Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows

Aug 28, 2020
Marco Rudolph, Bastian Wandt, Bodo Rosenhahn


  Access Paper or Ask Questions

TOAD-GAN: Coherent Style Level Generation from a Single Example

Aug 04, 2020
Maren Awiszus, Frederik Schubert, Bodo Rosenhahn

* 7 pages, 7 figures. AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) 2020 

  Access Paper or Ask Questions

Weakly-supervised Learning of Human Dynamics

Jul 17, 2020
Petrissa Zell, Bodo Rosenhahn, Bastian Wandt


  Access Paper or Ask Questions

Lifted Disjoint Paths with Application in Multiple Object Tracking

Jun 25, 2020
Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda

* ICML 2020, Codebase available at https://github.com/AndreaHor/LifT_Solver 

  Access Paper or Ask Questions

AMENet: Attentive Maps Encoder Network for Trajectory Prediction

Jun 15, 2020
Hao Cheng, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn, Monika Sester


  Access Paper or Ask Questions

LR-CNN: Local-aware Region CNN for Vehicle Detection in Aerial Imagery

May 28, 2020
Wentong Liao, Xiang Chen, Jingfeng Yang, Stefan Roth, Michael Goesele, Michael Ying Yang, Bodo Rosenhahn

* 8 pages 

  Access Paper or Ask Questions

Image Captioning through Image Transformer

Apr 29, 2020
Sen He, Wentong Liao, Hamed R. Tavakoli, Michael Yang, Bodo Rosenhahn, Nicolas Pugeault


  Access Paper or Ask Questions

FairNN- Conjoint Learning of Fair Representations for Fair Decisions

Apr 11, 2020
Tongxin Hu, Vasileios Iosifidis, Wentong Liao, Hang Zhang, Michael YingYang, Eirini Ntoutsi, Bodo Rosenhahn

* Code will be available 

  Access Paper or Ask Questions

MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic

Mar 03, 2020
Hao Cheng, Wentong Liao. Michael Ying Yang, Monika Sester, Bodo Rosenhahn

* 8 pages, 5 figures, code is available on https://github.com/haohao11/MCENET 

  Access Paper or Ask Questions

Context Conditional Variational Autoencoder for Predicting Multi-Path Trajectories in Mixed Traffic

Feb 17, 2020
Hao Cheng, Wentong Liao. Michael Ying Yang, Monica Sester, Bodo Rosenhahn

* 7 pages, 4 figures, code is available on https://github.com/wtliao/CCVAE 

  Access Paper or Ask Questions

NODIS: Neural Ordinary Differential Scene Understanding

Jan 14, 2020
Cong Yuren, Hanno Ackermann, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn


  Access Paper or Ask Questions

CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus

Jan 08, 2020
Florian Kluger, Eric Brachmann, Hanno Ackermann, Carsten Rother, Michael Ying Yang, Bodo Rosenhahn


  Access Paper or Ask Questions

Neural Random Forest Imitation

Nov 25, 2019
Christoph Reinders, Bodo Rosenhahn


  Access Paper or Ask Questions

Learning Disentangled Representations via Independent Subspaces

Aug 26, 2019
Maren Awiszus, Hanno Ackermann, Bodo Rosenhahn

* Accepted at ICCV 2019 Workshop on Robust Subspace Learning and Applications in Computer Vision 

  Access Paper or Ask Questions

Structuring Autoencoders

Aug 07, 2019
Marco Rudolph, Bastian Wandt, Bodo Rosenhahn


  Access Paper or Ask Questions

Temporally Consistent Horizon Lines

Jul 23, 2019
Florian Kluger, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn


  Access Paper or Ask Questions

Exploring the Semantics for Visual Relationship Detection

Apr 03, 2019
Wentong Liao, Cuiling Lan, Wenjun Zeng, Michael Ying Yang, Bodo Rosenhahn


  Access Paper or Ask Questions

RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation

Mar 12, 2019
Bastian Wandt, Bodo Rosenhahn

* accepted to CVPR 2019 

  Access Paper or Ask Questions

Security Event Recognition for Visual Surveillance

Oct 26, 2018
Michael Ying Yang, Wentong Liao, Chun Yang, Yanpeng Cao, Bodo Rosenhahn


  Access Paper or Ask Questions

Object Recognition from very few Training Examples for Enhancing Bicycle Maps

May 28, 2018
Christoph Reinders, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn

* Submitted to IV 2018. This research was supported by German Research Foundation DFG within Priority Research Programme 1894 "Volunteered Geographic Information: Interpretation, Visualization and Social Computing" 

  Access Paper or Ask Questions

Markov Chain Neural Networks

May 02, 2018
Maren Awiszus, Bodo Rosenhahn

* Accepted for CVPR 2018 Workshop Track 

  Access Paper or Ask Questions

Fusion of Head and Full-Body Detectors for Multi-Object Tracking

Apr 24, 2018
Roberto Henschel, Laura Leal-Taixé, Daniel Cremers, Bodo Rosenhahn

* 10 pages, 4 figures; Winner of the MOT17 challenge; CVPRW 2018 

  Access Paper or Ask Questions

Unbiased Sparse Subspace Clustering By Selective Pursuit

Feb 09, 2018
Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn

* Conference on Computer and Robot Vision, 2017 (Oral) 

  Access Paper or Ask Questions

Temporally Object-based Video Co-Segmentation

Feb 09, 2018
Michael Ying Yang, Matthias Reso, Jun Tang, Wentong Liao, Bodo Rosenhahn

* ISVC 2015 (Oral) 

  Access Paper or Ask Questions

Slice Sampling Particle Belief Propagation

Feb 09, 2018
Oliver Mueller, Michael Ying Yang, Bodo Rosenhahn

* published in ICCV 2013 

  Access Paper or Ask Questions

Video Event Recognition and Anomaly Detection by Combining Gaussian Process and Hierarchical Dirichlet Process Models

Feb 09, 2018
Michael Ying Yang, Wentong Liao, Yanpeng Cao, Bodo Rosenhahn


  Access Paper or Ask Questions

Triplet-based Deep Similarity Learning for Person Re-Identification

Feb 09, 2018
Wentong Liao, Michael Ying Yang, Ni Zhan, Bodo Rosenhahn

* ICCV Workshops 2017 

  Access Paper or Ask Questions

Vehicle Detection in Aerial Images

Feb 09, 2018
Michael Ying Yang, Wentong Liao, Xinbo Li, Bodo Rosenhahn


  Access Paper or Ask Questions

Natural Language Guided Visual Relationship Detection

Nov 21, 2017
Wentong Liao, Lin Shuai, Bodo Rosenhahn, Michael Ying Yang

* added supplementary material 

  Access Paper or Ask Questions

Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection

Nov 16, 2017
Florian Kluger, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn

* Accepted for publication at German Conference on Pattern Recognition (GCPR) 2017. This research was supported by German Research Foundation DFG within Priority Research Programme 1894 "Volunteered Geographic Information: Interpretation, Visualisation and Social Computing" 

  Access Paper or Ask Questions