TADACap: Time-series Adaptive Domain-Aware Captioning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916691839025152 |
|---|---|
| author | Fons, Elizabeth Kaur, Rachneet Zeng, Zhen Palande, Soham Balch, Tucker Vyetrenko, Svitlana Veloso, Manuela |
| author_facet | Fons, Elizabeth Kaur, Rachneet Zeng, Zhen Palande, Soham Balch, Tucker Vyetrenko, Svitlana Veloso, Manuela |
| contents | While image captioning has gained significant attention, the potential of captioning time-series images, prevalent in areas like finance and healthcare, remains largely untapped. Existing time-series captioning methods typically offer generic, domain-agnostic descriptions of time-series shapes and struggle to adapt to new domains without substantial retraining. To address these limitations, we introduce TADACap, a retrieval-based framework to generate domain-aware captions for time-series images, capable of adapting to new domains without retraining. Building on TADACap, we propose a novel retrieval strategy that retrieves diverse image-caption pairs from a target domain database, namely TADACap-diverse. We benchmarked TADACap-diverse against state-of-the-art methods and ablation variants. TADACap-diverse demonstrates comparable semantic accuracy while requiring significantly less annotation effort. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11441 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TADACap: Time-series Adaptive Domain-Aware Captioning Fons, Elizabeth Kaur, Rachneet Zeng, Zhen Palande, Soham Balch, Tucker Vyetrenko, Svitlana Veloso, Manuela Computer Vision and Pattern Recognition Computation and Language While image captioning has gained significant attention, the potential of captioning time-series images, prevalent in areas like finance and healthcare, remains largely untapped. Existing time-series captioning methods typically offer generic, domain-agnostic descriptions of time-series shapes and struggle to adapt to new domains without substantial retraining. To address these limitations, we introduce TADACap, a retrieval-based framework to generate domain-aware captions for time-series images, capable of adapting to new domains without retraining. Building on TADACap, we propose a novel retrieval strategy that retrieves diverse image-caption pairs from a target domain database, namely TADACap-diverse. We benchmarked TADACap-diverse against state-of-the-art methods and ablation variants. TADACap-diverse demonstrates comparable semantic accuracy while requiring significantly less annotation effort. |
| title | TADACap: Time-series Adaptive Domain-Aware Captioning |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2504.11441 |