output
20192022
most citedZero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP

113 citations

5 papers

cs.CV2022★ 1 cited

Human Activity Recognition in an Open World

Derek S. Prijatelj, Samuel Grieggs, Jin Huang +6

Managing novelty in perception-based human activity recognition (HAR) is critical in realistic settings to improve task performance over time and ensure solution generalization out…

econ.GN2022★ 28 cited

Agricultural Windfalls and the Seasonality of Political Violence in Africa

David Ubilava, Justin V. Hastings, Kadir Atalay

When the prices of cereal grains rise, social unrest and conflict become likely. In rural areas, the predation motives of perpetrators can explain the positive relationship between…

cs.CV2021★ 113 cited

Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP

Sepideh Esmaeilpour, Bing Liu, Eric Robertson +1

In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier. In testing, the classifier…

cs.CV2021★ 3 cited

Handwriting Recognition with Novelty

Derek S. Prijatelj, Samuel Grieggs, Futoshi Yumoto +2

This paper introduces an agent-centric approach to handle novelty in the visual recognition domain of handwriting recognition (HWR). An ideal transcription agent would rival or sur…

astro-ph.IM2019★ 1 cited

Recreating the OSIRIS-REx Slingshot Manoeuvre from a Network of Ground-Based Sensors

Trent Jansen-Sturgeon, Benjamin A. D. Hartig, Gregory J. Madsen +20

Optical tracking systems typically trade-off between astrometric precision and field-of-view. In this work, we showcase a networked approach to optical tracking using very wide fie…