Papers by Hernán Maina
Selectively Answering Visual Questions (2024.findings-acl)
Copied to clipboard
| Challenge: | Large multi-modal models (LMMs) are capable of visual question answering (VQA) with unprecedented accuracy. |
| Approach: | They propose a calibration score that can be used to quantify uncertainty in visual question answering models. |
| Outcome: | The proposed calibration score is better calibrated than in text-only models for in-context learning. |
Region under Discussion for visual dialog (2021.emnlp-main)
Copied to clipboard
| Challenge: | Visual Dialog is assumed to require the dialog history to generate correct responses during a dialog. |
| Approach: | They propose an interpretable representation that visually grounds dialog history by constraining the image’s spatial features according to a semantic representation inspired by Question under Discussion. |
| Outcome: | The proposed representation constrains the image’s spatial features according to a semantic representation of the history inspired by the information structure notion of Question under Discussion. |
What kinds of errors do reference resolution models make and what can we learn from them? (2022.findings-naacl)
Copied to clipboard
| Challenge: | Referring resolution is the task of identifying the referent of a natural language expression. |
| Approach: | They propose a model that restores weakening of the spatial natural constraints on referring expressions by evaluating their performance on different datasets. |
| Outcome: | The proposed model shows improved performance on the most challenging kinds of referring expressions on different datasets. |