Saliency Weighted Features for Person Re-identification

By Niki Martinel, Christian Micheloni, Gian Luca Foresti. 2014

144 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Dual Attention Matching Network for Context-Aware Feature Sequence Based Person Re-identification (2018, background): “Person Re-Identiﬁcation (ReID) aims at associating the same pedestrian across multiple cameras [13, 63], which has attracted rapidly increased attention in the computer vision community due to its importance for many potential applications, such as video surveillance analysis and content-based…”
Joint Learning of Single-Image and Cross-Image Representations for Person Re-identification (2016, background): “resentation of a given image [13, 14, 16, 28, 20, 17, 26, 7] and (ii) classification on cross-image representation, which is the representation of an image pair [19, 1, 24].”
Pose-Normalized Image Generation for Person Re-identification (2017, background): “Person Re-identiﬁcation (re-id) aims to match a person across multiple non-overlapping camera views [16].”
Person Re-Identification by Deep Joint Learning of Multi-Loss Classification (2017, background): “This is an inherently challenging task because person visual appearance may change dramatically in different camera views from different locations due to unknown changes in human pose, illumination, occlusion, and background clutter [Gong et al. , 2014].”
Person Recognition in Personal Photo Collections (2017, background): “There exist multiple tasks related to person recognition [34] differing mainly in the amount of training and testing data.”
Domain-Adversarial Training of Neural Networks (2015, methodology): “Finally, we evaluate domain-adversarial descriptor learning in the context of person re-identiﬁcation application (Gong et al., 2014), where the task is to obtain good pedestrian image descriptors that are suitable for retrieval and veriﬁcation.”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, background): “Several surveys on person Re-ID already exist, most of which are concentrated in hand-crafted systems [1], [2], [31], though some surveys have also summarized the deep learning techniques [37], [38].”
Features for Multi-target Multi-camera Tracking and Re-identification (2018, background): “Discriminative power is improved by saliency information [50, 80] or by learning features specific to body parts [14, 20, 21, 26, 27, 39, 42], either in the image [6, 7, 24] or back-projected onto an articulated [2, 23] or monolithic [3] 3D body model.”
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, background): “Person re-identiﬁcation (ReID) [6, 43] aims to match images of a person across dis-joint cameras, which is widely ∗ Equal contribution, works done as interns in Megvii Research. used in video surveillance, security and smart city.”
Harmonious Attention Network for Person Re-identification (2018, background): “These give rise to the notorious image matching misalignment challenge in cross-view re-id [7].”
Performance Measures and a Data Set for Multi-target, Multi-camera Tracking (2016, background): “Discriminative power is improved by saliency information [33, 34] or learning features specific to body parts [6, 18, 20–23, 27], either in the image [35–37] or back-projected onto an articulated [38, 39] or monolithic [40] 3D body model.”
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification (2020, background): “Person Re-Identiﬁcation (Re-ID) (Gong et al. 2014; Zheng, Yang, and Hauptmann 2016) is widely used in various applications such as video surveillance, security and smart city.”
An improved deep learning architecture for person re-identification (2015, methodology): “Features that have been used include variations on color histograms [25, 11, 12, 20, 14, 29], local binary patterns [25, 11, 12, 20, 14], Gabor features [14], color names [26], and local patches [28].”
Learning a Discriminative Null Space for Person Re-identification (2016, background): “The problem of person re-identiﬁcation (re-id) has at-tracted great attention in the past ﬁve years [34, 10].”
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, background): “Person re-identiﬁcation (Re-ID) aims to match images of a person captured from non-overlapping camera views [7, 44, 54].”