Context-Aware Crowd Counting

@article{Liu2019ContextAwareCC,
  title={Context-Aware Crowd Counting},
  author={Weizhe Liu and Mathieu Salzmann and Pascal Fua},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={5094-5103}
}
  • Weizhe Liu, M. Salzmann, P. Fua
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. [...] Key Method In other words, our approach adaptively encodes the scale of the contextual information required to accurately predict crowd density. This yields an algorithm that outperforms state-of-the-art crowd counting methods, especially when perspective effects are strong.Expand
Leveraging Self-Supervision for Cross-Domain Crowd Counting
TLDR
This work forces a network to learn perspective-aware features by training it to recognize upside-down real images from regular ones and incorporate into it the ability to predict its own uncertainty so that it can generate useful pseudo labels for fine-tuning purposes. Expand
Adaptive Context Learning Network for Crowd Counting
TLDR
This paper proposes a novel architecture called adaptive context learning network (ACLNet) to incorporate context of features in multiple levels to enhance the representative ability of multi-level features in crowd counting. Expand
Completely Self-Supervised Crowd Counting via Distribution Matching
TLDR
This work proposes the proposed paradigm of complete self-supervision, which does not need even a single labeled image to be trained, and establishes the superiority of the method in less data setting as well. Expand
Cascade-guided multi-scale attention network for crowd counting
TLDR
A cascade-guided crowd counting network, which is mainly embedded with scale aware model (SAM) and attentionaware model (AAM), which has higher accuracy, but also has stronger robustness to scale variation and background noise. Expand
Multi-Stream Networks and Ground-Truth Generation for Crowd Counting
TLDR
A Multi-Stream Convolutional Neural Network is developed and evaluated in this work, which receives an image as input and produces a density map that represents the spatial distribution of people in an end-to-end fashion. Expand
Towards Using Count-level Weak Supervision for Crowd Counting
TLDR
This paper studies the problem of weakly-supervised crowd counting, and devise a simple-yet-effective training strategy, namely Multiple Auxiliary Tasks Training (MATT), to construct regularizes for restricting the freedom of the generated density maps. Expand
Scale-Aware Crowd Counting via Depth-Embedded Convolutional Neural Networks
TLDR
A depth embedding module is proposed as add-ons into existing networks that exploits essential depth cues to spatially re-calibrate the magnitude of the original features and directly benefits the estimation of scale-aware density values. 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
Adaptive Depth Network for Crowd Counting And Beyond
  • Liangzi Rong, Chunping Li
  • Computer Science
  • 2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  • 2020
TLDR
A multi-output structure network named Adaptive Depth Network (ADNet) that can adaptively adjust the network’s depth according to the inputs’ features and selects the output from the output block that produces the best confidence value as the final result is proposed. Expand
Multi-Scale Context Aggregation Network with Attention-Guided for Crowd Counting
TLDR
A multi-scale context aggregation network (MSCANet) based on single column encoder-decoder architecture for crowd counting, which consists of an encoder based on dense context-aware module (DCAM) and a hierarchical attention-guided decoder, which achieves better performance than other similar state-of-the-art methods. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 44 REFERENCES
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
Multi-source Multi-scale Counting in Extremely Dense Crowd Images
TLDR
This work relies on multiple sources such as low confidence head detections, repetition of texture elements, and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region, and employs a global consistency constraint on counts using Markov Random Field. Expand
Towards Perspective-Free Object Counting with Deep Learning
TLDR
A novel convolutional neural network solution, named Counting CNN (CCNN), formulated as a regression model where the network learns how to map the appearance of the image patches to their corresponding object density maps, able to estimate object densities in different very crowded scenarios. 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
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
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting
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
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
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
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
TLDR
This work proposes a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework and demonstrates how to efficiently learn from these unlabeling datasets by incorporating learning- to-rank in a multi-task network which simultaneously ranks images and estimates crowd density maps. Expand
Spatiotemporal Modeling for Crowd Counting in Videos
TLDR
This work proposes a variant of a recent deep learning model called convolutional LSTM (ConvLSTM) for crowd counting which fully captures both spatial and temporal dependencies and extends the ConvLSTm model to a bidirectional ConvL STM model which can access long-range information in both directions. Expand
...
1
2
3
4
5
...