Urtasun, I.[Inaki]
Co Author Listing * Fast and robust ellipse detection algorithm for head-mounted eye tracking systems
Includes: Urtasun, I.[Inaki] Urtasun, I.[Iņaki]
Urtasun, R.
Co Author Listing * 3D Graph Neural Networks for RGBD Semantic Segmentation
* 3D Human Body Tracking Using Deterministic Temporal Motion Models
* 3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection
* 3D People Tracking with Gaussian Process Dynamical Models
* 3D tracking for gait characterization and recognition
* 3D Traffic Scene Understanding From Movable Platforms
* Active Learning with Gaussian Processes for Object Categorization
* Adversarial Attacks On Multi-Agent Communication
* AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles
* Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books
* Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs
* Annotating Object Instances with a Polygon-RNN
* Are we ready for autonomous driving? The KITTI vision benchmark suite
* automatic method for determining quaternion field boundaries for ball-and-socket joint limits, An
* Be Your Own Prada: Fashion Synthesis with Structural Coherence
* Beat the MTurkers: Automatic Image Labeling from Weak 3D Supervision
* Beyond Feature Points: Structured Prediction for Monocular Non-rigid 3D Reconstruction
* Bottom-Up Segmentation for Top-Down Detection
* Box in the Box: Joint 3D Layout and Object Reasoning from Single Images
* Co-training with noisy perceptual observations
* Combining discriminative and generative methods for 3D deformable surface and articulated pose reconstruction
* Conditional Entropy Coding for Efficient Video Compression
* constrained latent variable model, A
* Continuous Markov Random Fields for Robust Stereo Estimation
* Convolutional Recurrent Network for Road Boundary Extraction
* DAGMapper: Learning to Map by Discovering Lane Topology
* DARNet: Deep Active Ray Network for Building Segmentation
* Data-driven animation of hand-object interactions
* Deep Continuous Fusion for Multi-sensor 3D Object Detection
* Deep Feedback Inverse Problem Solver
* Deep Multi-Task Learning for Joint Localization, Perception, and Prediction
* Deep Parametric Continuous Convolutional Neural Networks
* Deep Rigid Instance Scene Flow
* Deep Watershed Transform for Instance Segmentation
* Deep Watershed Transform for Instance Segmentation
* DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
* DeepRoadMapper: Extracting Road Topology from Aerial Images
* Dense Reppoints: Representing Visual Objects with Dense Point Sets
* Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation
* Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts
* Distributed message passing for large scale graphical models
* DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation
* Dsdnet: Deep Structured Self-driving Network
* DSIC: Deep Stereo Image Compression
* Efficient Convolutions for Real-Time Semantic Segmentation of 3D Point Clouds
* Efficient Deep Learning for Stereo Matching
* Efficient Exact Inference for 3D Indoor Scene Understanding
* Efficient Joint Segmentation, Occlusion Labeling, Stereo and Flow Estimation
* Efficient Large-Scale Stereo Matching
* Efficient Multiple Instance Metric Learning Using Weakly Supervised Data
* Efficient structured prediction for 3D indoor scene understanding
* End-to-End Deep Structured Models for Drawing Crosswalks
* End-To-End Interpretable Neural Motion Planner
* Enhancing Road Maps by Parsing Aerial Images Around the World
* Estimating Drivable Collision-Free Space from Monocular Video
* Estimating the 3D Layout of Indoor Scenes and Its Clutter from Depth Sensors
* Exploiting Deep Matching and SAR Data for the Geo-Localization Accuracy Improvement of Optical Satellite Images
* Exploiting Semantic Information and Deep Matching for Optical Flow
* Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
* FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation
* Gaussian Processes for Object Categorization
* Generating Multi-sentence Natural Language Descriptions of Indoor Scenes
* generative model for 3D urban scene understanding from movable platforms, A
* GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation
* GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
* GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving
* HD Maps: Fine-Grained Road Segmentation by Parsing Ground and Aerial Images
* Hierarchical implicit surface joint limits for human body tracking
* Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture
* Hierarchical Recurrent Attention Networks for Structured Online Maps
* High Performance CRF Model for Clothes Parsing, A
* Holistic 3D scene understanding from a single geo-tagged image
* Holistic Scene Understanding for 3D Object Detection with RGBD Cameras
* HouseCraft: Building Houses from Rental Ads and Street Views
* Human-Machine CRFs for Identifying Bottlenecks in Scene Understanding
* Implicit Latent Variable Model for Scene-consistent Motion Forecasting
* Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving
* Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
* Learning Compact Representations for LiDAR Completion and Generation
