Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs
Citations
579 citations
Cites background from "Generating High-Quality Crowd Densi..."
...Sindagi and Patel [26] presented a CNNbased approach that incorporates global and local contextual information in an image to generate density maps....
[...]
573 citations
Cites background or methods from "Generating High-Quality Crowd Densi..."
...[32,6] explored methods to incorporate the contextual information by learning various density levels and generate high-resolution density maps....
[...]
...Method MCNN [3] Switch-CNN [5] CP-CNN [6] CSRNet [33] SANet...
[...]
...(2) [5,32,6] require density level classifier to provide contextual information....
[...]
...Some works [3,4,5,6] have achieved significant improvement by addressing the scale variation issue with multi-scale architecture....
[...]
...We follow experiment setting of [6] to generate density maps with perspective maps....
[...]
535 citations
Cites background from "Generating High-Quality Crowd Densi..."
...leveraged in various applications such as semantic segmentation [45], face-alignment [22], visual tracking [18] crowdcounting [30], single image super-resolution[43], face antiSpoofing [1], action recognition [48], depth estimation [5], single image dehazing [24, 42, 40] and also in single image de-raining [36]....
[...]
369 citations
348 citations
Cites background from "Generating High-Quality Crowd Densi..."
...In most cases [37, 3, 20, 28], to deal with human scale changes, multiple convolution paths (sub-networks) with varying sized kernels are fused to yield the final density map prediction....
[...]
...[34] MCNN [37] Switch-CNN [25] CP-CNN [28] ACSCP (ours)...
[...]
...Both our method and CP-CNN are contemporary works starting to consider the quality of density map....
[...]
...However, it seems unfair that the training process of CPCNN demands extra priori density-class labels (i.e., global and local density classes) which are NOT directly provided by datasets....
[...]
...First, although different sizes of convolutional kernels are utilized to extract multi-scale features [37, 28], (i....
[...]
References
49,914 citations
40,609 citations
38,211 citations
"Generating High-Quality Crowd Densi..." refers methods in this paper
...Furthermore, we train the CNNs in a Generative Adversarial Network (GAN) based framework [10] to exploit the recent success of adversarial loss to achieve highquality and sharper density maps....
[...]
...In a further attempt to improve the quality of density maps, the F-CNN is trained using a weighted combination of pixelwise Euclidean loss and adversarial loss [10]....
[...]
11,958 citations
"Generating High-Quality Crowd Densi..." refers background or methods in this paper
...The use of adversarial loss helps us combat the widely acknowledge issue of blurred results obtained by minimizing only the Euclidean loss [13]....
[...]
...Motivated by these observations and the recent success of GANs for overcoming the issues of L2-minimization [13], we attempt to further improve the quality of density maps by minimizing a weighted combination of pixel-wise Euclidean loss and adversarial loss....
[...]
...It has been widely acknowledged that minimization of L2 error results in blurred results especially for image reconstruction tasks [13, 14, 45, 46, 47]....
[...]
10,189 citations
"Generating High-Quality Crowd Densi..." refers background in this paper
...Several recent works for semantic segmentation [21], scene parsing [51] and visual saliency [52] have demonstrated that incorporating contextual information can provide significant improvements in the results....
[...]