Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.03916 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911078057771008 |
|---|---|
| author | Jiang, Yifan Xue, Yibo Kang, Yukun Zheng, Pin Peng, Jian Wu, Feiran Xu, Changliang |
| author_facet | Jiang, Yifan Xue, Yibo Kang, Yukun Zheng, Pin Peng, Jian Wu, Feiran Xu, Changliang |
| contents | Slide animations, such as fade-in, fly-in, and wipe, are critical for audience engagement, efficient information delivery, and vivid visual expression. However, most AI-driven slide-generation tools still lack native animation support, and existing vision-language models (VLMs) struggle with animation tasks due to the absence of public datasets and limited temporal-reasoning capabilities. To address this gap, we release the first public dataset for slide-animation modeling: 12,000 triplets of natural-language descriptions, animation JSON files, and rendered videos, collectively covering every built-in PowerPoint effect. Using this resource, we fine-tune Qwen-2.5-VL-7B with Low-Rank Adaptation (LoRA) and achieve consistent improvements over GPT-4.1 and Gemini-2.5-Pro in BLEU-4, ROUGE-L, SPICE, and our Coverage-Order-Detail Assessment (CODA) metric, which evaluates action coverage, temporal order, and detail fidelity. On a manually created test set of slides, the LoRA model increases BLEU-4 by around 60%, ROUGE-L by 30%, and shows significant improvements in CODA-detail. This demonstrates that low-rank adaptation enables reliable temporal reasoning and generalization beyond synthetic data. Overall, our dataset, LoRA-enhanced model, and CODA metric provide a rigorous benchmark and foundation for future research on VLM-based dynamic slide generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_03916 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Animation Needs Attention: A Holistic Approach to Slides Animation Comprehension with Visual-Language Models Jiang, Yifan Xue, Yibo Kang, Yukun Zheng, Pin Peng, Jian Wu, Feiran Xu, Changliang Artificial Intelligence Computer Vision and Pattern Recognition 68T01 Slide animations, such as fade-in, fly-in, and wipe, are critical for audience engagement, efficient information delivery, and vivid visual expression. However, most AI-driven slide-generation tools still lack native animation support, and existing vision-language models (VLMs) struggle with animation tasks due to the absence of public datasets and limited temporal-reasoning capabilities. To address this gap, we release the first public dataset for slide-animation modeling: 12,000 triplets of natural-language descriptions, animation JSON files, and rendered videos, collectively covering every built-in PowerPoint effect. Using this resource, we fine-tune Qwen-2.5-VL-7B with Low-Rank Adaptation (LoRA) and achieve consistent improvements over GPT-4.1 and Gemini-2.5-Pro in BLEU-4, ROUGE-L, SPICE, and our Coverage-Order-Detail Assessment (CODA) metric, which evaluates action coverage, temporal order, and detail fidelity. On a manually created test set of slides, the LoRA model increases BLEU-4 by around 60%, ROUGE-L by 30%, and shows significant improvements in CODA-detail. This demonstrates that low-rank adaptation enables reliable temporal reasoning and generalization beyond synthetic data. Overall, our dataset, LoRA-enhanced model, and CODA metric provide a rigorous benchmark and foundation for future research on VLM-based dynamic slide generation. |
| title | Animation Needs Attention: A Holistic Approach to Slides Animation Comprehension with Visual-Language Models |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition 68T01 |
| url | https://arxiv.org/abs/2507.03916 |