Generative Timelines for Instructed Visual Assembly
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929597729210368 |
|---|---|
| author | Pardo, Alejandro Wang, Jui-Hsien Ghanem, Bernard Sivic, Josef Russell, Bryan Heilbron, Fabian Caba |
| author_facet | Pardo, Alejandro Wang, Jui-Hsien Ghanem, Bernard Sivic, Josef Russell, Bryan Heilbron, Fabian Caba |
| contents | The objective of this work is to manipulate visual timelines (e.g. a video) through natural language instructions, making complex timeline editing tasks accessible to non-expert or potentially even disabled users. We call this task Instructed visual assembly. This task is challenging as it requires (i) identifying relevant visual content in the input timeline as well as retrieving relevant visual content in a given input (video) collection, (ii) understanding the input natural language instruction, and (iii) performing the desired edits of the input visual timeline to produce an output timeline. To address these challenges, we propose the Timeline Assembler, a generative model trained to perform instructed visual assembly tasks. The contributions of this work are three-fold. First, we develop a large multimodal language model, which is designed to process visual content, compactly represent timelines and accurately interpret timeline editing instructions. Second, we introduce a novel method for automatically generating datasets for visual assembly tasks, enabling efficient training of our model without the need for human-labeled data. Third, we validate our approach by creating two novel datasets for image and video assembly, demonstrating that the Timeline Assembler substantially outperforms established baseline models, including the recent GPT-4o, in accurately executing complex assembly instructions across various real-world inspired scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_12293 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generative Timelines for Instructed Visual Assembly Pardo, Alejandro Wang, Jui-Hsien Ghanem, Bernard Sivic, Josef Russell, Bryan Heilbron, Fabian Caba Computer Vision and Pattern Recognition Human-Computer Interaction Multimedia The objective of this work is to manipulate visual timelines (e.g. a video) through natural language instructions, making complex timeline editing tasks accessible to non-expert or potentially even disabled users. We call this task Instructed visual assembly. This task is challenging as it requires (i) identifying relevant visual content in the input timeline as well as retrieving relevant visual content in a given input (video) collection, (ii) understanding the input natural language instruction, and (iii) performing the desired edits of the input visual timeline to produce an output timeline. To address these challenges, we propose the Timeline Assembler, a generative model trained to perform instructed visual assembly tasks. The contributions of this work are three-fold. First, we develop a large multimodal language model, which is designed to process visual content, compactly represent timelines and accurately interpret timeline editing instructions. Second, we introduce a novel method for automatically generating datasets for visual assembly tasks, enabling efficient training of our model without the need for human-labeled data. Third, we validate our approach by creating two novel datasets for image and video assembly, demonstrating that the Timeline Assembler substantially outperforms established baseline models, including the recent GPT-4o, in accurately executing complex assembly instructions across various real-world inspired scenarios. |
| title | Generative Timelines for Instructed Visual Assembly |
| topic | Computer Vision and Pattern Recognition Human-Computer Interaction Multimedia |
| url | https://arxiv.org/abs/2411.12293 |