Human Tracking Using Convolutional Neural Networks

By Jialue Fan, Wei Xu, Ying Wu, Yihong Gong. 2010

353 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Pedestrian Detection with Unsupervised Multi-stage Feature Learning (2012, background): “Contrary to [12], the output of the first stage is branched after the non-linear transformations and pooling/subsampling operations rather than before.”
Recent advances in convolutional neural networks (2015, background): “In [143], the authors design a CNN tracker with a shift-variant architecture.”
Convolutional neural networks applied to house numbers digit classification (2012, neutral): “MS features have consistently improved performance in other work [4, 12, 10] and in Figure 3.”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, background): “Despite such huge success of CNNs, only a limited number of tracking algorithms using the representations from CNNs have been proposed so far [9, 20, 29, 44].”
A survey of randomized algorithms for training neural networks (2016, background): “This kind of randomization based connection is well studied in [43, 25].”
DeepTrack: Learning Discriminative Feature Representations by Convolutional Neural Networks for Visual Tracking (2014, methodology): “Using offline trained CNN for tracking has been proposed in the past [8], [17].”
Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks (2016, background): “While we are not the first to leverage the expressive power of neural networks in the context of tracking, prior art in this domain primarily concerned only the detection part of the tracking pipeline (Fan et al. 2010), (Jänen et al.”
Learning to Track at 100 FPS with Deep Regression Networks (2016, background): “A separate class of trackers are the model-based trackers which are designed to track a specific class of objects [12,1,11].”
Mixed Pooling for Convolutional Neural Networks (2014, neutral): “In [4], Fan et al.”
3D Convolutional Neural Networks for Human Action Recognition (2010, neutral): “…competitive performance in visual object recognition [17], [19], [22]–[24], human action recognition [25]–[27], natural language processing [28], audio classification [29], brain-computer interaction [30], human tracking [31], image restoration [32], denoising [33], and segmentation tasks [34].”
Robust Visual Tracking via Convolutional Networks Without Training (2015, background): “[20] present a human tracking algorithm that learns a specific feature extractor with CNNs from an offline training set (about 20000 image pairs).”
Traffic sign recognition with multi-scale Convolutional Networks (2011, methodology): “Contrary to [12], we use the output of the first stage after pooling/subsampling rather than before.”
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015, background): “(Fan et al., 2010) presents a human tracking algorithm based on a network trained ofﬂine, but it needs to learn a separate class-speciﬁc network to track other kind of objects.”
A review on deep convolutional neural networks (2017, methodology): “Initially it had been widely used for object recognition tasks but now it is being examined in other domains as well like object tracking [3], pose estimation”
Learning by Tracking: Siamese CNN for Robust Target Association (2016, methodology): “In the context of tracking, CNNs have been used to model appearance and scale variations of the target [18].”
CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark (2018, background): “Some works [11, 1] aim at human tracking in the crowd.”
Convolutional Features for Correlation Filter Based Visual Tracking (2015, background): “[14] by learning convolutional features from offline training data.”
Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification (2014, methodology): “In recent years, CNN has also been applied to object detection [15], [6], [18], [17], [13], image segmentation [20], scene labeling [5], [14], and tracking [4], and signiﬁcantly improved the accuracies in these applications.”