of intelligent video surveillance. Although existing methods have developed both theories and experimental results, most of effective ones pertain to fully supervised training styles, which suffer the small sample size (SSS) problem a lot, especially in label-insufficient practical applications. To bridge SSS problem and learning model with small labels, a novel semisupervised co-metric learning framework is proposed to learn a discriminative Mahalanobis-like distance matrix for label-insufficient person re-identification. Different from typical co-training task that contains multiview data originally, single-view person images are firstly decomposed into pseudo two views, and then metric learning models are produced and jointly updated based on both pseudo-labels and references iteratively. Experiments carried out on three representative person re-identification datasets show that the proposed method performs better than state of the art and possesses low label sensitivity.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Experiments On Vipermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Co-Metric Learning for Person Re-Identification

Leng

2018

Advances in Multimedia

View full text Add to dashboard Cite

show abstract

“…These cameras can cooperate, forming a wireless visual sensing network whose nodes besides visual sensing, also have processing, storage and communication capabilities. Because the smart camera networks have become increasingly more affordable and perform better in balancing the computational power and energy efficiency, they have been employed in many surveillance tasks including distributed object recognition [1], [2], [3], [4], cross view action recognition [5], [6] and person reidentification [7], [8] to name just a few.…”

Section: Introductionmentioning

confidence: 99%

Feature encoding in band-limited distributed surveillance systems

Rahimpour

Taalimi

2017

2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Distributed surveillance systems have become popular in recent years due to security concerns. However, transmitting high dimensional data in bandwidth-limited distributed systems becomes a major challenge. In this paper, we address this issue by proposing a novel probabilistic algorithm based on the divergence between the probability distributions of the visual features in order to reduce their dimensionality and thus save the network bandwidth in distributed wireless smart camera networks. We demonstrate the effectiveness of the proposed approach through extensive experiments on two surveillance recognition tasks.

show abstract

“…To further improve accuracy of correct matches, supervised learning algorithms are applied that learn to separate similar feature pairs from dissimilar ones [Ch16,ZXG16]. More recently, deep learning has drawn increasing interest from the research community with Convolution Neural Networks (CNN) outperforming hand-crafted feature descriptors, as they are able to learn more expressive features [AJM15,WCZ16].…”

Section: Introductionmentioning

confidence: 99%

Multimodal Neural Network for Overhead Person Re-Identification

Lejbolle

Nasrollahi

Krogh

et al. 2017

2017 International Conference of the Biometrics Special Interest Group (BIOSIG)

View full text Add to dashboard Cite

Person re-identification is a topic which has potential to be used for applications within forensics, flow analysis and queue monitoring. It is the process of matching persons across two or more camera views, most often by extracting colour and texture based hand-crafted features, to identify similar persons. Because of challenges regarding changes in lighting between views, occlusion or even privacy issues, more focus has turned to overhead and depth based camera solutions. Therefore, we have developed a system, based on a Convolutional Neural Network (CNN) which is trained using both depth and RGB modalities to provide a fused feature. By training on a locally collected dataset, we achieve a rank-1 accuracy of 74.69%, increased by 16.00% compared to using a single modality. Furthermore, tests on two similar publicly available benchmark datasets of TVPR and DPI-T show accuracies of 77.66% and 90.36%, respectively, outperforming state-of-the-art results by 3.60% and 5.20%, respectively.

show abstract

An improved deep learning architecture for person re-identification

Cited by 1,177 publications

References 19 publications

Co-Metric Learning for Person Re-Identification

Co-Metric Learning for Person Re-Identification

Feature encoding in band-limited distributed surveillance systems

Multimodal Neural Network for Overhead Person Re-Identification

Contact Info

Product

Resources

About