activity
20162024
most citedVisual Question: Predicting If a Crowd Will Agree on the Answer

4 citations · 4 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2024

SPIN: Hierarchical Segmentation with Subpart Granularity in Natural Images

Josh Myers-Dean, Jarek Reynolds, Brian Price +2

Hierarchical segmentation entails creating segmentations at varying levels of granularity. We introduce the first hierarchical semantic segmentation dataset with subpart annotation…

cs.CV2024

Interpreting COVID Lateral Flow Tests' Results with Foundation Models

Stuti Pandey, Josh Myers-Dean, Jarek Reynolds +1

Lateral flow tests (LFTs) enable rapid, low-cost testing for health conditions including Covid, pregnancy, HIV, and malaria. Automated readers of LFT results can yield many benefit…

cs.CV2023

VQA Therapy: Exploring Answer Differences by Visually Grounding Answers

Chongyan Chen, Samreen Anjum, Danna Gurari

Visual question answering is a task of predicting the answer to a question about an image. Given that different people can provide different answers to a visual question, we aim to…

cs.CV2022

VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments

Yu-Yun Tseng, Alexander Bell, Danna Gurari

We introduce a few-shot localization dataset originating from photographers who authentically were trying to learn about the visual content in the images they took. It includes nea…

cs.AI20164 cited

Visual Question: Predicting If a Crowd Will Agree on the Answer

Danna Gurari, Kristen Grauman

Visual question answering (VQA) systems are emerging from a desire to empower users to ask any natural language question about visual content and receive a valid answer in response…