Exploiting Local Shape Information for Cross-Modal Person Re-identification

Uddin, Kamal; Lam, Antony; Fukuda, Hisato; Kobayashi, Yoshinori; Kuno, Yoshinori

doi:10.1007/978-3-030-26766-7_8

Cited by 4 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For both datasets, integrating cross-modal attention improves the recognition accuracy by a significant margin in all measures. Including cross-modal attention we outperform the reported accuracy of the local shape method (Uddin et al, 2019) in rank-1 accuracy. Since Uddin et al Uddin et al (2019) do not report the used instance split and do not perform a validation (i.e., they use 40 instead of 32 training instances as we do), the improved rank-1 performance of our method indicates the superiority of our approach.…”

Section: Experimental Analysis With Cross-modal Attentionmentioning

confidence: 82%

“…The same features will be extracted for both modalities and are compared on the basis of Euclidean distance and the additional metric learning step Cross-view Quadratic Discriminant Analysis (XQDA). Additionally, the matching of Eigen-depth and HOG/SLTP features as reported by Zhuo et al (2017) and the local shape method (Uddin et al, 2019) is included in Table 3 for the BIWI dataset. Table 3 presents the metrics of state-of-the-art and proposed networks for different scenarios on the BIWI dataset and in Table 4 the results for the RobotPKU dataset are shown.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

“…Zhuo et al (2017) used the same features to perform cross-modal re-identification between depth and RGB. Uddin et al (2019) combined a body partitioning method and a HOG based feature extraction with a metric learning approach to enable cross-modal person re-identification.…”

Section: Related Workmentioning

confidence: 99%

“…Zhuo et al (2017) did not provide any details on their evaluation procedure. Uddin et al (2019) used different splits without a validation step (using 40 instead of 32 training instances as we do), thus their reported numbers might be too optimistic.…”

Section: Tablementioning

confidence: 99%

See 3 more Smart Citations

Cross-modal distillation for RGB-depth person re-identification

Hafner¹,

Bhuyian

Kooij

et al. 2022

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Section: Experimental Analysis With Cross-modal Attentionmentioning

confidence: 82%

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Tablementioning

confidence: 99%

See 2 more Smart Citations

Cross-modal distillation for RGB-depth person re-identification

Hafner¹,

Bhuyian

Kooij

et al. 2022

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…In the Re-ID literature, publicly available RGB–D and IR sensor-based datasets [ 4 , 14 , 33 , 35 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 ] have been recorded for specific purposes because some Re-ID approaches use different domains combinedly to improve the performance of Re-ID [ 33 , 34 , 35 , 36 , 37 , 38 , 39 , 47 , 48 ] while other approaches use cross-domain methods [ 49 , 50 , 51 , 52 , 53 ] in the Re-ID framework to continue surveillance between daytime visible images and nighttime infrared images. Still, some Re-ID methods consider only IR–IR [ 17 , 54 ] matching using the publicly available datasets.…”

Section: Introductionmentioning

confidence: 99%

Person Re-Identification with RGB–D and RGB–IR Sensors: A Comprehensive Survey

Uddin

Bhuiyan

Bappee

et al. 2023

Sensors

View full text Add to dashboard Cite

Learning about appearance embedding is of great importance for a variety of different computer-vision applications, which has prompted a surge in person re-identification (Re-ID) papers. The aim of these papers has been to identify an individual over a set of non-overlapping cameras. Despite recent advances in RGB–RGB Re-ID approaches with deep-learning architectures, the approach fails to consistently work well when there are low resolutions in dark conditions. The introduction of different sensors (i.e., RGB–D and infrared (IR)) enables the capture of appearances even in dark conditions. Recently, a lot of research has been dedicated to addressing the issue of finding appearance embedding in dark conditions using different advanced camera sensors. In this paper, we give a comprehensive overview of existing Re-ID approaches that utilize the additional information from different sensor-based methods to address the constraints faced by RGB camera-based person Re-ID systems. Although there are a number of survey papers that consider either the RGB–RGB or Visible-IR scenarios, there are none that consider both RGB–D and RGB–IR. In this paper, we present a detailed taxonomy of the existing approaches along with the existing RGB–D and RGB–IR person Re-ID datasets. Then, we summarize the performance of state-of-the-art methods on several representative RGB–D and RGB–IR datasets. Finally, future directions and current issues are considered for improving the different sensor-based person Re-ID systems.

show abstract