Acknowledging Focus Ambiguity in Visual Questions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913966709538816 |
|---|---|
| author | Chen, Chongyan Tseng, Yu-Yun Li, Zhuoheng Venkatesh, Anush Gurari, Danna |
| author_facet | Chen, Chongyan Tseng, Yu-Yun Li, Zhuoheng Venkatesh, Anush Gurari, Danna |
| contents | No published work on visual question answering (VQA) accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually grounds each plausible image region a question could refer to when arriving at valid answers. We next analyze and compare our dataset to existing datasets to reveal its unique properties. Finally, we benchmark modern models for two novel tasks related to acknowledging focus ambiguity: recognizing whether a visual question has focus ambiguity and locating all plausible focus regions within the image. Results show that the dataset is challenging for modern models. To facilitate future progress on these tasks, we publicly share the dataset with an evaluation server at https://vizwiz.org/tasks-and-datasets/focus-ambiguity-in-visual-questions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02201 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Acknowledging Focus Ambiguity in Visual Questions Chen, Chongyan Tseng, Yu-Yun Li, Zhuoheng Venkatesh, Anush Gurari, Danna Computer Vision and Pattern Recognition No published work on visual question answering (VQA) accounts for ambiguity regarding where the content described in the question is located in the image. To fill this gap, we introduce VQ-FocusAmbiguity, the first VQA dataset that visually grounds each plausible image region a question could refer to when arriving at valid answers. We next analyze and compare our dataset to existing datasets to reveal its unique properties. Finally, we benchmark modern models for two novel tasks related to acknowledging focus ambiguity: recognizing whether a visual question has focus ambiguity and locating all plausible focus regions within the image. Results show that the dataset is challenging for modern models. To facilitate future progress on these tasks, we publicly share the dataset with an evaluation server at https://vizwiz.org/tasks-and-datasets/focus-ambiguity-in-visual-questions. |
| title | Acknowledging Focus Ambiguity in Visual Questions |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.02201 |