Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929422049738752 |
|---|---|
| author | Mao, Shunqi Zhang, Chaoyi Su, Hang Song, Hwanjun Shalyminov, Igor Cai, Weidong |
| author_facet | Mao, Shunqi Zhang, Chaoyi Su, Hang Song, Hwanjun Shalyminov, Igor Cai, Weidong |
| contents | Contextualized Image Captioning (CIC) evolves traditional image captioning into a more complex domain, necessitating the ability for multimodal reasoning. It aims to generate image captions given specific contextual information. This paper further introduces a novel domain of Controllable Contextualized Image Captioning (Ctrl-CIC). Unlike CIC, which solely relies on broad context, Ctrl-CIC accentuates a user-defined highlight, compelling the model to tailor captions that resonate with the highlighted aspects of the context. We present two approaches, Prompting-based Controller (P-Ctrl) and Recalibration-based Controller (R-Ctrl), to generate focused captions. P-Ctrl conditions the model generation on highlight by prepending captions with highlight-driven prefixes, whereas R-Ctrl tunes the model to selectively recalibrate the encoder embeddings for highlighted tokens. Additionally, we design a GPT-4V empowered evaluator to assess the quality of the controlled captions alongside standard assessment methods. Extensive experimental results demonstrate the efficient and effective controllability of our method, charting a new direction in achieving user-adaptive image captioning. Code is available at https://github.com/ShunqiM/Ctrl-CIC . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11449 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights Mao, Shunqi Zhang, Chaoyi Su, Hang Song, Hwanjun Shalyminov, Igor Cai, Weidong Computer Vision and Pattern Recognition Artificial Intelligence Contextualized Image Captioning (CIC) evolves traditional image captioning into a more complex domain, necessitating the ability for multimodal reasoning. It aims to generate image captions given specific contextual information. This paper further introduces a novel domain of Controllable Contextualized Image Captioning (Ctrl-CIC). Unlike CIC, which solely relies on broad context, Ctrl-CIC accentuates a user-defined highlight, compelling the model to tailor captions that resonate with the highlighted aspects of the context. We present two approaches, Prompting-based Controller (P-Ctrl) and Recalibration-based Controller (R-Ctrl), to generate focused captions. P-Ctrl conditions the model generation on highlight by prepending captions with highlight-driven prefixes, whereas R-Ctrl tunes the model to selectively recalibrate the encoder embeddings for highlighted tokens. Additionally, we design a GPT-4V empowered evaluator to assess the quality of the controlled captions alongside standard assessment methods. Extensive experimental results demonstrate the efficient and effective controllability of our method, charting a new direction in achieving user-adaptive image captioning. Code is available at https://github.com/ShunqiM/Ctrl-CIC . |
| title | Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.11449 |