Multi-memory matching for unsupervised visible-infrared person re-identification
Unsupervised visible-infrared person re-identification (USL-VI-ReID) is a promising yet
highly challenging retrieval task. The key challenges in USL-VI-ReID are to accurately …
highly challenging retrieval task. The key challenges in USL-VI-ReID are to accurately …
Robust pseudo-label learning with neighbor relation for unsupervised visible-infrared person re-identification
Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable
challenge, which aims to match pedestrian images across visible and infrared modalities …
challenge, which aims to match pedestrian images across visible and infrared modalities …
Distilling consistent relations for multi-source domain adaptive person re-identification
Although unsupervised person re-identification has made great progress by employing
domain adaptation, existing methods rarely make use of multiple source datasets. These …
domain adaptation, existing methods rarely make use of multiple source datasets. These …
Unsupervised person re‐identification based on adaptive information supplementation and foreground enhancement
Unsupervised person re‐identification has attracted vital interest because of its ability to
protect privacy, significantly lower the expense of manual annotation, and eliminate the …
protect privacy, significantly lower the expense of manual annotation, and eliminate the …
Unsupervised Learning of Intrinsic Semantics With Diffusion Model for Person Re-Identification
Unsupervised person re-identification (Re-ID) aims to learn semantic representations for
person retrieval without using identity labels. Most existing methods generate fine-grained …
person retrieval without using identity labels. Most existing methods generate fine-grained …
Learning commonality, divergence and variety for unsupervised visible-infrared person re-identification
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified
persons in infrared images to visible images without annotations, and vice versa. USVI-ReID …
persons in infrared images to visible images without annotations, and vice versa. USVI-ReID …
Progressive Contrastive Learning with Multi-Prototype for Unsupervised Visible-Infrared Person Re-identification
Unsupervised visible-infrared person re-identification (USVI-ReID) aims to match specified
people in infrared images to visible images without annotation, and vice versa. USVI-ReID is …
people in infrared images to visible images without annotation, and vice versa. USVI-ReID is …
Dual-resolution fusion modeling for unsupervised cross-resolution person re-identification
Z Pang, L Zhao, C Wang - Proceedings of the 32nd ACM international …, 2024 - dl.acm.org
Cross-resolution person re-identification (CR-ReID) aims to match images of the same
person with different resolutions in different scenarios. Existing CR-ReID methods achieve …
person with different resolutions in different scenarios. Existing CR-ReID methods achieve …
Overcoming the Pitfalls of Vision-Language Model for Image-Text Retrieval
This work tackles the persistent challenge of image-text retrieval, a key problem at the
intersection of computer vision and natural language processing. Despite significant …
intersection of computer vision and natural language processing. Despite significant …
Disentangled Sample Guidance Learning for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) is challenging due to the lack of ground truth
labels. Most existing methods employ iterative clustering to generate pseudo labels for …
labels. Most existing methods employ iterative clustering to generate pseudo labels for …