TY - JOUR
T1 - Comprehensive Attribute Prediction Learning for Person Search by Language
AU - Niu, Kai
AU - Huang, Linjiang
AU - Long, Yuzhou
AU - Huang, Yan
AU - Wang, Liang
AU - Zhang, Yanning
N1 - Publisher Copyright:
© 1992-2012 IEEE.
PY - 2024
Y1 - 2024
N2 - Person search by language refers to searching for the interested pedestrian images given natural language sentences, which requires capturing fine-grained differences to accurately distinguish different pedestrians, while still far from being well addressed by most of the current solutions. In this paper, we propose the Comprehensive Attribute Prediction Learning (CAPL) method, which explicitly carries out attribute prediction learning, for improving the modeling capabilities of fine-grained semantic attributes and obtaining more discriminative visual and textual representations. First, we construct the semantic ATTribute Vocabulary (ATT-Vocab) based on sentence analysis. Second, the complementary context-wise and attribute-wise attribute predictions are simultaneously conducted to better model the high-frequency in-vocab attributes in our In-vocab Attribute Prediction (IAP) module. Third, to additionally consider the out-of-vocab semantics, we present the Attribute Completeness Learning (ACL) module for better capturing the low-frequency attributes outside the ATT-Vocab, obtaining more comprehensive representations. Combining the IAP and ACL modules together, our CAPL method has obtained the currently state-of-the-art retrieval performance on two widely-used benchmarks, i.e., CUHK-PEDES and ICFG-PEDES datasets. Extensive experiments and analyses have been carried out to validate the effectiveness and generalization capacities of our CAPL method.
AB - Person search by language refers to searching for the interested pedestrian images given natural language sentences, which requires capturing fine-grained differences to accurately distinguish different pedestrians, while still far from being well addressed by most of the current solutions. In this paper, we propose the Comprehensive Attribute Prediction Learning (CAPL) method, which explicitly carries out attribute prediction learning, for improving the modeling capabilities of fine-grained semantic attributes and obtaining more discriminative visual and textual representations. First, we construct the semantic ATTribute Vocabulary (ATT-Vocab) based on sentence analysis. Second, the complementary context-wise and attribute-wise attribute predictions are simultaneously conducted to better model the high-frequency in-vocab attributes in our In-vocab Attribute Prediction (IAP) module. Third, to additionally consider the out-of-vocab semantics, we present the Attribute Completeness Learning (ACL) module for better capturing the low-frequency attributes outside the ATT-Vocab, obtaining more comprehensive representations. Combining the IAP and ACL modules together, our CAPL method has obtained the currently state-of-the-art retrieval performance on two widely-used benchmarks, i.e., CUHK-PEDES and ICFG-PEDES datasets. Extensive experiments and analyses have been carried out to validate the effectiveness and generalization capacities of our CAPL method.
KW - Person search by language
KW - attribute prediction
KW - cross-modal retrieval
KW - smart video surveillance
UR - http://www.scopus.com/inward/record.url?scp=85187986342&partnerID=8YFLogxK
U2 - 10.1109/TIP.2024.3372832
DO - 10.1109/TIP.2024.3372832
M3 - 文章
C2 - 38457315
AN - SCOPUS:85187986342
SN - 1057-7149
VL - 33
SP - 1990
EP - 2003
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
ER -