Derek Hoiem

RELOCATE: A Simple Training-Free Baseline for Visual Query Localization Using Region-Based Representations CVPR 2025 Visual Program Distillation with Template-Based Augmentation EMNLP 2025 Anytime Continual Learning for Open Vocabulary Classification ECCV 2024 Consistent Multimodal Generation via a Unified GAN Framework WACV 2024 Region-Based Representations Revisited CVPR 2024 Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action CVPR 2024 WebWISE: Unlocking Web Interface Control for LLMs via Sequential Exploration NAACL 2024 StyleGAN knows Normal, Depth, Albedo, and More NeurIPS 2023 ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation EMNLP 2023 Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners NeurIPS 2022 Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture CVPR 2022 Webly Supervised Concept Expansion for General Purpose Vision Models ECCV 2022 Learning Curves for Analysis of Deep Networks ICML 2021 PatchMatch-RL: Deep MVS With Pixelwise Depth, Normal, and Visibility ICCV 2021 Task-Assisted Domain Adaptation With Anchor Tasks WACV 2021 Contrastive Learning for Weakly Supervised Phrase Grounding ECCV 2020 Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion CVPR 2020 Improving Confidence Estimates for Unfamiliar Examples CVPR 2020 Silhouette Guided Point Cloud Reconstruction beyond Occlusion WACV 2020 No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques ICCV 2019 ViCo: Word Embeddings From Visual Co-Occurrences ICCV 2019 Imagine This! Scripts to Compositions to Videos ECCV 2018 Improved Structure from Motion Using Fiducial Marker Matching ECCV 2018 LayoutNet: Reconstructing the 3D Room Layout From a Single RGB Image CVPR 2018 Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction CVPR 2018 3D-PRNN: Generating Shape Primitives With Recurrent Neural Networks ICCV 2017 Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks ICCV 2017 ChromaTag: A Colored Marker and Fast Detection Algorithm ICCV 2017 Geometry-Informed Material Recognition CVPR 2016 Learning to Localize Little Landmarks CVPR 2016 Swapout: Learning an ensemble of deep architectures NeurIPS 2016 Where to Look: Focus Regions for Visual Question Answering CVPR 2016 Completing 3D Object Shape From One Depth Image CVPR 2015 Learning a Sequential Search for Landmarks CVPR 2015 Boundary Cues for 3D Object Shape Recovery CVPR 2013 Learning Collections of Part Models for Object Recognition CVPR 2013 Support Surface Prediction in Indoor Scenes ICCV 2013