Learning people detection models from few training samples

By Leonid Pishchulin, Arjun Jain, Christian Wojek, Mykhaylo Andriluka, Thorsten Thormählen, Bernt Schiele. 2011

92 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

DensePose: Dense Human Pose Estimation in the Wild (2018, background): “Synthetic ground-truth can be established by rendering images using surface-based models [33, 32, 37, 11, 5, 30].”
Video-Based Human Behavior Understanding: A Survey (2013, methodology): “[37] perform training on synthetically generated models, by employing a rendering-based reshaping technique to create thousands of images from only a small number of real images.”
Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars (2017, background): “…and Schmid 2016; Zhou et al. 2016; Chen et al. 2016; Varol et al. 2017), depth prediction (Su et al. 2014), pedestrian detection (Marin et al. 2010; Pishchulin et al. 2011; Vázquez et al. 2014; Hattori et al. 2015), action recognition (Rahmani and Mian 2015, 2016; Roberto de et al. 2017), semantic…”
Transformation Pursuit for Image Classification (2014, background): “While it might be difficult to generate virtual samples that reflect intrinsic class variations (except for specific object classes such as pedestrians [20, 22]), it is possible to generate virtual samples that simulate extrinsic variations by applying simple geometric”
Expecting the Unexpected: Training Detectors for Unusual Pedestrians with Adversarial Imposters (2017, methodology): “[35] used 8 HD cameras to scan human body and built real 3D human models.”
Augmented Reality Meets Computer Vision: Efficient Data Generation for Urban Driving Scenes (2017, unknown): “[18] use synthetic human bodies rendered on random backgrounds for training a pedestrian detector.”
Learning from Synthetic Humans (2017, background): “[27] generate synthetic images with a game engine.”
Augmented Reality meets Deep Learning (2017, unknown): “[19] use synthetic human bodies rendered on random backgrounds for training a pedestrian detector.”
Learning scene-specific pedestrian detectors without real data (2015, background): “combined synthesized real 3D human body models and a small number of labeled pedestrian bounding boxes to learn a very robust pedestrian detector [26].”