ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915324374286336 |
|---|---|
| author | Maina, Hernán Ivetta, Guido Stuto, Mateo Lione Eisenschlos, Julian Martin Sánchez, Jorge Benotti, Luciana |
| author_facet | Maina, Hernán Ivetta, Guido Stuto, Mateo Lione Eisenschlos, Julian Martin Sánchez, Jorge Benotti, Luciana |
| contents | Visually impaired people could benefit from Visual Question Answering (VQA) systems to interpret text in their surroundings. However, current models often struggle with recognizing text in the photos taken by this population. Through in-depth interviews with visually impaired individuals, we identified common framing conventions that frequently result in misaligned text. Existing VQA benchmarks primarily feature well-oriented text captured by sighted users, under-representing these challenges. To address this gap, we introduce ROtated SAmpling (ROSA), a decoding strategy that enhances VQA performance in text-rich images with incorrectly oriented text. ROSA outperforms Greedy decoding by 11.7 absolute points in the best-performing model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03665 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling Maina, Hernán Ivetta, Guido Stuto, Mateo Lione Eisenschlos, Julian Martin Sánchez, Jorge Benotti, Luciana Computation and Language Computer Vision and Pattern Recognition Visually impaired people could benefit from Visual Question Answering (VQA) systems to interpret text in their surroundings. However, current models often struggle with recognizing text in the photos taken by this population. Through in-depth interviews with visually impaired individuals, we identified common framing conventions that frequently result in misaligned text. Existing VQA benchmarks primarily feature well-oriented text captured by sighted users, under-representing these challenges. To address this gap, we introduce ROtated SAmpling (ROSA), a decoding strategy that enhances VQA performance in text-rich images with incorrectly oriented text. ROSA outperforms Greedy decoding by 11.7 absolute points in the best-performing model. |
| title | ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling |
| topic | Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.03665 |