James Hays

is this you? claim profile

∙ 0 followers
Georgia Institute of Technology

Associate Professor at Georgia Institute of Technology

3D for Free: Crossmodal Transfer Learning using HD Maps

3D object detection is a core perceptual challenge for robotics and auto...
08/24/2020 ∙ by Benjamin Wilson, et al. ∙ 0 ∙ share

read it
TIDE: A General Toolbox for Identifying Object Detection Errors

We introduce TIDE, a framework and associated toolbox for analyzing the ...
08/18/2020 ∙ by Daniel Bolya, et al. ∙ 17 ∙ share

read it
ContactPose: A Dataset of Grasps with Object Contact and Hand Pose

Grasping is natural for humans. However, it involves complex hand config...
07/19/2020 ∙ by Samarth Brahmbhatt, et al. ∙ 14 ∙ share

read it
Argoverse: 3D Tracking and Forecasting with Rich Maps

We present Argoverse – two datasets designed to support autonomous vehic...
11/06/2019 ∙ by Ming-Fang Chang, et al. ∙ 22 ∙ share

read it
Towards Markerless Grasp Capture

Humans excel at grasping objects and manipulating them. Capturing human ...
07/17/2019 ∙ by Samarth Brahmbhatt, et al. ∙ 0 ∙ share

read it
Kernel Mean Matching for Content Addressability of GANs

We propose a novel procedure which adds "content-addressability" to any ...
05/14/2019 ∙ by Wittawat Jitkrittum, et al. ∙ 7 ∙ share

read it
ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging

Grasping and manipulating objects is an important human skill. Since han...
04/15/2019 ∙ by Samarth Brahmbhatt, et al. ∙ 0 ∙ share

read it
ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact

Grasping and manipulating objects is an important human skill. Since mos...
04/07/2019 ∙ by Samarth Brahmbhatt, et al. ∙ 0 ∙ share

read it
Let's Transfer Transformations of Shared Semantic Representations

With a good image understanding capability, can we manipulate the images...
03/02/2019 ∙ by Nam Vo, et al. ∙ 12 ∙ share

read it
Composing Text and Image for Image Retrieval - An Empirical Odyssey

In this paper, we study the task of image retrieval, where the input que...
12/18/2018 ∙ by Nam Vo, et al. ∙ 20 ∙ share

read it
Informative Features for Model Comparison

Given two candidate models, and a set of target observations, we address...
10/27/2018 ∙ by Wittawat Jitkrittum, et al. ∙ 0 ∙ share

read it
Generalization in Metric Learning: Should the Embedding Layer be the Embedding Layer?

Many recent works advancing deep learning tend to focus on large scale s...
03/08/2018 ∙ by Nam Vo, et al. ∙ 0 ∙ share

read it
Let's Dance: Learning From Online Dance Videos

In recent years, deep neural network approaches have naturally extended ...
01/23/2018 ∙ by Daniel Castro, et al. ∙ 0 ∙ share

read it
SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis

Synthesizing realistic images from human drawn sketches is a challenging...
01/09/2018 ∙ by Wengling Chen, et al. ∙ 0 ∙ share

read it
MapNet: Geometry-Aware Learning of Maps for Camera Localization

Maps are a key component in image-based camera localization and visual S...
12/09/2017 ∙ by Samarth Brahmbhatt, et al. ∙ 0 ∙ share

read it
TextureGAN: Controlling Deep Image Synthesis with Texture Patches

In this paper, we investigate deep image synthesis guided by sketch, col...
06/09/2017 ∙ by Wenqi Xian, et al. ∙ 0 ∙ share

read it
On Convergence and Stability of GANs

We propose studying GAN training dynamics as regret minimization, which ...
05/19/2017 ∙ by Naveen Kodali, et al. ∙ 0 ∙ share

read it
Revisiting IM2GPS in the Deep Learning Era

Image geolocalization, inferring the geographic location of an image, is...
05/13/2017 ∙ by Nam Vo, et al. ∙ 0 ∙ share

read it
DeepNav: Learning to Navigate Large Cities

We present DeepNav, a Convolutional Neural Network (CNN) based algorithm...
01/31/2017 ∙ by Samarth Brahmbhatt, et al. ∙ 0 ∙ share

read it
Super-resolution Using Constrained Deep Texture Synthesis

Hallucinating high frequency image details in single image super-resolut...
01/26/2017 ∙ by Libin Sun, et al. ∙ 0 ∙ share

read it
Complex Event Recognition from Images with Few Training Examples

We propose to leverage concept-level representations for complex event r...
01/17/2017 ∙ by Unaiza Ahsan, et al. ∙ 0 ∙ share

read it
Scribbler: Controlling Deep Image Synthesis with Sketch and Color

Recently, there have been several promising methods to generate realisti...
12/02/2016 ∙ by Patsorn Sangkloy, et al. ∙ 0 ∙ share

read it
StuffNet: Using 'Stuff' to Improve Object Detection

We propose a Convolutional Neural Network (CNN) based algorithm - StuffN...
10/19/2016 ∙ by Samarth Brahmbhatt, et al. ∙ 0 ∙ share

read it
Localizing and Orienting Street Views Using Overhead Imagery

In this paper we aim to determine the location and orientation of a grou...
07/30/2016 ∙ by Nam Vo, et al. ∙ 0 ∙ share

read it
Lens Factory: Automatic Lens Generation Using Off-the-shelf Components

Custom optics is a necessity for many imaging applications. Unfortunatel...
06/30/2015 ∙ by Libin Sun, et al. ∙ 0 ∙ share

read it
Microsoft COCO: Common Objects in Context

We present a new dataset with the goal of advancing the state-of-the-art...
05/01/2014 ∙ by Tsung-Yi Lin, et al. ∙ 0 ∙ share

read it

James Hays

Featured Co-authors

Bernhard Schölkopf

Li Fei-Fei

Jan Kautz

Dieter Fox

Arthur Gretton

Serge Belongie

Deva Ramanan

Ross Girshick

Kevin Murphy

Simon Lucey

Pietro Perona

3D for Free: Crossmodal Transfer Learning using HD Maps

TIDE: A General Toolbox for Identifying Object Detection Errors

ContactPose: A Dataset of Grasps with Object Contact and Hand Pose

Argoverse: 3D Tracking and Forecasting with Rich Maps

Towards Markerless Grasp Capture

Kernel Mean Matching for Content Addressability of GANs

ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging

ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact

Let's Transfer Transformations of Shared Semantic Representations

Composing Text and Image for Image Retrieval - An Empirical Odyssey

Informative Features for Model Comparison

Generalization in Metric Learning: Should the Embedding Layer be the Embedding Layer?

Let's Dance: Learning From Online Dance Videos

SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesis

MapNet: Geometry-Aware Learning of Maps for Camera Localization

TextureGAN: Controlling Deep Image Synthesis with Texture Patches

On Convergence and Stability of GANs

Revisiting IM2GPS in the Deep Learning Era

DeepNav: Learning to Navigate Large Cities

Super-resolution Using Constrained Deep Texture Synthesis

Complex Event Recognition from Images with Few Training Examples

Scribbler: Controlling Deep Image Synthesis with Sketch and Color

StuffNet: Using 'Stuff' to Improve Object Detection

Localizing and Orienting Street Views Using Overhead Imagery

Lens Factory: Automatic Lens Generation Using Off-the-shelf Components

Microsoft COCO: Common Objects in Context