Dongmei Mo

About Me

Hi! I'm currently a postdoctoral fellow collaborated with Prof. Calvin Wong at the Hong Kong Polytechnic University and Laboratory for Artificial Intelligence in Design (AiDLab), HKSAR.

Contact me by dongmei.mo@connect.polyu.hk

My research interests are in computer vision, deep learning, optimization and machine learning with the goal of intelligent applications, especially intelligent fashion aesthetics cognition and personalized recommendation. My previous research covers image detection, classification and retrieval. Download CV.

News

[Jan. 2023] The manuscript about personalized fashion compatibility learning accepted by Expert Systems with Applications.

[Apr. 2022] The manuscript about fashion compatibility evaluation and recommendation accepted by Expert Systems with Applications.

[Jan. 2020] The manuscript about image retrieval with deep hashing learning submitted to the journal of IEEE Transactions on Multimedia.

[Oct. 2019] A manuscript about image detection under Major Revision on the journal of IEEE Transactions on Automation Science and Engineering.

[Mar. 2019] A manuscript about image feature extraction submitted to the journal of IEEE Transactions on Cybernetics.

Honors and Awards

[Jun. 2018] Outstanding Postgraduate.

[Oct. 2017] National Scholarship.

Project Experience

Mar. 2022-Present, Postdoctoral Researcher, RP3-1 AI-based Fashion Design Assistant, the InnoHK Research Clusters.

Oct. 2022-Present, Postdoctoral Researcher, RP3-2 Intelligent Fashion Aesthetic Evaluation System, the InnoHK Research Clusters.

Professional Services and Experience

Reviewer of TNNLS, TMM, TCSVT, Pattern Recognition , Expert Systems with Applications, Neurocomputing.

26 Oct. 2022, Oral Presentation, "Consumer experience enhancement: developing intelligent fashion evaluation and recommendation service", INFORMS 2021 Annual Meeting.

Teaching Assistant

Autumn 2020 ITC4068M-Merchandising Management, The Hong Kong Polytechnic University

2019 ITC4085E-Omni-Channel Fashion Marketing and Retailing, The Hong Kong Polytechnic University

Spring 2019 ITC2019M-Management Principles in the Fashion Business, The Hong Kong Polytechnic University

Research

My previous research covers image detection, classification and retrieval using traditional methods and deep learning algorithms. Specifically, they are related to feature selection or extraction, low-rank decomposition, convex problem optimization, deep learning framework design, etc..

1. Private Stylists: Personalized Fashion Compatibility Learning

The work adopts physical and fashion attributes for effective personalized fashion compatibility evaluation and recommendation. The physical attributes are concluded into seven aspects: body shape, skin color, hairstyle, hair color, height, breast size (breasts), and color contrast. The model can not only predict the fashion attributes of the outfit’s top, bottom, shoes, and bag items, but also predict the incompatible physical attributes of an individual towards the given outfit. It can be used to recommend outfits that best fit an individual and the predicted fashion attributes can be used for result explanation.

The personalized compatibility evaluation framework. The framework composes of three parts: The image feature extractor, the first transformer encoder which is for fashion attribute prediction, and the second transformer encoder which is for physical attribute prediction.

2. Neural Stylist via Online Styling Service

Compatibility analysis from human aesthetics vs. automatic evaluation, diagnosis and recommendation. To proposes a visual and semantic representation model for explainable evaluation and recommendation.

The architecture of the proposed framework. The framework comprises four components: 1. multi-layer feature analysis; 2. colour- correlation enhancement; 3. visual-semantic similarity preserving, and 4: outfit diagnosis and recommendation.

3. Image Classification & Retrieval

The visualization of testing data on the Fashion-MNIST dataset. The image classification problem is basic when doing image interpretation research.

I study the problem of image retrieval and classification with Deep Hashing learning. Existing hashing methods are mainly focused on general images but few of them consider the application of fashion image retrieval and textile defect classification.

4. Image Detection

The results of locating multiple categories of defects for given fabric images. I design optimization models for the specific problems and find the optimal solution for the designed objective functions. The experiments are evaluated with the proposed iterative algorithms.

Use grid search to find optimal values for three parameters.

Low-rank decomposition problem solved by algorithm based on Alternating Direction Method of Multipliers (ADMM).

5. Feature Extraction & Dimensionality Reduction

I studied feature extraction and dimensionality reduction during my postgraduate period and published several papers on IEEE Transactions Q1 journals.

Presentation of reconstruction images and images of the first 2 projections from subspace.

Verify the performance on keeping the local structure of the data. These are the results that the images mapped onto the two-dimensional plane described by two coordinates of the proposed method.

6. Manifold Learning

I develop algorithms to maintain the local geometric structure of the image samples (i.e. manifold structure of the images).

The result of image samples from two classes projected onto the subspace.

The algorithms can guarantee that the data projected on the learned subspace is of great discrimination. Thus, any samples projected onto the subspace can obtain maximal discrimination and thus the intrinsic local geometric structure of the data can be preserved.

Publications

Submitted Manuscripts

Super Stylist: Personalized Fashion Recommendation via Deep Personality Learning, ICMR 2023 (submitted).

