no code implementations • 6 Oct 2023 • Weibin Liao, Xuhong LI, Qingzhong Wang, Yanwu Xu, Zhaozheng Yin, Haoyi Xiong
While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes, masks, and cell types for every cell in every image, to fine-tune the pre-trained model.
no code implementations • 15 Aug 2023 • Haodong Chen, Ming C. Leu, Md Moniruzzaman, Zhaozheng Yin, Solmaz Hajmohammadi
Repetitive counting (RepCount) is critical in various applications, such as fitness tracking and rehabilitation.
1 code implementation • 14 Jul 2023 • Chenyu Zhang, Zhaozheng Yin, Ruwen Qin
Efficiently monitoring the condition of civil infrastructure requires automating the structural condition assessment in visual inspection.
1 code implementation • 6 Jul 2023 • Hritam Basak, Zhaozheng Yin
In this work, we investigate relatively less explored semi-supervised domain adaptation (SSDA) for medical image segmentation, where access to a few labeled target samples can improve the adaptation performance substantially.
2 code implementations • CVPR 2023 • Hritam Basak, Zhaozheng Yin
Although recent works in semi-supervised learning (SemiSL) have accomplished significant success in natural image segmentation, the task of learning discriminative representations from limited annotations has been an open problem in medical images.
1 code implementation • 16 Sep 2022 • Muhammad Monjurul Karim, Ruwen Qin, Zhaozheng Yin
To this end, this paper proposes an attention-guided multistream feature fusion network (AM-Net) to localize dangerous traffic agents from dashcam videos.
no code implementations • 5 Sep 2022 • Chenyu Zhang, Muhammad Monjurul Karim, Zhaozheng Yin, Ruwen Qin
Aerial robots such as drones have been leveraged to perform bridge inspections.
no code implementations • 10 Sep 2021 • Muhammad Monjurul Karim, Ruwen Qin, Zhaozheng Yin, Genda Chen
This paper is motivated to develop an assistive intelligence model for segmenting multiclass bridge elements from inspection videos captured by an aerial inspection platform.
1 code implementation • 18 Jun 2021 • Muhammad Monjurul Karim, Yu Li, Ruwen Qin, Zhaozheng Yin
Visual cues for predicting a future accident are embedded deeply in dashcam video data.
Ranked #1 on Accident Anticipation on CCD
2 code implementations • 18 Jun 2021 • Muhammad Monjurul Karim, Yu Li, Ruwen Qin, Zhaozheng Yin
The paper further evaluates the performance of the Multi-Net and the efficiency of the developed system.
no code implementations • 10 Dec 2020 • Liang Han, Zhaozheng Yin, Zhurong Xia, Li Guo, Mingqian Tang, Rong Jin
Then, we design a vision-based price suggestion module which takes the extracted visual features along with some statistical item features from the shopping platform as the inputs to determine whether an uploaded item image is qualified for price suggestion by a binary classification model, and provide price suggestions for items with qualified images by a regression model.
no code implementations • 10 Dec 2020 • Liang Han, Zhaozheng Yin, Zhurong Xia, Mingqian Tang, Rong Jin
The goal of price prediction is to help sellers set effective and reasonable prices for their second-hand items with the images and text descriptions uploaded to the online platforms.
no code implementations • CVPR 2021 • Tianyi Zhao, Kai Cao, Jiawen Yao, Isabella Nogues, Le Lu, Lingyun Huang, Jing Xiao, Zhaozheng Yin, Ling Zhang
We exploit the feasibility to distinguish pancreatic ductal adenocarcinoma (PDAC) from the nine other nonPDAC masses using multi-phase CT imaging.
no code implementations • 20 Aug 2019 • Wenjin Tao, Ming C. Leu, Zhaozheng Yin
In a human-centered intelligent manufacturing system, sensing and understanding of the worker's activity are the primary tasks.
no code implementations • CVPR 2015 • Hang Su, Zhaozheng Yin, Takeo Kanade, Seungil Huh
When data have a complex manifold structure or the characteristics of data evolve over time, it is unrealistic to expect a graph-based semi-supervised learning method to achieve flawless classification given a small number of initial annotations.