Search Results for author: Arne Schumann

Found 7 papers, 4 papers with code

SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes

no code implementations12 Jul 2020 Seyed Majid Azimi, Corentin Henry, Lars Sommer, Arne Schumann, Eleonora Vig

We have defined two main tasks on this dataset: dense semantic segmentation and multi-class lane-marking prediction.

Autonomous Driving Edge Detection +2

Human Pose Estimation for Real-World Crowded Scenarios

1 code implementation16 Jul 2019 Thomas Golda, Tobias Kalb, Arne Schumann, Jürgen Beyerer

In order to overcome the transfer gap of JTA originating from a low pose variety and less dense crowds, an extension dataset is created to ease the use for real-world applications.

Data Augmentation Object Recognition +1

A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking

2 code implementations CVPR 2018 M. Saquib Sarfraz, Arne Schumann, Andreas Eberle, Rainer Stiefelhagen

In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation.

Person Re-Identification Re-Ranking +1

Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model

no code implementations19 Jul 2017 M. Saquib Sarfraz, Arne Schumann, Yan Wang, Rainer Stiefelhagen

The visual cues hinting at attributes can be strongly localized and inference of person attributes such as hair, backpack, shorts, etc., are highly dependent on the acquired view of the pedestrian.

Attribute Multi-Label Image Classification +2

Deep Learning Prototype Domains for Person Re-Identification

no code implementations17 Oct 2016 Arne Schumann, Shaogang Gong, Tobias Schuchert

Person re-identification (re-id) is the task of matching multiple occurrences of the same person from different cameras, poses, lighting conditions, and a multitude of other factors which alter the visual appearance.

Person Re-Identification Unsupervised Domain Adaptation

Cannot find the paper you are looking for? You can Submit a new open access paper.