A comprehensive survey on video saliency detection with auditory information: the audio-visual consistency perceptual is the key!

C Chen, M Song, W Song, L Guo… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Video saliency detection (VSD) aims at fast locating the most attractive
objects/things/patterns in a given video clip. Existing VSD-related works have mainly relied …

Learning disentangled representation implicitly via transformer for occluded person re-identification

M Jia, X Cheng, S Lu, J Zhang - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Person re-IDentification (re-ID) under various occlusions has been a long-standing
challenge as person images with different types of occlusions often suffer from misalignment …

Visible-infrared person re-identification via cross-modality interaction transformer

Y Feng, J Yu, F Chen, Y Ji, F Wu, S Liu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Visible-infrared person re-identification (VI Re-ID) is designed to match person images of the
same identity from visible and infrared cameras. Transformer structures have been …

Camera invariant feature learning for unsupervised person re-identification

Z Pang, L Zhao, Q Liu, C Wang - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Fully unsupervised person re-identification (ReID) methods aim to learn discriminative
features without using labeled ReID data. Because these methods are easily affected by …

Text-based person search without parallel image-text data

Y Bai, J Wang, M Cao, Y Wu, X Hu, Y Sun, Y Zhou, W Zhu, F Rao… - ar** cameras. The key to accomplishing this challenging task is …

Progressive context-aware graph feature learning for target re-identification

M Cao, C Ding, C Chen, H Dou, X Hu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
This paper aims at robust and discriminative feature learning for target re-identification (Re-
ID). In addition to paying attention to the individual appearance information as in most Re-ID …