https://scholars.lib.ntu.edu.tw/handle/123456789/559410
標題: | Learning to reduce dual-level discrepancy for infrared-visible person re-identification | 作者: | Wang, Z. Wang, Z. Zheng, Y. Satoh, S. YUNG-YU CHUANG |
關鍵字: | Infrared-Visible person RE-IDentification (IV-REID) is a rising task. Compared to conventional person re-identification (re-ID), IV-REID concerns the additional modality discrepancy originated from the different imaging processes of spectrum cameras, in addition to the person's appearance discrepancy caused by viewpoint changes, pose variations and deformations presented in the conventional re-ID task. The co-existed discrepancies make IV-REID more difficult to solve. Previous methods attempt to reduce the appearance and modality discrepancies simultaneously using feature-level constraints. It is however difficult to eliminate the mixed discrepancies using only feature-level constraints. To address the problem, this paper introduces a novel Dual-level Discrepancy Reduction Learning (D 2RL) scheme which handles the two discrepancies separately. For reducing the modality discrepancy, an image-level sub-network is trained to translate an infrared image into its visible counterpart and a visible image to its infrared version. With the image-level sub-network, we can unify the representations for images with different modalities. With the help of the unified multi-spectral images, a feature-level sub-network is trained to reduce the remaining appearance discrepancy through feature embedding. By cascading the two sub-networks and training them jointly, the dual-level reductions take their responsibilities cooperatively and attentively. Extensive experiments demonstrate the proposed approach outperforms the state-of-the-art methods. © 2019 IEEE. | 公開日期: | 2019 | 卷: | 2019-June | 起(迄)頁: | 618-626 | 來源出版物: | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | 摘要: | Infrared-Visible person RE-IDentification (IV-REID) is a rising task. Compared to conventional person re-identification (re-ID), IV-REID concerns the additional modality discrepancy originated from the different imaging processes of spectrum cameras, in addition to the person's appearance discrepancy caused by viewpoint changes, pose variations and deformations presented in the conventional re-ID task. The co-existed discrepancies make IV-REID more difficult to solve. Previous methods attempt to reduce the appearance and modality discrepancies simultaneously using feature-level constraints. It is however difficult to eliminate the mixed discrepancies using only feature-level constraints. To address the problem, this paper introduces a novel Dual-level Discrepancy Reduction Learning (D 2RL) scheme which handles the two discrepancies separately. For reducing the modality discrepancy, an image-level sub-network is trained to translate an infrared image into its visible counterpart and a visible image to its infrared version. With the image-level sub-network, we can unify the representations for images with different modalities. With the help of the unified multi-spectral images, a feature-level sub-network is trained to reduce the remaining appearance discrepancy through feature embedding. By cascading the two sub-networks and training them jointly, the dual-level reductions take their responsibilities cooperatively and attentively. Extensive experiments demonstrate the proposed approach outperforms the state-of-the-art methods. © 2019 IEEE. |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85074292584&partnerID=40&md5=8b0adf1d52d7840a5fd6116bde251744 https://scholars.lib.ntu.edu.tw/handle/123456789/559410 |
ISSN: | 10636919 | DOI: | 10.1109/CVPR.2019.00071 | SDG/關鍵字: | Infrared imaging; Spectroscopy; Body pose; Categorization; Face; Gesture; Retrieval; Computer vision |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。