Attention mechanisms in computer vision: A survey

MH Guo, TX Xu, JJ Liu, ZN Liu, PT Jiang, TJ Mu… - Computational visual …, 2022 - Springer
Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

Person re-identification: A retrospective on domain specific open challenges and future trends

A Zahra, N Perwaiz, M Shahzad, MM Fraz - Pattern Recognition, 2023 - Elsevier
Abstract Person Re-Identification (Re-ID) is a critical aspect of visual surveillance systems,
which aims to automatically recognize and locate individuals across a multi-camera network …

Counterfactual attention learning for fine-grained visual categorization and re-identification

Y Rao, G Chen, J Lu, J Zhou - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Attention mechanism has demonstrated great potential in fine-grained visual recognition
tasks. In this paper, we present a counterfactual attention learning method to learn more …

Nformer: Robust person re-identification with neighbor transformer

H Wang, J Shen, Y Liu, Y Gao… - Proceedings of the …, 2022 - openaccess.thecvf.com
Person re-identification aims to retrieve persons in highly varying settings across different
cameras and scenarios, in which robust and discriminative representation learning is …

Dynamic dual-attentive aggregation learning for visible-infrared person re-identification

M Ye, J Shen, D J. Crandall, L Shao, J Luo - Computer Vision–ECCV 2020 …, 2020 - Springer
Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian
retrieval problem. Due to the large intra-class variations and cross-modality discrepancy with …

Adaptive subspaces for few-shot learning

C Simon, P Koniusz, R Nock… - Proceedings of the …, 2020 - openaccess.thecvf.com
Object recognition requires a generalization capability to avoid overfitting, especially when
the samples are extremely few. Generalization from limited samples, usually studied under …

Relation-aware global attention for person re-identification

Z Zhang, C Lan, W Zeng, X Jin… - Proceedings of the ieee …, 2020 - openaccess.thecvf.com
For person re-identification (re-id), attention mechanisms have become attractive as they
aim at strengthening discriminative features and suppressing irrelevant ones, which …

Semantic-aware knowledge distillation for few-shot class-incremental learning

A Cheraghian, S Rahman, P Fang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts
gradually, where only a few examples per concept are available to the learner. Due to the …

Cross-modality person re-identification with shared-specific feature transfer

Y Lu, Y Wu, B Liu, T Zhang, B Li… - Proceedings of the …, 2020 - openaccess.thecvf.com
Cross-modality person re-identification (cm-ReID) is a challenging but key technology for
intelligent video analysis. Existing works mainly focus on learning modality-shared …

Visible-infrared person re-identification via semantic alignment and affinity inference

X Fang, Y Yang, Y Fu - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Visible-infrared person re-identification (VI-ReID) focuses on matching the pedestrian
images of the same identity captured by different modality cameras. The part-based methods …