Search Results for author: Kristin Dana

Found 28 papers, 9 papers with code

Reflectance Hashing for Material Recognition

no code implementations CVPR 2015 Hang Zhang, Kristin Dana, Ko Nishino

Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality.

Dictionary Learning Material Recognition

Reading Between the Pixels: Photographic Steganography for Camera Display Messaging

no code implementations6 Apr 2016 Eric Wengrowski, Kristin Dana, Marco Gruteser, Narayan Mandayam

We sample from the resulting metamer sets to find color steps for each base color to embed a binary message into an arbitrary image with reduced visible artifacts.

Differential Angular Imaging for Material Recognition

no code implementations CVPR 2017 Jia Xue, Hang Zhang, Kristin Dana, Ko Nishino

We realize this by developing a framework for differential angular imaging, where small angular variations in image capture provide an enhanced appearance representation and significant recognition improvement.

Material Recognition

Deep TEN: Texture Encoding Network

12 code implementations CVPR 2017 Hang Zhang, Jia Xue, Kristin Dana

The representation is orderless and therefore is particularly useful for material and texture recognition.

Dictionary Learning Material Recognition

Multi-style Generative Network for Real-time Transfer

6 code implementations20 Mar 2017 Hang Zhang, Kristin Dana

Despite the rapid progress in style transfer, existing approaches using feed-forward generative network for multi-style or arbitrary-style transfer are usually compromised of image quality and model flexibility.

Style Transfer

Context Encoding for Semantic Segmentation

12 code implementations CVPR 2018 Hang Zhang, Kristin Dana, Jianping Shi, Zhongyue Zhang, Xiaogang Wang, Ambrish Tyagi, Amit Agrawal

In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps.

Image Classification Segmentation +2

Deep Texture Manifold for Ground Terrain Recognition

1 code implementation CVPR 2018 Jia Xue, Hang Zhang, Kristin Dana

The GTOS database (comprised of over 30, 000 images of 40 classes of ground terrain in outdoor scenes) enables supervised recognition.

Material Segmentation of Multi-View Satellite Imagery

no code implementations17 Apr 2019 Matthew Purri, Jia Xue, Kristin Dana, Matthew Leotta, Dan Lipsa, Zhixin Li, Bo Xu, Jie Shan

The residuals are computed by differencing the sparse-sampled reflectance function with a dictionary of pre-defined dense-sampled reflectance functions.

Material Recognition Segmentation +1

Finding Berries: Segmentation and Counting of Cranberries using Point Supervision and Shape Priors

no code implementations18 Apr 2020 Peri Akiva, Kristin Dana, Peter Oudemans, Michael Mars

Precision agriculture has become a key factor for increasing crop yields by providing essential information to decision makers.

Segmentation

Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images

1 code implementation ECCV 2020 Matthew Purri, Kristin Dana

The connection between visual input and tactile sensing is critical for object manipulation tasks such as grasping and pushing.

Friction Neural Architecture Search

Feudal Steering: Hierarchical Learning for Steering Angle Prediction

no code implementations11 Jun 2020 Faith Johnson, Kristin Dana

The steering angle at a particular time instance is the worker network output which is regulated by the manager's high level task.

Hierarchical Reinforcement Learning Self-Driving Cars

Angular Luminance for Material Segmentation

no code implementations22 Sep 2020 Jia Xue, Matthew Purri, Kristin Dana

We demonstrate the increased performance of AngLNet over prior state-of-the-art in material segmentation from satellite imagery.

Material Recognition Object Recognition +2

H2O-Net: Self-Supervised Flood Segmentation via Adversarial Domain Adaptation and Label Refinement

no code implementations11 Oct 2020 Peri Akiva, Matthew Purri, Kristin Dana, Beth Tellman, Tyler Anderson

We demonstrate that H2O-Net outperforms the state-of-the-art semantic segmentation methods on satellite imagery by 10% and 12% pixel accuracy and mIoU respectively for the task of flood segmentation.

Domain Adaptation Segmentation +1

AI on the Bog: Monitoring and Evaluating Cranberry Crop Risk

no code implementations8 Nov 2020 Peri Akiva, Benjamin Planche, Aditi Roy, Kristin Dana, Peter Oudemans, Michael Mars

Toward this goal, we propose two main deep learning-based modules for: 1) cranberry fruit segmentation to delineate the exact fruit regions in the cranberry field image that are exposed to sun, 2) prediction of cloud coverage conditions and sun irradiance to estimate the inner temperature of exposed cranberries.

