Jianghong Ma

Dr. Jianghong Ma


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 July 2022 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
LDLi Dong
Li Dong
HZHaijun Zhang
Haijun Zhang
KYKai Yang
Kai Yang
DZDongliang Zhou
Dongliang Zhou
JSJianyang Shi
Jianyang Shi
JMJianghong Ma
Jianghong Ma
Crowd counting has important applications in the environments of smart cities, such as intelligent surveillance. In this paper, we propose a novel convolutional neural network (CNN) framework for crowd counting with mixed ground-truth, called top- $k$ relation-based network (TKRNet). Specifically, the estimated density maps generated in a coarse-to-fine manner are treated as coarse locations for crowds so as to assist our TKRNet to regress the scattered point-annotated ground truth. Moreover, an adaptive top- $k$ relation module (ATRM) is proposed to enhance feature representations by leveraging the top- $k$ dependencies between the pixels with an adaptive filtering mechanism. Specifically, we first compute the similarity between two pixels so as to select the top- $k$ relations for each position. Then, a weight normalization operation with an adaptive filtering mechanism is proposed to make the ATRM adaptively eliminate the influence from the low correlation positions in the top- $k$ relations. Finally, a weight attention mechanism is introduced to make the ATRM pay more attention to the positions with high weights in the top- $k$ relations. Extensive experimental results demonstrate the effectiveness of our proposed TKRNet on several public datasets in comparison to state-of-the-art methods.

10 March 2023 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
HYHan Yan
Han Yan
HZHaijun Zhang
Haijun Zhang
JSJianyang Shi
Jianyang Shi
JMJianghong Ma
Jianghong Ma
XXXiaofei Xu
Xiaofei Xu
Traditional fashion design is heavily dependent on the talent and inspiration of designers. However, for inexperienced designers or common consumers, it is difficult to complete the design of ready-to-wear clothes. In this paper, we introduce a novel fashion attributes disentanglement generative adversarial network (FadGAN) to assist users in automatically accomplishing the design process. Different from the typical style transfer methods, which are limited to perform coarse-level style transfer, our FadGAN works on learning the accurate mapping which can preserve the identity of one fashion item, as well as learning the texture of another fashion item. Specifically, given two different fashion items, a fashion item disentanglement encoder first disentangles the features of the two inputs into structure codes and texture codes, respectively. Subsequently, a texture swap module is proposed to learn mixed texture codes to eliminate the differences of features from different fashion items. The mixed texture codes and the structure codes are then fed into a generator for new fashion item generation. Experimental results demonstrate that our model achieves superior results in comparison to several state-of-the-art methods with a 0.006-0.446 improvement on the mask-LPIPS, a 3.976-6.724 improvement on CDH, a 9.266-13.127 improvement on CIEDE, and a 0.145-0.325 improvement on HISTO.

22 October 2022 in Neural Networks
Verified
Journal Article
Closed access
TWTianjun WEI
Tianjun WEI
TCTommy W.S. Chow
Tommy W.S. Chow
JMJianghong Ma
Jianghong Ma
MZMingbo Zhao
Mingbo Zhao

23 June 2022 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
DZDongliang Zhou
Dongliang Zhou
HZHaijun Zhang
Haijun Zhang
QLQun Li
Qun Li
JMJianghong Ma
Jianghong Ma
XXXiaofei Xu
Xiaofei Xu
How to recommend outfits has gained considerable attention in both academia and industry in recent years. Many studies have been carried out regarding fashion compatibility learning, to determine whether the fashion items in an outfit are compatible or not. These methods mainly focus on evaluating the compatibility of existing outfits and rarely consider applying such knowledge to ‘design’ new fashion items. We propose the new task of generating complementary and compatible fashion items based on an arbitrary number of given fashion items. In particular, given some fashion items that can make up an outfit, the aim of this paper is to synthesize photo-realistic images of other, complementary, fashion items that are compatible with the given ones. To achieve this, we propose an outfit generation framework, referred to as COutfitGAN, which includes a pyramid style extractor, an outfit generator, a UNet-based real/fake discriminator, and a collocation discriminator. To train and evaluate this framework, we collected a large-scale fashion outfit dataset with over 200K outfits and 800K fashion items from the Internet. Extensive experiments show that COutfitGAN outperforms other baselines in terms of similarity, authenticity, and compatibility measurements.

21 August 2019 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
JMJianghong Ma
Jianghong Ma
HZHaijun Zhang
Haijun Zhang
TCTommy W. S. Chow
Tommy W. S. Chow
Multilabel classification deals with instances assigned with multiple labels simultaneously. It focuses on learning a mapping from feature space to label a space for out-of-sample extrapolation. The mapping can be seen as a feature selection process in the feature domain or as a classifier training process in the classifier domain. The existing methods do not effectively learn the mapping when combining these two domains together. In this article, we derive a mechanism to extract label-specific features in local and global levels. We also derive a mechanism to train label-specific classifiers in individual and joint levels. Extracting features globally and training classifiers jointly can be seen as a dual process of learning the mapping function on two domains in a coarse-tuned way, while extracting features locally and training classifiers individually can be seen as a dual process of learning the mapping function on two domains in a fine-tuned way. The two-level feature selection and the two-level classifier training are derived to make the entire mapping learning process robust. Finally, extensive experimental results on several benchmarks under four domains are presented to demonstrate the effectiveness of the proposed approach.

25 February 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
HYHan Yan
Han Yan
HZHaijun Zhang
Haijun Zhang
JSJianyang Shi
Jianyang Shi
JMJianghong Ma
Jianghong Ma
XXXiaofei Xu
Xiaofei Xu
Texture and shape in fashion, constituting essential elements of garments, characterize the body and surface of the fabric and outline the silhouette of clothing, respectively. The selection of texture and shape plays a critical role in the design process, as they largely determine the success of a new design for fashion items. In this research, we propose a texture and shape disentangled generative adversarial network (TSD-GAN) to perform “intelligent” design with the transformation of texture and shape in fashion items. Our TSD-GAN aims to learn how to disentangle the features of texture and shape of different fashion items in an unsupervised manner. Specifically, a fashion attribute encoder is developed to decompose the input fashion items into independent representations of texture and shape. Then, to learn the coarse or fine styles hidden in the features of texture and shape, a texture mapping network and a shape mapping network are proposed to disentangle the features into different hierarchical representations. The different hierarchical representations of texture and shape are then fed into a multi-factor-based generator to generate mixed-style fashion items. In addition, a multi-discriminator framework is developed to distinguish the authenticity and texture similarity between the generated images and the real images. Experimental results on different fashion categories demonstrate that our proposed TSD-GAN may be useful for assisting designers to accomplish the design process by transforming the texture and shape of fashion items.