Script-to-Slide Grounding: Grounding Script Sentences to Slide Objects for Automatic Instructional Video Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914404375724032 |
|---|---|
| author | Suzuki, Rena Kikuchi, Masato Ozono, Tadachika |
| author_facet | Suzuki, Rena Kikuchi, Masato Ozono, Tadachika |
| contents | While slide-based videos augmented with visual effects are widely utilized in education and research presentations, the video editing process -- particularly applying visual effects to ground spoken content to slide objects -- remains highly labor-intensive. This study aims to develop a system that automatically generates such instructional videos from slides and corresponding scripts. As a foundational step, this paper proposes and formulates Script-to-Slide Grounding (S2SG), defined as the task of grounding script sentences to their corresponding slide objects. Furthermore, as an initial step, we propose ``Text-S2SG,'' a method that utilizes a large language model (LLM) to perform this grounding task for text objects. Our experiments demonstrate that the proposed method achieves high performance (F1-score: 0.924). The contribution of this work is the formalization of a previously implicit slide-based video editing process into a computable task, thereby paving the way for its automation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16931 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Script-to-Slide Grounding: Grounding Script Sentences to Slide Objects for Automatic Instructional Video Generation Suzuki, Rena Kikuchi, Masato Ozono, Tadachika Computer Vision and Pattern Recognition Artificial Intelligence While slide-based videos augmented with visual effects are widely utilized in education and research presentations, the video editing process -- particularly applying visual effects to ground spoken content to slide objects -- remains highly labor-intensive. This study aims to develop a system that automatically generates such instructional videos from slides and corresponding scripts. As a foundational step, this paper proposes and formulates Script-to-Slide Grounding (S2SG), defined as the task of grounding script sentences to their corresponding slide objects. Furthermore, as an initial step, we propose ``Text-S2SG,'' a method that utilizes a large language model (LLM) to perform this grounding task for text objects. Our experiments demonstrate that the proposed method achieves high performance (F1-score: 0.924). The contribution of this work is the formalization of a previously implicit slide-based video editing process into a computable task, thereby paving the way for its automation. |
| title | Script-to-Slide Grounding: Grounding Script Sentences to Slide Objects for Automatic Instructional Video Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.16931 |