* Learning Deep Structured Active Contours End-to-End
* Learning Joint 2D-3D Representations for Depth Completion
* Learning Lane Graph Representations for Motion Forecasting
* Learning to Localize Through Compressed Binary Maps
* Learning to Recognize Objects from Unseen Modalities
* Learning to segment under various forms of weak supervision
* Levelset R-CNN: A Deep Variational Method for Instance Segmentation
* LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
* Local deformation models for monocular 3D shape recovery
* LookOut: Diverse Multi-Future Prediction and Planning for Self-Driving
* Lost Shopping! Monocular Localization in Large Indoor Spaces
* Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization
* Map-Based Probabilistic Visual Self-Localization
* Matching Adversarial Networks
* MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory
* Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild
* MIXSIM: A Hierarchical Framework for Mixed Reality Traffic Simulation
* Modeling Human Locomotion with Topologically Constrained Latent Variable Models
* Monocular 3-D Tracking of the Golf Swing
* Monocular 3D Object Detection for Autonomous Driving
* Monocular Object Instance Segmentation and Depth Ordering with CNNs
* MovieQA: Understanding Stories in Movies through Question-Answering
* MP3: A Unified Model to Map, Perceive, Predict and Plan
* Multi-Task Multi-Sensor Fusion for 3D Object Detection
* Neuroaesthetics in fashion: Modeling the perception of fashionability
* OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
* Patch-Based Pose Inference with a Mixture of Density Estimators
* Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations
* Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks
* Physically Realizable Adversarial Examples for LiDAR Object Detection
* Physically-based motion models for 3D tracking: A convex formulation
* PIXOR: Real-time 3D Object Detection from Point Clouds
* PnPNet: End-to-End Perception and Prediction With Tracking in the Loop
* PolyTransform: Deep Polygon Transformer for Instance Segmentation
* Priors for People Tracking from Small Training Sets
* Radarnet: Exploiting Radar for Robust Perception of Dynamic Objects
* Rank Priors for Continuous Non-Linear Dimensionality Reduction
* Real-time coarse-to-fine topologically preserving segmentation
* Real-Time Neural Rasterization for Large Scenes
* Rent3D: Floor-plan priors for monocular layout estimation
* Rethinking Closed-Loop Training for Autonomous Driving
* Robust Monocular Epipolar Flow Estimation
* Role of Context for Object Detection and Semantic Segmentation in the Wild, The
* S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling
* SBNet: Sparse Blocks Network for Fast Inference
* SceneGen: Learning to Generate Realistic Traffic Scenes
* segDeepM: Exploiting segmentation and context in deep neural networks for object detection
* Segmentation of 3D Head MR Images Using Morphological Reconstruction Under Constraints and Automatic Selection of Markers
* Sentence Is Worth a Thousand Pixels, A
* SGN: Sequential Grouping Networks for Instance Segmentation
* Single Image Intrinsic Decomposition Without a Single Intrinsic Image
* Situation Recognition with Graph Neural Networks
* Sparse probabilistic regression for activity-independent human pose inference
* Sports Field Localization via Deep Structured Models
* Sufficient dimension reduction for visual sequence classification
* Supervised hierarchical Pitman-Yor process for natural scene segmentation
* SurfConv: Bridging 3D and 2D Convolution for RGBD Images
* Tell Me What You See and I Will Show You Where It Is
* Temporal motion models for monocular and multiview 3D human body tracking
* Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction
* Topologically controlled segmentation of 3D magnetic resonance images of the head by using morphological operators
* TorontoCity: Seeing the World with a Million Eyes
* Towards Affordable Self-driving Cars
* Towards Diverse and Natural Image Descriptions via a Conditional GAN
* Towards Unsupervised Object Detection from LiDAR Point Clouds
* Towards Zero Domain Gap: A Comprehensive Study of Realistic LiDAR Simulation for Autonomy Testing
* TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors
* Transductive Gaussian processes for image denoising
* Transferring Nonlinear Representations using Gaussian Processes with a Shared Latent Space
* Understanding High-Level Semantics by Modeling Traffic Patterns
* UniSim: A Neural Closed-Loop Sensor Simulator
* Unsupervised feature selection via distributed coding for multi-view object recognition
* UPSNet: A Unified Panoptic Segmentation Network
* V2vnet: Vehicle-to-vehicle Communication for Joint Perception and Prediction
* Virtual Correspondence: Humans as a Cue for Extreme-View Geometry
* Vision meets robotics: The KITTI dataset
* Visual Semantic Search: Retrieving Videos via Complex Textual Queries
* Weakly-supervised 3d Shape Completion in the Wild
* What Are You Talking About? Text-to-Image Coreference
Includes: Urtasun, R. Urtasun, R.[Raquel]
158 for Urtasun, R.