Search Results - "Van Horn, Grant"

Perspectives in machine learning for wildlife conservation by Tuia, Devis, Kellenberger, Benjamin, Beery, Sara, Costelloe, Blair R., Zuffi, Silvia, Risse, Benjamin, Mathis, Alexander, Mathis, Mackenzie W., van Langevelde, Frank, Burghardt, Tilo, Kays, Roland, Klinck, Holger, Wikelski, Martin, Couzin, Iain D., van Horn, Grant, Crofoot, Margaret C., Stewart, Charles V., Berger-Wolf, Tanya

“…Inexpensive and accessible sensors are accelerating data acquisition in animal ecology. These technologies hold great potential for large-scale ecological…”
Get full text

The iNaturalist Species Classification and Detection Dataset by Van Horn, Grant, Mac Aodha, Oisin, Song, Yang, Cui, Yin, Sun, Chen, Shepard, Alex, Adam, Hartwig, Perona, Pietro, Belongie, Serge

“…Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories. In contrast, the natural…”
Get full text

Nighthawk: Acoustic monitoring of nocturnal bird migration in the Americas by Van Doren, Benjamin M., Farnsworth, Andrew, Stone, Kate, Osterhaus, Dylan M., Drucker, Jacob, Van Horn, Grant

“…Animal migration is one of nature's most spectacular phenomena, but migratory animals and their journeys are imperilled across the globe. Migratory birds are…”
Get full text

Lean Crowdsourcing: Combining Humans and Machines in an Online System by Branson, Steve, Van Horn, Grant, Perona, Pietro

“…We introduce a method to greatly reduce the amount of redundant annotations required when crowdsourcing annotations such as bounding boxes, parts, and class…”
Get full text

Similarity Comparisons for Interactive Fine-Grained Categorization by Wah, Catherine, Van Horn, Grant, Branson, Steve, Maji, Subhransu, Perona, Pietro, Belongie, Serge

“…Current human-in-the-loop fine-grained visual categorization systems depend on a predefined vocabulary of attributes and parts, usually determined by experts…”
Get full text

Lean Multiclass Crowdsourcing by Horn, Grant Van, Branson, Steve, Loarie, Scott, Belongie, Serge, Perona, Pietro

“…We introduce a method for efficiently crowdsourcing multiclass annotations in challenging, real world image datasets. Our method is designed to minimize the…”
Get full text

Benchmarking Representation Learning for Natural World Image Collections by Van Horn, Grant, Cole, Elijah, Beery, Sara, Wilber, Kimberly, Belongie, Serge, MacAodha, Oisin

“…Recent progress in self-supervised learning has resulted in models that are capable of extracting rich representations from image collections without requiring…”
Get full text

Glass transition behavior of poly(methyl methacrylate) in compressed carbon dioxide revisited – New perspectives by Sarver, Joseph A., van Horn, Grant A., Kiran, Erdogan

“…•Glass transition behavior of poly(methyl methacrylate) in carbon dioxide.•Examination of molecular weight effects on glass transition behavior of poly(methyl…”
Get full text

Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection by Van Horn, Grant, Branson, Steve, Farrell, Ryan, Haber, Scott, Barry, Jessie, Ipeirotis, Panos, Perona, Pietro, Belongie, Serge

“…We introduce tools and methodologies to collect high quality, large scale fine-grained computer vision datasets using citizen scientists - crowd annotators who…”
Get full text

Thermal transitions and foaming of a rubbery polymer, poly(ethylene-co-vinyl acetate-co-carbon monoxide), in carbon dioxide: Temperature scaling as a new approach for rational selection of foaming conditions by Sarver, Joseph A., Rhee, Dawn D., Van Horn, Grant A., Adams, Jake F., Kiran, Erdogan

“…The foaming of a thermoplastic elastomer, poly(ethylene-co-vinyl acetate-co-carbon monoxide) with varying copolymer compositions was explored using CO2…”
Get full text

The Ignorant Led by the Blind: A Hybrid Human–Machine Vision System for Fine-Grained Categorization by Branson, Steve, Van Horn, Grant, Wah, Catherine, Perona, Pietro, Belongie, Serge

“…We present a visual recognition system for fine-grained visual categorization. The system is composed of a human and a machine working together and combines…”
Get full text

Citizen science photographs indicate different timing and location use of migrating adult and juvenile Whimbrels by Hines, Chance, Duval, Laura, Watts, Bryan D., Van Horn, Grant, Miller, Eliot

“…It is imperative to identify factors that influence population trends for declining species, but demographic parameters can be especially challenging to…”
Get full text

Seeing biodiversity: perspectives in machine learning for wildlife conservation by Tuia, Devis, Kellenberger, Benjamin, Beery, Sara, Costelloe, Blair R, Zuffi, Silvia, Risse, Benjamin, Mathis, Alexander, Mathis, Mackenzie W, van Langevelde, Frank, Burghardt, Tilo, Kays, Roland, Klinck, Holger, Wikelski, Martin, Couzin, Iain D, van Horn, Grant, Crofoot, Margaret C, Stewart, Charles V, Berger-Wolf, Tanya

“…Data acquisition in animal ecology is rapidly accelerating due to inexpensive and accessible sensors such as smartphones, drones, satellites, audio recorders…”
Get full text

Towards a Visipedia: Combining Computer Vision and Communities of Experts by Van Horn, Grant

“…Motivated by the idea of a Visipedia, where users can search and explore by image, this thesis presents tools and techniques for empowering expert communities…”
Get full text

The Ignorant Led by the Blind: A Hybrid Human-Machine Vision System for Fine-Grained Categorization: Active and Interactive Methods in Computer Vision by BRANSON, Steve, VAN HORN, Grant, WAH, Catherine, PERONA, Pietro, BELONGIE, Serge

Get full text

Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions by Saha, Oindrila, Van Horn, Grant, Maji, Subhransu

“…The zero-shot performance of existing vision-language models (VLMs) such as CLIP [29] is limited by the availability of large-scale, aligned image and text…”
Get full text

Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions by Saha, Oindrila, Van Horn, Grant, Maji, Subhransu

“…The zero-shot performance of existing vision-language models (VLMs) such as CLIP is limited by the availability of large-scale, aligned image and text datasets…”
Get full text

Human-in-the-Loop Visual Re-ID for Population Size Estimation by Perez, Gustavo, Sheldon, Daniel, Van Horn, Grant, Maji, Subhransu

“…Computer vision-based re-identification (Re-ID) systems are increasingly being deployed for estimating population size in large image collections. However, the…”
Get full text

Active Learning-Based Species Range Estimation by Lange, Christian, Cole, Elijah, Van Horn, Grant, Mac Aodha, Oisin

“…We propose a new active learning approach for efficiently estimating the geographic range of a species from a limited number of on the ground observations. We…”
Get full text

Towards Scalable and Accurate Fine-Grained Categorization by Van Horn, Grant Richard

“…In this work I contribute two solutions towards increasing the utility and performance of fine-grained categorization. First, I present a software…”
Get full text