no code implementations • 7 Oct 2020 • Fangbo Qin, Jie Qin, Siyu Huang, De Xu
For the novel CPI extraction task, we built the Object Contour Primitives dataset using online public images, and the Robotic Object Contour Measurement dataset using a camera mounted on a robot.
1 code implementation • 17 Feb 2020 • Yingjie Yin, De Xu, Xingang Wang, Lei Zhang
We propose a directional deep embedding and appearance learning (DDEAL) method, which is free of the online fine-tuning process, for fast VOS.
no code implementations • 19 Apr 2019 • Siyang Sun, Yingjie Yin, Xingang Wang, De Xu, Yuan Zhao, Haifeng Shen
To address this problem, we propose a multiple receptive field and small-object-focusing weakly-supervised segmentation network (MRFSWSnet) to achieve fast object detection.
no code implementations • 13 Sep 2018 • Yingjie Yin, Lei Zhang, De Xu, Xingang Wang
The tracking-by-detection framework usually consist of two stages: drawing samples around the target object in the first stage and classifying each sample as the target object or background in the second stage.