Scatter Matrix Decomposition for Jointly Sparse Learning, Pattern Recognition (Major revision).

Selected Publications

[1] Dongmei Mo, Xingxing Zou, and WaiKeung Wong. "Towards private stylists via personalized compatibility learning", Expert Systems with Applications (2023): 119632.

[2] Dongmei Mo, Xingxing Zou, and WaiKeung Wong. "Neural stylist: Towards online styling service", Expert Systems with Applications (2022): 117333.

[3] Dongmei Mo, Xianjing Liu, Yao Ge and Waikeung Wong. "Concentrated Hashing with Neighborhood Embedding for Image Retrieval and Classification", International Journal of Machine Learning and Cybernetics 13.6 (2022): 1571-1587.

[4] Dongmei Mo, WaiKeung Wong, Zhihui Lai. "Weighted Double Low-rank Decomposition with Application to Fabric Defect Detection", IEEE Transactions on Automation Science and Engineering 18.3 (2020): 1170-1190.

[5] Dongmei Mo, WaiKeung Wong, “Efficient Fabric Defect Classification based on Deep Hashing Learning”, ]. AATCC Journal of Research, 2021, 8(1_suppl): 191-201.

[6] Dongmei Mo, Zhihui Lai, Waikeung Wong, Xizhao Wang. "Jointly Sparse Locality Regression for Feature Extraction", IEEE Transactions on Multimedia, 2019, 22(11): 2873-2888.

[7] Dongmei Mo, and Zhihui Lai. "Robust Jointly Sparse Regression with Generalized Orthogonal Learning for Image Feature Selection", Pattern Recognition 93 (2019): 164-178.

[8] Dongmei Mo, Zhihui Lai, and WaiKeung Wong. "Locally Joint Sparse Marginal Embedding for Feature Extraction", IEEE Transactions on Multimedia, 2019, 21(12): 3038-3052.

[9] Zhihui Lai, Dongmei Mo, et al.. "Robust Discriminant Regression for Feature Extraction", IEEE transactions on Cybernetics 48, no. 8 (2017): 2472-2484. (Q1, Top Journal)

[10] Zhihui Lai, Dongmei Mo, et al. "Generalized Robust Regression for Jointly Sparse Subspace Learning", IEEE Transactions on Circuits and Systems for Video Technology 29, no. 3 (2018): 756-772.

2019

[1] Jointly Sparse Locality Regression for Feature Extraction.
Dongmei Mo, Zhihui Lai, Waikeung Wong, Xizhao Wang. IEEE Transactions on Multimedia (Accepted 2019).

[2] Robust Jointly Sparse Regression with Generalized Orthogonal Learning for Image Feature Selection.
Dongmei Mo, and Zhihui Lai. Pattern Recognition 93 (2019): 164-178.

[3] Locally Joint Sparse Marginal Embedding for Feature Extraction.
Dongmei Mo, Zhihui Lai, and WaiKeung Wong. IEEE Transactions on Multimedia (Accepted 2019).

2018

[4] Generalized Robust Regression for Jointly Sparse Subspace Learning.
Zhihui Lai, Dongmei Mo, et al. IEEE Transactions on Circuits and Systems for Video Technology 29, no. 3 (2018): 756-772.

[5] Robust Jointly Sparse Embedding for Dimensionality Reduction.
Zhihui Lai, Yudong Chen, Dongmei Mo, Jiajun Wen, and Heng Kong. Neurocomputing 314 (2018): 30-38.

[6] Jointly Sparse Reconstructed Regression Learning.
Dongmei Mo, Zhihui Lai, and Heng Kong. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 597-609. Springer, Cham, 2018.

[7] Robust jointly sparse regression and its applications.
Dongmei Mo, Zhihui Lai, and Yuyang Meng. Journal of Ambient Intelligence and Humanized Computing 9, no. 6 (2018): 1797-1807.

[8] Robust Feature Extraction for Material Image Retrieval in Fashion Accessory Management.
Meng, Yuyang, Dongmei Mo, Xiaotang Guo, Yan Cui, Jiajun Wen, and Wai Keung Wong. In International Conference on Artificial Intelligence on Textile and Apparel, pp. 299-305. Springer, Cham, 2018.

[9] Sparse Discriminant Principle Component Analysis.
Zhihui Lai, Mangqi Chen, Dongmei Mo, Xingxing Zou, and Heng Kong. In International Conference on Artificial Intelligence on Textile and Apparel, pp. 111-119. Springer, Cham, 2018.

[10] Fashion Meets AI Technology.
Xingxing Zou, Wai Keung Wong, and Dongmei Mo. In International Conference on Artificial Intelligence on Textile and Apparel, pp. 111-119. Springer, Cham, 2018.

2017

[11] Robust Discriminant Regression for Feature Extraction.
Zhihui Lai, Dongmei Mo, et al. IEEE transactions on Cybernetics 48, no. 8 (2017): 2472-2484.

[12] Robust jointly sparse regression for image feature selection.
Dongmei Mo, and Zhihui Lai. In 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR), pp. 477-482. IEEE, 2017.

Contact

Address: The Hong Kong Polytechnic University Hung Hom, Kowloon, Hong Kong.

Email: dongmei.mo@connect.polyu.hk