Gregory D. Hager

is this you? claim profile

Professor of Computer Science at Johns Hopkins University, Founding Director, Malone Center for Engineering in Healthcare

"Good Robot!": Efficient Reinforcement Learning for Multi-Step Visual Tasks via Reward Shaping

In order to learn effectively, robots must be able to extract the intang...
09/25/2019 ∙ by Andrew Hundt, et al. ∙ 34 ∙ share

read it
Car Pose in Context: Accurate Pose Estimation with Ground Plane Constraints

Scene context is a powerful constraint on the geometry of objects within...
12/09/2019 ∙ by Pengfei Li, et al. ∙ 23 ∙ share

read it
Extremely Dense Point Correspondences using a Learned Feature Descriptor

High-quality 3D reconstructions from endoscopy video play an important r...
03/02/2020 ∙ by Xingtong Liu, et al. ∙ 18 ∙ share

read it
Artificial Intelligence-based Clinical Decision Support for COVID-19 – Where Art Thou?

The COVID-19 crisis has brought about new clinical questions, new workfl...
06/05/2020 ∙ by Mathias Unberath, et al. ∙ 16 ∙ share

read it
Semantic Stereo for Incidental Satellite Images

The increasingly common use of incidental satellite images for stereo re...
11/21/2018 ∙ by Marc Bosch, et al. ∙ 10 ∙ share

read it
RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition

Despite the rapid growth in datasets for video activity, stable robust a...
12/03/2019 ∙ by Yi Zhang, et al. ∙ 8 ∙ share

read it
Guide Me: Interacting with Deep Networks

Interaction and collaboration between humans and intelligent machines ha...
03/30/2018 ∙ by Christian Rupprecht, et al. ∙ 2 ∙ share

read it
Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies

Recurrent neural networks (RNNs) have achieved state-of-the-art performa...
02/24/2017 ∙ by Robert DiPietro, et al. ∙ 0 ∙ share

read it
Advances in Artificial Intelligence Require Progress Across all of Computer Science

Advances in Artificial Intelligence require progress across all of compu...
07/13/2017 ∙ by Gregory D. Hager, et al. ∙ 0 ∙ share

read it
Adversarial Deep Structured Nets for Mass Segmentation from Mammograms

Mass segmentation provides effective morphological features which are im...
10/24/2017 ∙ by Wentao Zhu, et al. ∙ 0 ∙ share

read it
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing

Monocular 3D object parsing is highly desirable in various scenarios inc...
12/08/2016 ∙ by Chi Li, et al. ∙ 0 ∙ share

read it
Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses

Many prediction tasks contain uncertainty. In some cases, uncertainty is...
12/01/2016 ∙ by Christian Rupprecht, et al. ∙ 0 ∙ share

read it
Temporal Convolutional Networks for Action Segmentation and Detection

The ability to identify and temporally segment fine-grained human action...
11/16/2016 ∙ by Colin Lea, et al. ∙ 0 ∙ share

read it
Anatomically Constrained Video-CT Registration via the V-IMLOP Algorithm

Functional endoscopic sinus surgery (FESS) is a surgical procedure used ...
10/25/2016 ∙ by Seth D. Billings, et al. ∙ 0 ∙ share

read it
Temporal Convolutional Networks: A Unified Approach to Action Segmentation

The dominant paradigm for video-based action segmentation is composed of...
08/29/2016 ∙ by Colin Lea, et al. ∙ 0 ∙ share

read it
SANTIAGO: Spine Association for Neuron Topology Improvement and Graph Optimization

Developing automated and semi-automated solutions for reconstructing wir...
08/08/2016 ∙ by William Gray Roncal, et al. ∙ 0 ∙ share

read it
Recognizing Surgical Activities with Recurrent Neural Networks

We apply recurrent neural networks to the task of recognizing surgical a...
06/20/2016 ∙ by Robert DiPietro, et al. ∙ 0 ∙ share

read it
Segmental Spatiotemporal CNNs for Fine-grained Action Segmentation

Joint segmentation and classification of fine-grained actions is importa...
02/09/2016 ∙ by Colin Lea, et al. ∙ 0 ∙ share

read it
Automated Objective Surgical Skill Assessment in the Operating Room Using Unstructured Tool Motion

Previous work on surgical skill assessment using intraoperative tool mot...
12/18/2014 ∙ by Piyush Poddar, et al. ∙ 0 ∙ share

read it
An Automated Images-to-Graphs Framework for High Resolution Connectomics

Reconstructing a map of neuronal connectivity is a critical challenge in...
11/25/2014 ∙ by William Gray Roncal, et al. ∙ 0 ∙ share

read it
Hierarchical Sparse and Collaborative Low-Rank Representation for Emotion Recognition

In this paper, we design a Collaborative-Hierarchical Sparse and Low-Ran...
10/07/2014 ∙ by Xiang Xiang, et al. ∙ 0 ∙ share

read it
Multi-environment model estimation for motility analysis of Caenorhabditis Elegans

