Search Results for author:
Found 30 papers, 9 papers with code
Agtech Framework for Cranberry-Ripening Analysis Using Vision Foundation Models
For interpretability, we create a 2D manifold of cranberry appearance by using a UMAP dimensionality reduction on ViT features.
Memory Proxy Maps for Visual Navigation
Key to our approach is a memory proxy map (MPM), an intermediate representation of the environment learned in a self-supervised manner by the high-level manager agent that serves as a simplified memory, approximating what the agent has seen.
A Landmark-Aware Visual Navigation Dataset
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.
Feudal Networks for Visual Navigation
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.
Hierarchical Reinforcement Learning for Temporal Pattern Prediction
In this work, we explore the use of hierarchical reinforcement learning (HRL) for the task of temporal sequence prediction.
ViFiT: Reconstructing Vision Trajectories from IMU and Wi-Fi Fine Time Measurements
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.
Vision-Based Cranberry Crop Ripening Assessment
Agricultural domains are being transformed by recent advances in AI and computer vision that support quantitative visual evaluation.
Self-Supervised Object Detection from Egocentric Videos
Understanding the visual world from the perspective of humans (egocentric) has been a long-standing challenge in computer vision.
Learning a Pedestrian Social Behavior Dictionary
Understanding pedestrian behavior patterns is a key component to building autonomous agents that can navigate among humans.
ViFi-Loc: Multi-modal Pedestrian Localization using GAN with Camera-Phone Correspondences
During inference, it generates refined position estimations based only on pedestrians' phone data that consists of GPS, IMU and FTM.
ViFiCon: Vision and Wireless Association Via Self-Supervised Contrastive Learning
We introduce ViFiCon, a self-supervised contrastive learning scheme which uses synchronized information across vision and wireless modalities to perform cross-modal association.
ViTag: Online WiFi Fine Time Measurements Aided Vision-Motion Identity Association in Multi-person Environments
ViTag associates a sequence of vision tracker generated bounding boxes with Inertial Measurement Unit (IMU) data and Wi-Fi Fine Time Measurements (FTM) from smartphones.
Vi-Fi: Associating Moving Subjects across Vision and Wireless Sensors
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).
Shape From Sky: Polarimetric Normal Recovery Under the Sky
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.
Towards Single Stage Weakly Supervised Semantic Segmentation
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
AI on the Bog: Monitoring and Evaluating Cranberry Crop Risk
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.
H2O-Net: Self-Supervised Flood Segmentation via Adversarial Domain Adaptation and Label Refinement
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.
Angular Luminance for Material Segmentation
We demonstrate the increased performance of AngLNet over prior state-of-the-art in material segmentation from satellite imagery.
Feudal Steering: Hierarchical Learning for Steering Angle Prediction
The steering angle at a particular time instance is the worker network output which is regulated by the manager's high level task.
Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images
The connection between visual input and tactile sensing is critical for object manipulation tasks such as grasping and pushing.
Finding Berries: Segmentation and Counting of Cranberries using Point Supervision and Shape Priors
Precision agriculture has become a key factor for increasing crop yields by providing essential information to decision makers.
Material Segmentation of Multi-View Satellite Imagery
The residuals are computed by differencing the sparse-sampled reflectance function with a dictionary of pre-defined dense-sampled reflectance functions.
Deep Texture Manifold for Ground Terrain Recognition
The GTOS database (comprised of over 30, 000 images of 40 classes of ground terrain in outdoor scenes) enables supervised recognition.
Context Encoding for Semantic Segmentation
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.
Ranked #7 on
Semantic Segmentation
on PASCAL VOC 2012 test
Multi-style Generative Network for Real-time Transfer
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.
Deep TEN: Texture Encoding Network
The representation is orderless and therefore is particularly useful for material and texture recognition.
Differential Angular Imaging for Material Recognition
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.
Reading Between the Pixels: Photographic Steganography for Camera Display Messaging
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.
Friction from Reflectance: Deep Reflectance Codes for Predicting Physical Surface Properties from One-Shot In-Field Reflectance
In this work, we address the question of what reflectance can reveal about materials in an efficient manner.
Reflectance Hashing for Material Recognition
Reflectance offers a unique signature of the material but is challenging to measure and use for recognizing materials due to its high-dimensionality.
