Deep learning for visible-infrared cross-modality person re-identification: A comprehensive review
Visible-infrared cross-modality person re-identification (VI-ReID) is currently a prevalent but
challenging research topic in computer vision, since it can remedy the poor performance of …
challenging research topic in computer vision, since it can remedy the poor performance of …
PIAFusion: A progressive infrared and visible image fusion network based on illumination aware
Infrared and visible image fusion aims to synthesize a single fused image containing salient
targets and abundant texture details even under extreme illumination conditions. However …
targets and abundant texture details even under extreme illumination conditions. However …
Image fusion in the loop of high-level vision tasks: A semantic-aware real-time infrared and visible image fusion network
Infrared and visible image fusion aims to synthesize a single fused image that not only
contains salient targets and abundant texture details but also facilitates high-level vision …
contains salient targets and abundant texture details but also facilitates high-level vision …
Fmcnet: Feature-level modality compensation for visible-infrared person re-identification
Abstract For Visible-Infrared person Re-IDentification (VI-ReID), existing modality-specific
information compensation based models try to generate the images of missing modality from …
information compensation based models try to generate the images of missing modality from …
Diverse part discovery: Occluded person re-identification with part-aware transformer
Occluded person re-identification (Re-ID) is a challenging task as persons are frequently
occluded by various obstacles or other persons, especially in the crowd scenario. To …
occluded by various obstacles or other persons, especially in the crowd scenario. To …
Diverse embedding expansion network and low-light cross-modality benchmark for visible-infrared person re-identification
For the visible-infrared person re-identification (VIReID) task, one of the major challenges is
the modality gaps between visible (VIS) and infrared (IR) images. However, the training …
the modality gaps between visible (VIS) and infrared (IR) images. However, the training …
Channel augmented joint learning for visible-infrared recognition
This paper introduces a powerful channel augmented joint learning strategy for the visible-
infrared recognition problem. For data augmentation, most existing methods directly adopt …
infrared recognition problem. For data augmentation, most existing methods directly adopt …
Specificity-preserving RGB-D saliency detection
RGB-D saliency detection has attracted increasing attention, due to its effectiveness and the
fact that depth cues can now be conveniently captured. Existing works often focus on …
fact that depth cues can now be conveniently captured. Existing works often focus on …
Learning memory-augmented unidirectional metrics for cross-modality person re-identification
This paper tackles the cross-modality person re-identification (re-ID) problem by
suppressing the modality discrepancy. In cross-modality re-ID, the query and gallery images …
suppressing the modality discrepancy. In cross-modality re-ID, the query and gallery images …