ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding

@article{Liu2019ADCrowdNetAA,
  title={ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding},
  author={N. Liu and Yongchao Long and C. Zou and Qun Niu and Li Pan and Hefeng Wu},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={3220-3229}
}
  • N. Liu, Yongchao Long, +3 authors Hefeng Wu
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes. ADCrowdNet contains two concatenated networks. An attention-aware network called Attention Map Generator (AMG) first detects crowd regions in images and computes the congestion degree of these regions. Based on detected crowd regions and congestion priors, a multi-scale deformable network called Density… Expand
ACCNet: Attention-based Contextual Convolutional Network for Crowd Counting
In recent years, crowd counting has been widely used in computer vision. But on many issues like large scale variations, perspective distortions and complex backgrounds, it remains a challengingExpand
Spatial-related and Scale-aware Network for Crowd Counting
  • Lei Li, Yuan Dong, Hongliang Bai
  • Computer Science
  • 2020 25th International Conference on Pattern Recognition (ICPR)
  • 2021
TLDR
A learnable spatial attention module is proposed which can get the spatial relations to diminish the negative impact of backgrounds and a dense hybrid dilated convolution module is also brought up to preserve information derived from varied scales. Expand
Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation
In this paper, we propose a novel SpatioTemporal convolutional Dense Network (STDNet) to address the videobased crowd counting problem, which contains the decomposition of 3D convolution and the 3DExpand
Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting
TLDR
This paper proposes two modified neural networks based on dual path multi-scale fusion networks (SFANet) and SegNet for accurate and efficient crowd counting and shows that these modifications yield algorithms that could improve state-of-the-art crowd counting methods. Expand
HA-CCN: Hierarchical Attention-Based Crowd Counting Network
TLDR
This paper presents the Hierarchical Attention-based Crowd Counting Network (HA-CCN), a single-step training framework that employs attention mechanisms at various levels to selectively enhance the features of the network. Expand
Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs
TLDR
The Adaptive Capacity Multi-scale convolutional neural networks (ACM-CNN), a novel crowd counting approach which can assign different capacities to different portions of the input, is proposed. Expand
Crowd Counting Via Cross-Stage Refinement Networks
TLDR
A Cross-stage Refinement Network (CRNet) that can refine predicted density maps progressively based on hierarchical multi-level density priors, and achieves superior performances against state-of-the-art methods on four widely-used challenging benchmarks in terms of counting accuracy and density map quality. Expand
Recurrent Distillation based Crowd Counting
TLDR
This work proposes a simple yet effective crowd counting framework that is able to achieve the state-of-the-art performance on various crowded scenes and introduces a perspective-aware density map generation method to train crowd counting model to accomplish superior performance than priordensity map generation techniques. Expand
Perspective-aware Distillation-based Crowd Counting
TLDR
This work introduces a perspective-aware density map generation method that is able to produce ground-truth density maps from point annotations and proposes an iterative distillation algorithm to progressively enhance the model with identical network structures. Expand
Attention Scaling for Crowd Counting
TLDR
This work presents a novel Adaptive Pyramid Loss (APLoss) to hierarchically calculate the estimation losses of sub-regions, which alleviates the training bias and demonstrates the superiority of the proposed approach to alleviate the counting performance differences in different regions. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 45 REFERENCES
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimationExpand
Crowd Counting using Deep Recurrent Spatial-Aware Network
TLDR
A unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two issues in a learnable spatial transform module with a region-wise refinement process, and achieves an improvement on the largest dataset WorldExpo'10 and 22.8% on the most challenging dataset UCF_CC_50. Expand
CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
TLDR
This work uses a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd image, and shows that this combination is used for effectively capturing both the high-level semantic information and the low-level features, necessary for crowd counting under large scale variations. Expand
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
TLDR
With the proposed simple MCNN model, the method outperforms all existing methods and experiments show that the model, once trained on one dataset, can be readily transferred to a new dataset. Expand
Cross-scene crowd counting via deep convolutional neural networks
TLDR
A deep convolutional neural network is proposed for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count, to obtain better local optimum for both objectives. Expand
Fully Convolutional Crowd Counting on Highly Congested Scenes
TLDR
The state-of-the-art for crowd counting in high density scenes is advanced by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016), and a training set augmentation scheme that minimises redundancy among training samples to improve model generalisation and overall counting performance is developed. Expand
Switching Convolutional Neural Network for Crowd Counting
TLDR
A novel crowd counting model that maps a given crowd scene to its density and switch convolutional neural network that leverages variation of crowd density within an image to improve the accuracy and localization of the predicted crowd count is proposed. Expand
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting
  • Vishwanath A. Sindagi, V. Patel
  • Computer Science
  • 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
  • 2017
TLDR
A novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and density map estimation achieves lower count error and better quality density maps as compared to the recent state-of-the-art methods. Expand
End-to-end crowd counting via joint learning local and global count
  • C. Shang, H. Ai, Bo Bai
  • Computer Science
  • 2016 IEEE International Conference on Image Processing (ICIP)
  • 2016
TLDR
An end-to-end convolutional neural network architecture that takes a whole image as its input and directly outputs the counting result, taking advantages of contextual information when predicting both local and global count is proposed. Expand
Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid
TLDR
This paper utilizes an image pyramid to deal with scale variations, and adaptively fuse the predictions from different scales (using adaptively changing per-pixel weights), which makes the method adapt to scale changes within an image. Expand
...
1
2
3
4
5
...