Learning People Detectors for Tracking in Crowded Scenes

By Siyu Tang, Mykhaylo Andriluka, Anton Milan, Konrad Schindler, Stefan Roth, Bernt Schiele. 2013

96 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

Learning Non-maximum Suppression (2017, methodology): “We use the same training and test set as well as the same detections from [28], a model built specifically to handle occlusions.”
Detection and Tracking of Occluded People (2014, methodology): “In this paper we follow this standard practice, but refer to our recent work (Tang et al. 2013) where we further address this issue by reformulating our joint detector using structural SVM framework andmodifying the loss function to penalize detection of single people with double-person components a”
DeepID-Net: Object Detection with Deformable Part Based Convolutional Neural Networks (2017, unknown): “object-scene interaction [60], [61], and the presence, location, orientation and size relationship among objects [33], [58], [59], [60], [62], [63], [64], [65], [66], [67], [68], [69], [70], [71], [72].”
Subgraph decomposition for multi-target tracking (2015, unknown): “[18] 82.”
DeepID-Net: Deformable deep convolutional neural networks for object detection (2014, background): “The context information investigated in literature includes regions surrounding objects [5, 8, 13], object-scene interaction [9, 20], and the presence, location, orientation and size relationship among objects [2, 48, 49, 7, 31, 13, 40, 9, 53, 8, 50, 30, 6, 35, 45].”
Lucid Data Dreaming for Object Tracking (2017, background): “Compositing real images provides more realistic results, and has shown promise for object detection [14, 52], text localization [17] and pose estimation [43].”
Multiple People Tracking by Lifted Multicut and Person Re-identification (2017, background): “Recent works on multi-person tracking focus on the tracking-by-detection approach [21, 36, 35, 29, 30].”
A Convnet for Non-maximum Suppression (2015, methodology): “PETS has been previously used to study person detection (Tang et al., 2013), tracking (Milan et al., 2014), and crowd density estimation (Subburaman et al., 2012).”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, methodology): “4) The experiment is done on more specific datasets in [74], [75] while our experimental results are”
Multiple object tracking: A literature review (2014, methodology): “In [114] and [113], a multi-person detector is trained based on the detection hypotheses.”