Hoiem, D.[Derek]
Co Author Listing * 3D Layout CRF for Multi-View Object Class Recognition and Segmentation
* 3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks
* Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks
* Attribute-centric recognition for cross-category generalization
* benefits and challenges of collecting richer object annotations, The
* Beyond the Line of Sight: Labeling the Underlying Surfaces
* Boundary Cues for 3D Object Shape Recovery
* Building text features for object image classification
* Category Independent Object Proposals
* Category-Independent Object Proposals with Diverse Ranking
* ChromaTag: A Colored Marker and Fast Detection Algorithm
* Closing the loop in scene interpretation
* Comparative object similarity for improved recognition with few or no examples
* Complete 3D Scene Parsing from an RGBD Image
* Completing 3D object shape from one depth image
* Computer Vision for Music Identification
* Computer Vision for Music Identification: Video Demonstration
* Consistent Multimodal Generation via A Unified GAN Framework
* Contrastive Learning for Weakly Supervised Phrase Grounding
* data driven method for feature transformation, A
* Describing objects by their attributes
* Diagnosing Error in Object Detectors
* Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion
* Editorial: Introduction to the Special Section on CVPR2019 Best Papers
* empirical study of context in object detection, An
* Family Member Identification from Photo Collections
* FEATS: Synthetic Feature Tracks for Structure from Motion Evaluation
* Geometric Context from a Single Image
* Geometry-Informed Material Recognition
* Guest Editorial: Scene Understanding
* Imagine This! Scripts to Compositions to Videos
* Improved Object Categorization and Detection Using Comparative Object Similarity
* Improved Structure from Motion Using Fiducial Marker Matching
* Improving Confidence Estimates for Unfamiliar Examples
* Improving Structure from Motion with Reliable Resectioning
* Indoor Segmentation and Support Inference from RGBD Images
* Labeling Complete Surfaces in Scene Understanding
* LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
* Learning a sequential search for landmarks
* Learning Collections of Part Models for Object Recognition
* Learning CRFs Using Graph Cuts
* Learning Discriminative Collections of Part Detectors for Object Recognition
* Learning Image Similarity from Flickr Groups Using Fast Kernel Machines
* Learning image similarity from Flickr groups using Stochastic Intersection Kernel Machines
* Learning shared body plans
* Learning to Find Object Boundaries Using Motion Cues
* Learning to localize detected objects
* Learning to Localize Little Landmarks
* Learning Without Forgetting
* Manhattan Room Layout Reconstruction from a Single 360° Image: A Comparative Study of State-of-the-Art Methods
* No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques
* Object-based image retrieval using the statistical structure of images
* Paired Regions for Shadow Detection and Removal
* Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization
* PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility
* Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction
* Putting Objects in Perspective
* Recovering free space of indoor scenes from a single image
* Recovering Occlusion Boundaries from a Single Image
* Recovering Occlusion Boundaries from an Image
* Recovering Surface Layout from an Image
* Recovering the spatial layout of cluttered rooms
* Seeing the World Behind the Image: Spatial Layout for 3D Scene Understanding
* Semantic Learning for Audio Applications: A Computer Vision Approach
* Silhouette Guided Point Cloud Reconstruction beyond Occlusion
* Single-image shadow detection and removal using paired regions
* Support Surface Prediction in Indoor Scenes
* Task-Assisted Domain Adaptation with Anchor Tasks
* Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry
* Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture
* ViCo: Word Embeddings From Visual Co-Occurrences
* Webly Supervised Concept Expansion for General Purpose Vision Models
* Where to Look: Focus Regions for Visual Question Answering
Includes: Hoiem, D.[Derek] Hoiem, D.
73 for Hoiem, D.
Hoier, R.K.[Rasmus Kjær]
Co Author Listing * AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks
Includes: Hoier, R.K.[Rasmus Kjær] Høier, R.K.[Rasmus Kjær]