Yujia Zhang

Ms. Yujia Zhang


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
14 December 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MKMichael Kampffmeyer
Michael Kampffmeyer
NDNanqing Dong
Nanqing Dong
XLXiaodan Liang
Xiaodan Liang
YZYujia Zhang
Yujia Zhang
EXEric P. Xing
Eric P. Xing
Salient segmentation aims to segment out attentiongrabbing regions, a critical yet challenging task and the foundation of many high-level computer vision applications. It requires semantic-aware grouping of pixels into salient regions and benefits from the utilization of global multi-scale contexts to achieve good local reasoning. Previous works often address it as two-class segmentation problems utilizing complicated multi-step procedures including refinement networks and complex graphical models. We argue that semantic salient segmentation can instead be effectively resolved by reformulating it as a simple yet intuitive pixel-pair based connectivity prediction task. Following the intuition that salient objects can be naturally grouped via semanticaware connectivity between neighboring pixels, we propose a pure Connectivity Net (ConnNet). ConnNet predicts connectivity probabilities of each pixel with its neighboring pixels by leveraging multi-level cascade contexts embedded in the image and long-range pixel relations. We investigate our approach on two tasks, namely salient object segmentation and salient instancelevel segmentation, and illustrate that consistent improvements can be obtained by modeling these tasks as connectivity instead of binary segmentation tasks for a variety of network architectures. We achieve state-of-the-art performance, outperforming or being comparable to existing approaches while reducing inference time due to our less complex approach.

1 February 2020 in Pattern Recognition Letters
Verified
Journal Article
Closed access
YZYujia Zhang
Yujia Zhang
XLXiaodan Liang
Xiaodan Liang
DZDingwen Zhang
Dingwen Zhang
MTMin Tan
Min Tan
EXEric P. Xing
Eric P. Xing

1 November 2021 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
JWJinting Wu
Jinting Wu
YZYujia Zhang
Yujia Zhang
SSShiying Sun
Shiying Sun
QLQianzhong Li
Qianzhong Li
XZXiaoguang Zhao
Xiaoguang Zhao

21 February 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YZYujia Zhang
Yujia Zhang
MKMichael Kampffmeyer
Michael Kampffmeyer
XZXiaoguang Zhao
Xiaoguang Zhao
MTMin Tan
Min Tan
Query-conditioned video summarization requires to (1) find a diverse set of video shots/frames that are representative for the whole video, and that (2) the selected shots/frames are related to a given query. Thus it can be tailored to different user interests leading to a better personalized summary and differs from the generic video summarization which only focuses on video content. Our work targets this query-conditioned video summarization task, by first proposing a Mapping Network (MapNet) in order to express how related a shot is to a given query. MapNet helps establish the relation between the two different modalities (videos and query), which allows mapping of visual information to query space. After that, a deep reinforcement learning-based summarization network (SummNet) is developed to provide personalized summaries by integrating relatedness, representativeness and diversity rewards. These rewards jointly guide the agent to select the most representative and diversity video shots that are most related to the user query. Experimental results on a query-conditioned video summarization benchmark demonstrate the effectiveness of our proposed method, indicating the usefulness of the proposed mapping mechanism as well as the reinforcement learning approach.

22 December 2021 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
YZYujia Zhang
Yujia Zhang
JWJunxian Wu
Junxian Wu
QLQianzhong Li
Qianzhong Li
XZXiaoguang Zhao
Xiaoguang Zhao
MTMin Tan
Min Tan
Pavement defect segmentation is a fundamental task in the field of transport infrastructure inspection. Existing methods mainly focus on detection/segmentation for long and thin cracks. However, there are many other types of defects with various sizes and shapes that are also essential to segment, which brings more challenges toward detailed road inspection. To address the above problems and provide a more comprehensive understanding of the overall road conditions, we propose a three-stream neural network that combines spatial, contextual and boundary information for fine-grained defect segmentation. Specifically, the spatial stream captures rich low-level spatial features. The contextual stream utilizes an attention mechanism and models high-level contextual relationships over local features. To further refine the segmentation results, the boundary stream encodes detailed boundaries using a global gated convolution and generates additional boundary maps. By combining the above different information, our model can effectively produce pixel-wise predictions for fine-grained road inspection. The network is trained using a dual-task loss in an end-to-end manner, and experiments were performed on three newly collected datasets, i.e., a fine-grained defect dataset and two crack datasets, which shows that the proposed method achieves favorable segmentation results on complex multi-class defects, and is also able to segment single-class cracks. Specifically, on the fine-grained dataset, it achieved state-of-the-art performance over other competing baselines (mPA of 0.54, mIoU of 0.38, Mic_F of 0.78 and Mac_F of 0.65), where each image is resized to 512 $\times 512$ and the processing speed is 21 FPS on average.

12 October 2019 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
YZYujia Zhang
Yujia Zhang
MKMichael Kampffmeyer
Michael Kampffmeyer
XLXiaodan Liang
Xiaodan Liang
DZDingwen Zhang
Dingwen Zhang
MTMin Tan
Min Tan
EXEric P. Xing
Eric P. Xing