The nematode Caenorhabditis elegans is a well-known model organism used ...
07/08/2010 ∙ by Raphael Sznitman, et al. ∙ 0 ∙ share

read it
Temporal and Physical Reasoning for Perception-Based Robotic Manipulation

Accurate knowledge of object poses is crucial to successful robotic mani...
10/11/2017 ∙ by Felix Jonathan, et al. ∙ 0 ∙ share

read it
Regularizing Face Verification Nets For Pain Intensity Regression

Limited labeled data are available for the research of estimating facial...
02/22/2017 ∙ by Feng Wang, et al. ∙ 0 ∙ share

read it
Deep Supervision with Intermediate Concepts

Recent data-driven approaches to scene interpretation predominantly pose...
01/08/2018 ∙ by Chi Li, et al. ∙ 0 ∙ share

read it
Learning to Imagine Manipulation Goals for Robot Task Planning

Prospection is an important part of how humans come up with new task pla...
11/08/2017 ∙ by Chris Paxton, et al. ∙ 0 ∙ share

read it
A Unified Framework for Multi-View Multi-Class Object Pose Estimation

One core challenge in object pose estimation is to ensure accurate and r...
03/21/2018 ∙ by Chi Li, et al. ∙ 0 ∙ share

read it
Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation

Fast, collision-free motion through unknown environments remains a chall...
03/06/2018 ∙ by Kapil Katyal, et al. ∙ 0 ∙ share

read it
Visual Robot Task Planning

Prospection, the act of predicting the consequences of many possible fut...
03/30/2018 ∙ by Chris Paxton, et al. ∙ 0 ∙ share

read it
Unsupervised Learning for Surgical Motion by Learning to Predict the Future

We show that it is possible to learn meaningful representations of surgi...
06/08/2018 ∙ by Robert DiPietro, et al. ∙ 0 ∙ share

read it
Endoscopic navigation in the absence of CT imaging

Clinical examinations that involve endoscopic exploration of the nasal c...
06/08/2018 ∙ by Ayushi Sinha, et al. ∙ 0 ∙ share

read it
Surgical Data Science: A Consensus Perspective

Surgical data science is a scientific discipline with the objective of i...
06/08/2018 ∙ by Lena Maier-Hein, et al. ∙ 0 ∙ share

read it
Evaluating Methods for End-User Creation of Robot Task Plans

How can we enable users to create effective, perception-driven task plan...
11/06/2018 ∙ by Chris Paxton, et al. ∙ 0 ∙ share

read it
Training Frankenstein's Creature to Stack: HyperTree Architecture Search

We propose HyperTrees for the low cost automatic design of multiple-inpu...
10/27/2018 ∙ by Andrew Hundt, et al. ∙ 0 ∙ share

read it
Artificial Intelligence for Social Good

The Computing Community Consortium (CCC), along with the White House Off...
01/16/2019 ∙ by Gregory D. Hager, et al. ∙ 0 ∙ share

read it
Towards automatic initialization of registration algorithms using simulated endoscopy images

Registering images from different modalities is an active area of resear...
06/28/2018 ∙ by Ayushi Sinha, et al. ∙ 0 ∙ share

read it
sharpDARTS: Faster and More Accurate Differentiable Architecture Search

Neural Architecture Search (NAS) has been a source of dramatic improveme...
03/23/2019 ∙ by Andrew Hundt, et al. ∙ 0 ∙ share

read it
Automated Surgical Activity Recognition with One Labeled Sequence

Prior work has demonstrated the feasibility of automated activity recogn...
07/20/2019 ∙ by Robert DiPietro, et al. ∙ 0 ∙ share

read it
Self-supervised Dense 3D Reconstruction from Monocular Endoscopic Video

We present a self-supervised learning-based pipeline for dense 3D recons...
09/06/2019 ∙ by Xingtong Liu, et al. ∙ 0 ∙ share

read it
Action Recognition Using Volumetric Motion Representations

Traditional action recognition models are constructed around the paradig...
11/19/2019 ∙ by Michael Peven, et al. ∙ 0 ∙ share

read it
Zero-shot Recognition of Complex Action Sequences

Zero-shot video classification for fine-grained activity recognition has...
12/08/2019 ∙ by Jonathan D. Jones, et al. ∙ 0 ∙ share

read it
Semantic Image Manipulation Using Scene Graphs

Image manipulation can be considered a special case of image generation ...
04/07/2020 ∙ by Helisa Dhamo, et al. ∙ 0 ∙ share

read it
Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images

Visual cues of enforcing bilaterally symmetric anatomies as normal findi...
07/03/2020 ∙ by Haomin Chen, et al. ∙ 0 ∙ share

read it
Learning Geocentric Object Pose in Oblique Monocular Images

An object's geocentric pose, defined as the height above ground and orie...
07/01/2020 ∙ by Gordon Christie, et al. ∙ 0 ∙ share

read it

Gregory D. Hager

Featured Co-authors