Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910379859247104 |
|---|---|
| author | Du, Zhicheng Xie, Zhaotian Ying, Huazhang Zhang, Likun Qin, Peiwu |
| author_facet | Du, Zhicheng Xie, Zhaotian Ying, Huazhang Zhang, Likun Qin, Peiwu |
| contents | This study explores the ability of Image Captioning (IC) models to decode masked visual content sourced from diverse datasets. Our findings reveal the IC model's capability to generate captions from masked images, closely resembling the original content. Notably, even in the presence of masks, the model adeptly crafts descriptive textual information that goes beyond what is observable in the original image-generated captions. While the decoding performance of the IC model experiences a decline with an increase in the masked region's area, the model still performs well when important regions of the image are not masked at high coverage. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15876 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content Du, Zhicheng Xie, Zhaotian Ying, Huazhang Zhang, Likun Qin, Peiwu Computer Vision and Pattern Recognition Artificial Intelligence This study explores the ability of Image Captioning (IC) models to decode masked visual content sourced from diverse datasets. Our findings reveal the IC model's capability to generate captions from masked images, closely resembling the original content. Notably, even in the presence of masks, the model adeptly crafts descriptive textual information that goes beyond what is observable in the original image-generated captions. While the decoding performance of the IC model experiences a decline with an increase in the masked region's area, the model still performs well when important regions of the image are not masked at high coverage. |
| title | Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual content |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2403.15876 |