Towards Single Stage Weakly Supervised Semantic Segmentation

1 code implementation18 Jun 2021 Peri Akiva, Kristin Dana

The costly process of obtaining semantic segmentation labels has driven research towards weakly supervised semantic segmentation (WSSS) methods, using only image-level, point, or box labels.

Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation

Shape From Sky: Polarimetric Normal Recovery Under the Sky

no code implementations CVPR 2021 Tomoki Ichikawa, Matthew Purri, Ryo Kawahara, Shohei Nobuhara, Kristin Dana, Ko Nishino

That is, we show that the unique polarization pattern encoded in the polarimetric appearance of an object captured under the sky can be decoded to reveal the surface normal at each pixel.

Navigate

Vi-Fi: Associating Moving Subjects across Vision and Wireless Sensors

1 code implementation ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN) 2022 Hansi Liu, Abrar Alali, Mohamed Ibrahim, Bryan Bo Cao, Nicholas Meegan, Hongyu Li, Marco Gruteser, Shubham Jain, Kristin Dana, Ashwin Ashok, Bin Cheng, HongSheng Lu

In this paper, we present Vi-Fi, a multi-modal system that leverages a user’s smartphone WiFi Fine Timing Measurements (FTM) and inertial measurement unit (IMU) sensor data to associate the user detected on a camera footage with their corresponding smartphone identifier (e. g. WiFi MAC address).

Graph Matching Multimodal Association

ViFiCon: Vision and Wireless Association Via Self-Supervised Contrastive Learning

no code implementations11 Oct 2022 Nicholas Meegan, Hansi Liu, Bryan Cao, Abrar Alali, Kristin Dana, Marco Gruteser, Shubham Jain, Ashwin Ashok

We introduce ViFiCon, a self-supervised contrastive learning scheme which uses synchronized information across vision and wireless modalities to perform cross-modal association.

Contrastive Learning Region Proposal

ViFi-Loc: Multi-modal Pedestrian Localization using GAN with Camera-Phone Correspondences

no code implementations22 Nov 2022 Hansi Liu, Kristin Dana, Marco Gruteser, HongSheng Lu

During inference, it generates refined position estimations based only on pedestrians' phone data that consists of GPS, IMU and FTM.

Generative Adversarial Network Self-Learning +1

Learning a Pedestrian Social Behavior Dictionary

no code implementations2 Dec 2022 Faith Johnson, Kristin Dana

Understanding pedestrian behavior patterns is a key component to building autonomous agents that can navigate among humans.

Dictionary Learning Navigate +1

Vision-Based Cranberry Crop Ripening Assessment

no code implementations31 Aug 2023 Faith Johnson, Jack Lowry, Kristin Dana, Peter Oudemans

Agricultural domains are being transformed by recent advances in AI and computer vision that support quantitative visual evaluation.

Time Series

ViFiT: Reconstructing Vision Trajectories from IMU and Wi-Fi Fine Time Measurements

1 code implementation MobiCom ISACom 2023 Bryan Bo Cao, Abrar Alali, Hansi Liu, Nicholas Meegan, Marco Gruteser, Kristin Dana, Ashwin Ashok, Shubham Jain

Tracking subjects in videos is one of the most widely used functions in camera-based IoT applications such as security surveillance, smart city traffic safety enhancement, vehicle to pedestrian communication and so on.

Hierarchical Reinforcement Learning for Temporal Pattern Prediction

no code implementations9 Oct 2023 Faith Johnson, Kristin Dana

In this work, we explore the use of hierarchical reinforcement learning (HRL) for the task of temporal sequence prediction.

Hierarchical Reinforcement Learning reinforcement-learning

Feudal Networks for Visual Navigation

no code implementations19 Feb 2024 Faith Johnson, Bryan Bo Cao, Kristin Dana, Shubham Jain, Ashwin Ashok

We introduce a new approach to visual navigation using feudal learning, which employs a hierarchical structure consisting of a worker agent, a mid-level manager, and a high-level manager.

Navigate Visual Navigation

A Landmark-Aware Visual Navigation Dataset

no code implementations22 Feb 2024 Faith Johnson, Bryan Bo Cao, Kristin Dana, Shubham Jain, Ashwin Ashok

However, recent advancements in the visual navigation field face challenges due to the lack of human datasets in the real world for efficient supervised representation learning of the environments.

Representation Learning Visual Navigation

Cannot find the paper you are looking for? You can Submit a new open access paper.