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 …
This paper focuses on domain generalization (DG), the task of learning from multiple source domains a model that generalizes well to unseen domains. A main challenge for DG is that …
K Zhu, W Zhai, Y Cao, J Luo… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation …
Y Pang, J Lin, T Qin, Z Chen - IEEE Transactions on Multimedia, 2021 - ieeexplore.ieee.org
Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations. I2I has drawn increasing attention and …
As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate …
Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge …
Y Chen, L Wan, Z Li, Q Jing… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
RGB-Infrared person re-identification (RGB-IR ReID) is a challenging cross-modality retrieval problem, which aims at matching the person-of-interest over visible and infrared …
Abstract Unsupervised Domain Adaptive (UDA) person re-identification (ReID) aims at adapting the model trained on a labeled source-domain dataset to a target-domain dataset …
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in …