Single-Image Crowd Counting via Multi-Column Convolutional Neural Network

By Desen Zhou, Siqin Chen, Shenghua Gao, Yi Ma. 2016

2,110 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

DeepSetNet: Predicting Sets with Deep Neural Networks (2016, background): “It is important to bear in mind that unlike many existing approaches that learn to count [1, 5, 12, 20, 24, 35, 50, 51], our main goal is not object counting.”
Domain Adaptation for Traffic Density Estimation (2021, methodology): “A more efficient structure is proposed by (Zhang et al., 2016) introducing a Multi-Column CNN-based architecture (MCNN) for crowd counting.”
Image Inpainting via Generative Multi-column Convolutional Neural Networks (2018, methodology): “The multi-column structure [3, 27, 1] is used since it can decompose images into components with different receptive ﬁelds and feature resolutions.”
ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding (2018, methodology): “Dataset MAE MSE MAE MSE MAE MSE MAE MSE ShanghaiTech Part A [37] 68.”
Guided Attention Network for Object Detection and Counting on Drones (2019, background): “Object counting methods aim to predict the total number of objects in different categories existing in images, such as pedestrian counting [20, 26, 46, 50], vehicle counting [12, 49], goods counting [11, 21] and general object counting [2, 3, 18].”
Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs (2017, methodology): “Previous works on multi-scale [23] or multi-column [50] architectures have demonstrated abilities to handle the presence of considerably large variations in object sizes by achieving signiﬁcant improvements in such scenarios.”
Learning Multi-Level Density Maps for Crowd Counting (2020, methodology): “Zhang et al. [14] proposed one MCNN architecture which comprises three column CNNs having ﬁl-ters with receptive ﬁelds of different sizes.”
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation (2017, methodology): “Traditional crowd counting by density estimation methods regress density maps by minimizing the pixel-wise Euclidean loss to the ground-truth [36, 2, 42, 22].”
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank (2018, methodology): “Given the large success of pre-trained features in neural networks, it is somewhat surprising to note that the vast majority of deep learning methods for crowd counting train from scratch [37, 1, 31].”
Attention Scaling for Crowd Counting (2020, methodology): “Even so, there is still much room for improvement in counting performance, especially in several challenging crowd datasets [49, 10, 11].”
Loss Functions for Multiset Prediction (2017, background): “[12, 28, 15], model the counting problem as density estimation over image space, and assume that each object is annotated with a dot specifying its location.”
Incorporating Side Information by Adaptive Convolution (2017, methodology): “Hence, in contrast to Zhang et al. (2015, 2016), Onoro-Rubio and López-Sastre (2016), Sam et al. (2017) and Sindagi and Patel (2017), we propose to use the existing side information (e.g. perspective weight) as an input to adapt the convolutional layers to different scenes.”
Bayesian Loss for Crowd Count Estimation With Point Supervision (2019, methodology): “Recently, crowd counting methods using Convolutional Neural Networks (CNNs) have made remarkable progresses [53, 46, 36, 6, 57, 59, 38, 9, 4, 32, 16].”
Object Counting and Instance Segmentation With Image-Level Supervision (2019, background): “The problem of density map estimation to preserve the spatial distribution of people is well studied in crowd counting [3,16,18,22,32].”
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (2019, methodology): “Most crowd counting methods are based on detection [17, 9, 44], regression [27, 4, 10], and density estimation [16, 52, 2, 11 Density estimation based methods, in particular, have received increasing research focus.”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, methodology): “10, the proposed network consists of multiple independent regressors similar to multi-column network [111] with di ﬀ erent receptive ﬁelds and a switch clas-siﬁer.”
Towards Perspective-Free Object Counting with Deep Learning (2016, methodology): “To the best of our knowledge, only two methods have previously explored similar ideas [7, 21].”
Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework (2021, methodology): “While the PartB is collected from a busy street and represents relatively sparse scenes.”