Reading recognition of pointer meter based on pattern recognition and dynamic three-points on a line

By Yongqiang Zhang, Ming Ding, Wu Fu, Yongqiang Li. 2017

13 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Industrial and Manufacturing Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ming Ding
2. Yancheng Bai
3. Yongqiang Zhang
4. Bernard Ghanem
5. Yongqiang Li
6. Shibiao Xu
7. Luc Van Gool
8. Ming-Hsuan Yang

In Industrial and Manufacturing Engineering

1. Yancheng Bai
2. Bernard Ghanem
3. Ming Ding
4. Yongqiang Zhang

Citations in the corpus

• Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection (2021, neutral): “In the task of image-based object detection, object detectors are trained on large-scale datasets and then deployed on real-world applications [9, 11, 8, 24, 5, 15, 23, 17, 16, 1, 2, 39, 33, 34, 38, 36, 37, 35, 32].”
• KGSNet: Key-Point-Guided Super-Resolution Network for Pedestrian Detection in the Wild (2020, background): “In this paradigm, designing effective hand-crafted features (e.g., Haar [5] and HOG [6], [7]), training a stronger classifier (e.g., SVM [6] and boosting classifiers [8]) and combining features from multiple channels (e.g., [9] and [10]) are of critical importance for achieving state-of-the-art…”
• Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild (2020, methodology): “Driven by the great success of RCNN, some works (Jiang and Learned-Miller 2017; Wan et al. 2016; Zhu et al. 2017a; Tang et al. 2018; Chi et al. 2018; Zhang et al. 2017a, 2019b) employ this framework to detect faces, and impressive performance have been achieved on the simple benchmarks [e.g. FDDB…”
• W2F: A Weakly-Supervised to Fully-Supervised Framework for Object Detection (2018, methodology): “As for training a weakly-supervised object detector, most existing methods [13, 31, 23, 16, 29, 35] treat it as a Multiple Instance Learning (MIL) problem, and the result is only discriminative object parts are highlighted instead of the whole object, which is detrimental when a tight pseudo ground ”