SFANet: A Spectrum-Aware Feature Augmentation Network for Visible-Infrared Person Reidentification

Liu, Haojie; Ma, Shun; Xia, Daoxun; Li, Shaozi

doi:10.1109/tnnls.2021.3105702

Cited by 40 publications

(21 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to conventional appearance discrepancy, it also suffers from the modality discrepancy originating from different wavelength ranges of spectrum cameras [34]. To handle such cross-modality discrepancies, early works try to learn a modality-sharable feature representation using feature-level constraints [19], [35], [37], [38], [44]. They design novel classification and/or triplet losses for pointing at optimizing cross-modality samples.…”

Section: B Visible-infrared Re-id Methodsmentioning

confidence: 99%

“…For each identity, 10 images are captured by the visible camera, and 10 images are obtained by the thermal camera. We following a previously developed evaluation protocol [19] that randomly splits the dataset into two halves and alternatively uses all visible/thermal images as the gallery set.…”

Section: A Datasets and Evaluation Metricmentioning

confidence: 99%

“…Similar improvement can be observed under thermal-to-visible mode. For instance, AGMNet beats the SFANet [19] that adopts the same backbone model and training environment by 15.20% in terms of Rank-1 accuracy and 17.42% in terms of mAP. Moreover, It also outperforms the best SOTA method CAJL [40] by 0.59%, 3.37% and 4.20% respectively in terms of Rank-1 accuracy, mAP and mINP.…”

Section: E Comparison To the State-of-the-artmentioning

confidence: 99%

See 2 more Smart Citations

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

Liu¹,

Xia²,

Jiang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Section: B Visible-infrared Re-id Methodsmentioning

confidence: 99%

Section: A Datasets and Evaluation Metricmentioning

confidence: 99%

Section: E Comparison To the State-of-the-artmentioning

confidence: 99%

See 1 more Smart Citation

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

Liu¹,

Xia²,

Jiang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

“…Wang et al added a pixel alignment module based on feature alignment module [47] to further reduce the gap between the two modalities [12]. However, Liu et al [55] thought that those methods employing GAN to generate fake images destroy the structure information of generated images and introduce plenty of noise. Hence, they replaced fake images generated by GAN with grayscale images with three channels.…”

Section: Modality Translationmentioning

confidence: 99%

Visible-Infrared Person Re-Identification: A Comprehensive Survey and a New Setting

et al. 2022

View full text Add to dashboard Cite

Person re-identification (ReID) plays a crucial role in video surveillance with the aim to search a specific person across disjoint cameras, and it has progressed notably in recent years. However, visible cameras may not be able to record enough information about the pedestrian’s appearance under the condition of low illumination. On the contrary, thermal infrared images can significantly mitigate this issue. To this end, combining visible images with infrared images is a natural trend, and are considerably heterogeneous modalities. Some attempts have recently been contributed to visible-infrared person re-identification (VI-ReID). This paper provides a complete overview of current VI-ReID approaches that employ deep learning algorithms. To align with the practical application scenarios, we first propose a new testing setting and systematically evaluate state-of-the-art methods based on our new setting. Then, we compare ReID with VI-ReID in three aspects, including data composition, challenges, and performance. According to the summary of previous work, we classify the existing methods into two categories. Additionally, we elaborate on frequently used datasets and metrics for performance evaluation. We give insights on the historical development and conclude the limitations of off-the-shelf methods. We finally discuss the future directions of VI-ReID that the community should further address.

show abstract

“…With the arrival of modernization, digitalization and information age, the rapid development of computer technology and the internet has continuously promoted the reform of finance, medicine, military and other fields. [1][2][3] Introducing advanced computer technology into the field of educational research is also an irresistible trend. After various learning management systems 4 and network teaching tools 5 swept the whole educational field, there have been increasingly relevant unstructured data(images, videos, audio, and texts) about students and teachers.…”

Section: Introductionmentioning

confidence: 99%

Real‐time sentiment analysis of students based on mini‐Xception architecture for wisdom classroom

Tian

Tang

Zhu

et al. 2022

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Sentiment analysis has a wide application prospect in business, medicine, security and other fields, which provides a new perspective for the development of education. Students' sentiment data play an important role in the evaluation of teachers' teaching quality and students' learning effect, and provide a basis for the implementation of effective learning intervention. However, most of the research is to obtain the real-time learning status of students in the classroom through teachers' naked eye observation and students' text feedback, which will lead to some problems such as incomplete feedback content and delayed feedback analysis. Based on the mini-Xception framework, this article implements the real-time identification and analysis of student sentiment in classroom teaching, and the degree of student engagement is analyzed according to the teaching events triggered by teacher to provide reasonable suggestions for subsequent teaching progress. The experimental results show that the mini-Xception model trained by FER2013 data sets has high recognition accuracy for the real-time detection of seven student sentiments, and the average accuracy is 76.71%. Compared with text feedback, it can assist teachers in understanding student learning states in time so that they can take corresponding actions, and realize the real-time performance of wisdom classroom teaching information feedback, the high efficiency of information transmission, and the intelligence of information processing.

show abstract

SFANet: A Spectrum-Aware Feature Augmentation Network for Visible-Infrared Person Reidentification

Cited by 40 publications

References 48 publications

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

Visible-Infrared Person Re-Identification: A Comprehensive Survey and a New Setting

Real‐time sentiment analysis of students based on mini‐Xception architecture for wisdom classroom

Contact Info

Product

Resources

About