Automatic Feature Learning for Robust Shadow Detection

By Salman Hameed Khan, Mohammed Bennamoun, Ferdous Sohel, Roberto B. Togneri. 2014

153 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, Ocean 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. Wenqi Ren
2. Xiaochun Cao
3. Jin-shan Pan
4. Ming-Hsuan Yang
5. P. Heng
6. Vishal M. Patel
7. Radu Timofte
8. Song Wang

In Environmental Engineering

1. P. Heng
2. Ming-Hsuan Yang

In Ocean Engineering

1. Wenqi Ren
2. P. Heng
3. Ming-Hsuan Yang
4. Xiaochun Cao
5. Hua Zhang
6. Jin-shan Pan

Citations in the corpus

• A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection (2020, background): “Khan et al. [19] formulated the first network to classify image pixels as shadows/non-shadows by building a 7-layer CNN, which extracts deep features from superpixels, and then feeding Figure 3: The schematic illustration of the proposed MT-CNN in Fig.”
• Single Image Dehazing via Multi-scale Convolutional Neural Networks (2016, methodology): “We minimize the loss using the stochastic gradient descent method with the backpropagation learning rule [12,32,33].”