Abby Stylianou
YOU?
Author Swipe
View article: New Roots for Restoration: Building a foundation for interdisciplinary work in plant organismal biology and ecology to advance restoration in natural and agricultural ecosystems
New Roots for Restoration: Building a foundation for interdisciplinary work in plant organismal biology and ecology to advance restoration in natural and agricultural ecosystems Open
Societal Impact Statement Soils are globally degraded due in part to conventional agriculture and wildland conversion. To address the global challenge of soil degradation, we formed an interdisciplinary, cross‐institutional collaborative r…
View article: ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval
ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval Open
Composed image retrieval (CIR) is the task of retrieving a target image specified by a query image and a relative text that describes a semantic modification to the query image. Existing methods in CIR struggle to accurately represent the …
View article: QuARI: Query Adaptive Retrieval Improvement
QuARI: Query Adaptive Retrieval Improvement Open
Massive-scale pretraining has made vision-language models increasingly popular for image-to-image and text-to-image retrieval across a broad collection of domains. However, these models do not perform well when used for challenging retriev…
View article: Seed Protein Content Estimation with Bench-Top Hyperspectral Imaging and Attentive Convolutional Neural Network Models
Seed Protein Content Estimation with Bench-Top Hyperspectral Imaging and Attentive Convolutional Neural Network Models Open
Wheat is a globally cultivated cereal crop with substantial protein content present in its seeds. This research aimed to develop robust methods for predicting seed protein concentration in wheat seeds using bench-top hyperspectral imaging …
View article: Design and Evaluation of Camera-Centric Mobile Crowdsourcing Applications
Design and Evaluation of Camera-Centric Mobile Crowdsourcing Applications Open
The data that underlies automated methods in computer vision and machine learning, such as image retrieval and fine-grained recognition, often comes from crowdsourcing. In contexts that rely on the intrinsic motivation of users, we seek to…
View article: OPEN-Augmented Reality GUI for Bioenergy Crop Phenotyping and Precision Agriculture (Donald Danforth Plant Science Center Final Scientific Technical Report)
OPEN-Augmented Reality GUI for Bioenergy Crop Phenotyping and Precision Agriculture (Donald Danforth Plant Science Center Final Scientific Technical Report) Open
The project led by the Donald Danforth Plant Science Center, in collaboration with Arizona State University, George Washington University, and Saint Louis University, has made significant strides in advancing the phenotypic analysis of bio…
View article: Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning
Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning Open
This paper presents a novel approach to Single-Positive Multi-label Learning. In general multi-label learning, a model learns to predict multiple labels or categories for a single input image. This is in contrast with standard multi-class …
View article: Comparing Deep Learning Approaches for Understanding Genotype × Phenotype Interactions in Biomass Sorghum
Comparing Deep Learning Approaches for Understanding Genotype × Phenotype Interactions in Biomass Sorghum Open
We explore the use of deep convolutional neural networks (CNNs) trained on overhead imagery of biomass sorghum to ascertain the relationship between single nucleotide polymorphisms (SNPs), or groups of related SNPs, and the phenotypes they…
View article: Metric Learning for Large Scale Agricultural Phenotyping
Metric Learning for Large Scale Agricultural Phenotyping Open
Earth and Space Science Open Archive This is a preprint and has not been peer reviewed. ESSOAr is a venue for early communication or feedback before peer review. Data may be preliminary.Learn more about preprints preprintOpen AccessYou are…
View article: What Does TERRA-REF’s High Resolution, Multi Sensor Plant Sensing Public Domain Data Offer the Computer Vision Community?
What Does TERRA-REF’s High Resolution, Multi Sensor Plant Sensing Public Domain Data Offer the Computer Vision Community? Open
A core objective of the TERRA-REF project was to generate an open-access reference dataset for the evaluation of sensing technologies to study plants under field conditions. The TERRA-REF program deployed a suite of high-resolution, cuttin…
View article: Data-Driven Artificial Intelligence for Calibration of Hyperspectral Big Data
Data-Driven Artificial Intelligence for Calibration of Hyperspectral Big Data Open
Near-earth hyperspectral big data present both huge opportunities and challenges for spurring developments in agriculture and high-throughput plant phenotyping and breeding. In this article, we present data-driven approaches to address the…
View article: Classification and Visualization of Genotype x Phenotype Interactions in Biomass Sorghum
Classification and Visualization of Genotype x Phenotype Interactions in Biomass Sorghum Open
We introduce a simple approach to understanding the relationship between single nucleotide polymorphisms (SNPs), or groups of related SNPs, and the phenotypes they control. The pipeline involves training deep convolutional neural networks …
View article: The 2021 Hotel-ID to Combat Human Trafficking Competition Dataset
The 2021 Hotel-ID to Combat Human Trafficking Competition Dataset Open
Hotel recognition is an important task for human trafficking investigations since victims are often photographed in hotel rooms. Identifying these hotels is vital to trafficking investigations since they can help track down current and fut…
View article: Multi-resolution Outlier Pooling for Sorghum Classification
Multi-resolution Outlier Pooling for Sorghum Classification Open
Automated high throughput plant phenotyping involves leveraging sensors, such as RGB, thermal and hyperspectral cameras (among others), to make large scale and rapid measurements of the physical properties of plants for the purpose of bett…
View article: Hard negative examples are hard, but useful
Hard negative examples are hard, but useful Open
Triplet loss is an extremely common approach to distance metric learning. Representations of images from the same class are optimized to be mapped closer together in an embedding space than representations of images from different classes.…
View article: TraffickCam: Explainable Image Matching For Sex Trafficking Investigations
TraffickCam: Explainable Image Matching For Sex Trafficking Investigations Open
Investigations of sex trafficking sometimes have access to photographs of victims in hotel rooms. These images directly link victims to places, which can help verify where victims have been trafficked or where traffickers might operate in …
View article: Visualizing How Embeddings Generalize
Visualizing How Embeddings Generalize Open
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many tri…
View article: Hotels-50K: A Global Hotel Recognition Dataset
Hotels-50K: A Global Hotel Recognition Dataset Open
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them…
View article: Improved Embeddings with Easy Positive Triplet Mining
Improved Embeddings with Easy Positive Triplet Mining Open
Deep metric learning seeks to define an embedding where semantically similar images are embedded to nearby locations, and semantically dissimilar images are embedded to distant locations. Substantial work has focused on loss functions and …
View article: Hotels-50K: A Global Hotel Recognition Dataset
Hotels-50K: A Global Hotel Recognition Dataset Open
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them…
View article: Visualizing Deep Similarity Networks
Visualizing Deep Similarity Networks Open
For convolutional neural network models that optimize an image embedding, we propose a method to highlight the regions of images that contribute most to pairwise similarity. This work is a corollary to the visualization tools developed for…
View article: Learning about Large Scale Image Search: Lessons from Global Scale Hotel Recognition to Fight Sex Trafficking
Learning about Large Scale Image Search: Lessons from Global Scale Hotel Recognition to Fight Sex Trafficking Open
Hotel recognition is a sub-domain of scene recognition that involves determining what hotel is seen in a photograph taken in a hotel. The hotel recognition task is a challenging computer vision task due to the properties of hotel rooms, in…
View article: Webcams, Crowdsourcing, and Enhanced Crosswalks: Developing a Novel Method to Analyze Active Transportation
Webcams, Crowdsourcing, and Enhanced Crosswalks: Developing a Novel Method to Analyze Active Transportation Open
The methods employed provide an objective, cost-effective alternative to traditional means of examining the effects of built environment changes on active transportation. The use of webcams to collect active transportation data has applica…