Corpus ID: 201645333

MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation

  title={MTCNET: Multi-task Learning Paradigm for Crowd Count Estimation},
  author={Abhay Kumar and Nishant Jain and Suraj Tripathi and Chirag Singh and K. Chaitanya Krishna},
We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale variations and the arbitrary perspective of an individual image. The proposed model has two related tasks, with Crowd Density Estimation as the main task and Crowd-Count Group Classification as the auxiliary task. The auxiliary task helps in capturing the… Expand
CNN-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal
This survey is to provide a comprehensive summary of recent advanced crowd counting techniques based on Convolutional Neural Network via density map estimation, and educate new researchers in this field the design principles and trade-offs. Expand
DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation
This paper proposes a novel deep learning method for counting on-ear corn kernels in-field to aid in the gathering of real-time data and, ultimately, to improve decision making to maximize yield. Expand


Crowd Counting with Fully Convolutional Neural Network
A deep learning framework for crowd counting from a single static image with different number of people and arbitrary perspective is presented, and the model achieves the lowest mean absolute error and comparable mean square error and outperforms the current state-of-the-art methods. Expand
Multi-scale convolutional neural networks for crowd counting
A novel multi-scale convolutional neural network (MSCNN) for single image crowd counting is proposed, able to generate scale-relevant features for higher crowd counting performances in a single-column architecture, which is both accuracy and cost effective for practical applications. Expand
Cross-scene crowd counting via deep convolutional neural networks
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
Switching Convolutional Neural Network for Crowd Counting
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
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
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
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
Deep People Counting in Extremely Dense Crowds
This paper proposes an end-to-end deep convolutional neural networks (CNN) regression model for counting people of images in extremely dense crowds that achieves superior performance than the state-of-the-arts in term of the mean and variance of absolute difference. Expand
COUNT Forest: CO-Voting Uncertain Number of Targets Using Random Forest for Crowd Density Estimation
This paper presents a patch-based approach for crowd density estimation in public scenes that achieved state-of-the-art results on the public Mall dataset and UCSD dataset, and also proposed two potential applications in traffic counts and scene understanding with promising results. Expand
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank
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
Multi-Scale Context Aggregation by Dilated Convolutions
This work develops a new convolutional network module that is specifically designed for dense prediction, and shows that the presented context module increases the accuracy of state-of-the-art semantic segmentation systems. Expand