Clothing attribute recognition via a holistic relation network
Clothing attribute recognition via a holistic relation network
复制标题
通过整体关系网络进行服装属性识别
DOI：
10.1002/int.22840
复制
发表时间：
2022-02
影响因子：
7
通讯作者：
Hao Li
中科院分区：
文献类型：
--
作者：
Di Wu;Zijie Li;Juxiang Zhou;Jianhou Gan;Wei Gao;Hao Li
Clothing attribute prediction is a fundamental image classification task in the field of computer vision. Motivated by the human recognition system, we investigate the task relationship and spatial importance where people usually utilize these useful clues to assist in recognizing clothing attributes. In this paper, we propose a novel Holistic Relation Network (HRNet) for clothing attribute recognition, considering the fusion of multiple relations, including spatial and spatial relation via a spatial relation module, spatial and task relation via a task attention module, and task and task relation via a graph context reasoning module. Specifically, we first use the backbone network to extract features from the input image, two types of attention models followed will further learn the features, then the graph context reasoning module will be used to further enhance the features, and finally, a classifier exploited to classify the clothing attributes with the learned representation information. Without using manual image feature filtering methods, this paper aims to achieve clothing attribute recognition by deeply exploring the relationships among different clothing attribute recognition tasks. In this paper, we use double‐branches of the attention model to model the relevance of spatial context information and learn more discriminative feature representations from multitask features for clothing attribute prediction. Derived from the prior knowledge learned from the two above‐mentioned attention models, we further propose a graph‐relation model constructing relationships among different clothing attribute tasks by integrating the spatial association relationships among multitask. The proposed HRNet only uses image‐level annotation but it owns a good ability for obtaining distinguishing feature representations. We obtain state‐of‐the‐art performance, which is demonstrated by extensive experiments on three mainstream benchmarks, for example, woman clothing data set, man clothing data set, and shop‐domain clothing data set.
登录
查看更多内容
影响因子：
7.4
作者：
Muhan Zhang;Yixin Chen
通讯作者：
Muhan Zhang;Yixin Chen
DOI：
10.1109/wacv.2017.64
发表时间：
2016-10
期刊：
2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
影响因子：
--
作者：
Qi Dong;S. Gong;Xiatian Zhu
通讯作者：
Qi Dong;S. Gong;Xiatian Zhu
DOI：
10.1109/tcsvt.2014.2352552
发表时间：
2015-05
影响因子：
8.4
作者：
Annan Li;Luoqi Liu;Kang Wang;Si Liu;Shuicheng Yan
通讯作者：
Annan Li;Luoqi Liu;Kang Wang;Si Liu;Shuicheng Yan
DOI：
10.1609/aaai.v32i1.11782
发表时间：
2018-04
期刊：
--
影响因子：
--
作者：
Muhan Zhang;Zhicheng Cui;Marion Neumann;Yixin Chen
通讯作者：
Muhan Zhang;Zhicheng Cui;Marion Neumann;Yixin Chen
DOI：
10.1109/iccvw.2019.00399
发表时间：
2019-10
期刊：
2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)
影响因子：
--
作者：
A. Sidnev;Alexey Trushkov;Maxim Kazakov;Ivan Korolev;Vladislav Sorokin
通讯作者：
A. Sidnev;Alexey Trushkov;Maxim Kazakov;Ivan Korolev;Vladislav Sorokin