Real-time RGB-D based people detection and tracking for mobile robots and head-worn cameras O Hosseini Jafari, D Mitzel, B Leibe IEEE International Conference on Robotics and Automation (ICRA), 2014, 5636-5643, 2014 | 246 | 2014 |
Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios? A Behl*, O Hosseini Jafari*, SK Mustikovela*, H Abu Alhaija, C Rother, ... The IEEE International Conference on Computer Vision (ICCV), 2574-2583, 2017 | 169 | 2017 |
Deep Object Co-Segmentation W Li*, O Hosseini Jafari*, C Rother, (* = equal contribution) Asian Conference on Computer Vision (ACCV), 2018, 2018 | 153* | 2018 |
Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation O Hosseini Jafari, O Groth, A Kirillov, MY Yang, C Rother IEEE International Conference on Robotics and Automation (ICRA), 2017, 2017 | 81 | 2017 |
iPose: instance-aware 6D pose estimation of partly occluded objects O Hosseini Jafari, SK Mustikovela, K Pertsch, E Brachmann, C Rother ACCV, 2018 | 75* | 2018 |
Real-time RGB-D based template matching pedestrian detection O Hosseini Jafari, MY Yang IEEE International Conference on Robotics and Automation (ICRA), 2016, 5520-5527, 2016 | 12 | 2016 |
Localizing Common Objects Using Common Component Activation Map. W Li, OH Jafari, C Rother CVPR Workshops, 28-31, 2019 | 6 | 2019 |
Semantic-aware image smoothing W Li, OH Jafari, C Rother Proceedings of the conference on Vision, Modeling and Visualization, 153-160, 2017 | 3 | 2017 |
Split-merge pooling OH Jafari, C Rother arXiv preprint arXiv:2006.07742, 2020 | 1 | 2020 |
Exploring Subtasks of Scene Understanding: Challenges and Cross-Modal Analysis O Hosseini Jafari | | 2020 |