Raquel Urtasun

Research interests

Publications

• V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction

  Lecture notes in computer science · 2020 · 10.1007/978-3-030-58536-5_36

• Learning Lane Graph Representations for Motion Forecasting

  Lecture notes in computer science · 2020 · 10.1007/978-3-030-58536-5_32

• Multi-Task Multi-Sensor Fusion for 3D Object Detection

  · 2019 · 10.1109/cvpr.2019.00752

• Deep Continuous Fusion for Multi-sensor 3D Object Detection

  Lecture notes in computer science · 2018 · 10.1007/978-3-030-01270-0_39

• MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving

  · 2018 · 10.1109/ivs.2018.8500504

• Learning to Reweight Examples for Robust Deep Learning

  arXiv (Cornell University) · 2018 · 10.48550/arxiv.1803.09050

• PIXOR: Real-time 3D Object Detection from Point Clouds

  Journal · 2018 · https://doi.org/10.1109/cvpr.2018.00798

• Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net

  · 2018 · 10.1109/cvpr.2018.00376

• 3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2017 · 10.1109/tpami.2017.2706685

• Understanding the Effective Receptive Field in Deep Convolutional Neural Networks

  arXiv (Cornell University) · 2017 · 10.48550/arxiv.1701.04128

• Deep Watershed Transform for Instance Segmentation

  · 2017 · 10.1109/cvpr.2017.305

• 3D Graph Neural Networks for RGBD Semantic Segmentation

  · 2017 · 10.1109/iccv.2017.556

• Towards Diverse and Natural Image Descriptions via a Conditional GAN

  · 2017 · 10.1109/iccv.2017.323

• DeepRoadMapper: Extracting Road Topology from Aerial Images

  · 2017 · 10.1109/iccv.2017.372

• Understanding the Effective Receptive Field in Deep Convolutional Neural\n Networks

  arXiv (Cornell University) · 2017 · 10.48550/arxiv.1701.04128

• Monocular 3D Object Detection for Autonomous Driving

  Journal · 2016 · https://doi.org/10.1109/cvpr.2016.236

• Efficient Deep Learning for Stereo Matching

  · 2016 · 10.1109/cvpr.2016.614

• Skip-Thought Vectors

  arXiv (Cornell University) · 2015 · 10.48550/arxiv.1506.06726

• 3D object proposals for accurate object class detection

  · 2015

• Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books

  Journal · 2015 · https://doi.org/10.1109/iccv.2015.11

• Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts

  · 2014 · 10.1109/cvpr.2014.254

• The Role of Context for Object Detection and Semantic Segmentation in the Wild

  Journal · 2014 · https://doi.org/10.1109/cvpr.2014.119

• Vision meets robotics: The KITTI dataset

  The International Journal of Robotics Research · 2013 · https://doi.org/10.1177/0278364913491297

• Efficient Large-Scale Stereo Matching

  Lecture notes in computer science · 2011 · 10.1007/978-3-642-19315-6_3

• 3D People Tracking with Gaussian Process Dynamical Models

  · 2006 · 10.1109/cvpr.2006.15

Current projects

No projects listed.