Piotr Dollár

Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning CVPR 2026 SAM 3D: 3Dfy Anything in Images CVPR 2026 SAM 3D Body: Robust Full-Body Human Mesh Recovery CVPR 2026 SAM 2: Segment Anything in Images and Videos ICLR 2025 Segment Anything ICCV 2023 The Effectiveness of MAE Pre-Pretraining for Billion-Scale Pretraining ICCV 2023 Masked Autoencoders Are Scalable Vision Learners CVPR 2022 Revisiting Weakly Supervised Pre-Training of Visual Perception Models CVPR 2022 Boundary IoU: Improving Object-Centric Image Segmentation Evaluation CVPR 2021 Early Convolutions Help Transformers See Better NeurIPS 2021 Fast and Accurate Model Scaling CVPR 2021 Are Labels Necessary for Neural Architecture Search? ECCV 2020 Designing Network Design Spaces CVPR 2020 LVIS: A Dataset for Large Vocabulary Instance Segmentation CVPR 2019 On Network Design Spaces for Visual Recognition ICCV 2019 Panoptic Feature Pyramid Networks CVPR 2019 Panoptic Segmentation CVPR 2019 Rethinking ImageNet Pre-Training ICCV 2019 TensorMask: A Foundation for Dense Object Segmentation ICCV 2019 Data Distillation: Towards Omni-Supervised Learning CVPR 2018 Detecting and Recognizing Human-Object Interactions CVPR 2018 Learning to Segment Every Thing CVPR 2018 Aggregated Residual Transformations for Deep Neural Networks CVPR 2017 Feature Pyramid Networks for Object Detection CVPR 2017 Focal Loss for Dense Object Detection ICCV 2017 Learning Features by Watching Objects Move CVPR 2017 Mask R-CNN ICCV 2017 Semantic Amodal Segmentation CVPR 2017 Unsupervised Learning of Edges CVPR 2016 From Captions to Visual Concepts and Back CVPR 2015 Learning to Segment Object Candidates NeurIPS 2015 Detecting Objects using Deformation Dictionaries CVPR 2014 Local Decorrelation For Improved Pedestrian Detection NeurIPS 2014 Exploring Weak Stabilization for Motion Feature Extraction CVPR 2013 Quickly Boosting Decision Trees – Pruning Underachieving Features Early ICML 2013 Robust Face Landmark Estimation under Occlusion ICCV 2013 Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection CVPR 2013 Structured Forests for Fast Edge Detection ICCV 2013 Learning to Traverse Image Manifolds NeurIPS 2006