Yujiang Wang

Dr. Yujiang Wang


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
11 March 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YLYiming Lin
Yiming Lin
JSJie Shen
Jie Shen
YWYujiang Wang
Yujiang Wang
MPMaja Pantic
Maja Pantic
Image-based age estimation aims to predict a person’s age from facial images. It is used in a variety of real-world applications. Although end-to-end deep models have achieved impressive results for age estimation on benchmark datasets, their performance in-the-wild still leaves much room for improvement due to the challenges caused by large variations in head pose, facial expressions, and occlusions. To address this issue, we propose a simple yet effective method to explicitly incorporate facial semantics into age estimation, so that the model would learn to correctly focus on the most informative facial components from unaligned facial images regardless of head pose and non-rigid deformation. To this end, we design a face parsing-based network to learn semantic information at different scales and a novel face parsing attention module to leverage these semantic features for age estimation. To evaluate our method on in-the-wild data, we also introduce a new challenging large-scale benchmark called IMDB-Clean. This dataset is created by semi-automatically cleaning the noisy IMDB-WIKI dataset using a constrained clustering method. Through comprehensive experiment on IMDB-Clean and other benchmark datasets, under both intra-dataset and cross-dataset evaluation protocols, we show that our method consistently outperforms all existing age estimation methods and achieves a new state-of-the-art performance. To the best of our knowledge, our work presents the first attempt of leveraging face parsing attention to achieve semantic-aware age estimation, which may be inspiring to other high level facial analysis tasks.

1 January 2017
Verified
Conference Paper
Closed access
SPStavros Petridis
Stavros Petridis
YWYujiang Wang
Yujiang Wang
ZLZuwei Li
Zuwei Li
MPMaja Pantic
Maja Pantic

1 March 2020 in Pattern Recognition Letters
Verified
Journal Article
Closed access
SPStavros Petridis
Stavros Petridis
YWYujiang Wang
Yujiang Wang
PMPingchuan Ma
Pingchuan Ma
ZLZuwei Li
Zuwei Li
MPMaja Pantic
Maja Pantic

1 December 2019 in Pattern Recognition Letters
Verified
Journal Article
Open access
YWYujiang Wang
Yujiang Wang
JSJie Shen
Jie Shen
SPStavros Petridis
Stavros Petridis
MPMaja Pantic
Maja Pantic

25 August 2017
Verified
Conference Paper
Closed access
SPStavros Petridis
Stavros Petridis
YWYujiang Wang
Yujiang Wang
ZLZuwei Li
Zuwei Li
MPMaja Pantic
Maja Pantic

16 November 2018 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
YWYujiang Wang
Yujiang Wang
BLBingnan Luo
Bingnan Luo
JSJie Shen
Jie Shen
MPMaja Pantic
Maja Pantic
Inspired by the recent development of deep network-based methods in semantic image segmentation, we introduce an end-to-end trainable model for face mask extraction in video sequence. Comparing to landmark-based sparse face shape representation, our method can produce the segmentation masks of individual facial components, which can better reflect their detailed shape variations. By integrating convolutional LSTM (ConvLSTM) algorithm with fully convolutional networks (FCN), our new ConvLSTM-FCN model works on a per-sequence basis and takes advantage of the temporal correlation in video clips. In addition, we also propose a novel loss function, called segmentation loss, to directly optimise the intersection over union (IoU) performances. In practice, to further increase segmentation accuracy, one primary model and two additional models were trained to focus on the face, eyes, and mouth regions, respectively. Our experiment shows the proposed method has achieved a 16.99% relative improvement (from 54.50 to 63.76% mean IoU) over the baseline FCN model on the 300 Videos in the Wild (300VW) dataset.