TY - GEN
T1 - Variation generalized feature learning via intra-view variation adaptation
AU - Li, Jiawei
AU - Ye, Mang
AU - Ma, Andy J.
AU - YUEN, Pong Chi
N1 - Funding Information:
This work is supported by Hong Kong RGC General Research Fund HKBU (12200518).
PY - 2019/8
Y1 - 2019/8
N2 - This paper addresses the variation generalized feature learning problem in unsupervised video-based person re-identification (re-ID). With advanced tracking and detection algorithms, large-scale intra-view positive samples can be easily collected by assuming that the image frames within the tracking sequence belong to the same person. Existing methods either directly use the intra-view positives to model cross-view variations or simply minimize the intra-view variations to capture the invariant component with some discriminative information loss. In this paper, we propose a Variation Generalized Feature Learning (VGFL) method to learn adaptable feature representation with intra-view positives. The proposed method can learn a discriminative re-ID model without any manually annotated cross-view positive sample pairs. It could address the unseen testing variations with a novel variation generalized feature learning algorithm. In addition, an Adaptability-Discriminability (AD) fusion method is introduced to learn adaptable video-level features. Extensive experiments on different datasets demonstrate the effectiveness of the proposed method.
AB - This paper addresses the variation generalized feature learning problem in unsupervised video-based person re-identification (re-ID). With advanced tracking and detection algorithms, large-scale intra-view positive samples can be easily collected by assuming that the image frames within the tracking sequence belong to the same person. Existing methods either directly use the intra-view positives to model cross-view variations or simply minimize the intra-view variations to capture the invariant component with some discriminative information loss. In this paper, we propose a Variation Generalized Feature Learning (VGFL) method to learn adaptable feature representation with intra-view positives. The proposed method can learn a discriminative re-ID model without any manually annotated cross-view positive sample pairs. It could address the unseen testing variations with a novel variation generalized feature learning algorithm. In addition, an Adaptability-Discriminability (AD) fusion method is introduced to learn adaptable video-level features. Extensive experiments on different datasets demonstrate the effectiveness of the proposed method.
UR - https://www.ijcai.org/proceedings/2019/
UR - http://www.scopus.com/inward/record.url?scp=85074944755&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2019/116
DO - 10.24963/ijcai.2019/116
M3 - Conference contribution
AN - SCOPUS:85074944755
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 826
EP - 832
BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
A2 - Kraus, Sarit
PB - International Joint Conferences on Artificial Intelligence
T2 - 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
Y2 - 10 August 2019 through 16 August 2019
ER -