Please use this identifier to cite or link to this item:
http://arks.princeton.edu/ark:/88435/dsp01pz50gz967| Title: | Moving from Recognition to Reasoning in Image Captioning |
| Authors: | Feng, Berthy |
| Advisors: | Russakovsky, Olga Narasimhan, Karthik |
| Department: | Computer Science |
| Certificate Program: | Center for Statistics and Machine Learning |
| Class Year: | 2019 |
| Abstract: | Image captioning is an artificial intelligence (AI) task at the intersection of vision and language. Current approaches to the task are recognition-based, leading to models that struggle to reason about image content and context. We explore the current state of image captioning and offer solutions for advancing the task from recognition to reasoning, specifically through the use of unpaired training data and evaluation based on a novel discriminativeness metric. |
| URI: | http://arks.princeton.edu/ark:/88435/dsp01pz50gz967 |
| Type of Material: | Princeton University Senior Theses |
| Language: | en |
| Appears in Collections: | Computer Science, 1988-2020 |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| FENG-BERTHY-THESIS.pdf | 2.36 MB | Adobe PDF | Request a copy |
Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.