Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.08873 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918239990185984 |
|---|---|
| author | Tan, Jing Jie Mokraoui, Anissa Kwan, Ban-Hoe Ng, Danny Wee-Kiat Hum, Yan-Chai |
| author_facet | Tan, Jing Jie Mokraoui, Anissa Kwan, Ban-Hoe Ng, Danny Wee-Kiat Hum, Yan-Chai |
| contents | Image captioning is essential in many fields including assisting visually impaired individuals, improving content management systems, and enhancing human-computer interaction. However, a recent challenge in this domain is dealing with low-resolution image (LRI). While performance can be improved by using larger models like transformers for encoding, these models are typically heavyweight, demanding significant computational resources and memory, leading to challenges in retraining. To address this, the proposed SOLI (Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning) approach presents a solution specifically designed for lightweight, low-resolution images captioning. It employs a Siamese network architecture to optimize latent embeddings, enhancing the efficiency and accuracy of the image-to-text translation process. By focusing on a dual-pathway neural network structure, SOLI minimizes computational overhead without sacrificing performance, making it an ideal choice for training on resource-constrained scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_08873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning Tan, Jing Jie Mokraoui, Anissa Kwan, Ban-Hoe Ng, Danny Wee-Kiat Hum, Yan-Chai Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction Image captioning is essential in many fields including assisting visually impaired individuals, improving content management systems, and enhancing human-computer interaction. However, a recent challenge in this domain is dealing with low-resolution image (LRI). While performance can be improved by using larger models like transformers for encoding, these models are typically heavyweight, demanding significant computational resources and memory, leading to challenges in retraining. To address this, the proposed SOLI (Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning) approach presents a solution specifically designed for lightweight, low-resolution images captioning. It employs a Siamese network architecture to optimize latent embeddings, enhancing the efficiency and accuracy of the image-to-text translation process. By focusing on a dual-pathway neural network structure, SOLI minimizes computational overhead without sacrificing performance, making it an ideal choice for training on resource-constrained scenarios. |
| title | Siamese-Driven Optimization for Low-Resolution Image Latent Embedding in Image Captioning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2512.08873 |