PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912559394717696 |
|---|---|
| author | Hou, Xiaolu Ma, Bing Cheng, Jiaxiang Ren, Xuhua Yu, Kai Li, Wenyue Zheng, Tianxiang Lu, Qinglin |
| author_facet | Hou, Xiaolu Ma, Bing Cheng, Jiaxiang Ren, Xuhua Yu, Kai Li, Wenyue Zheng, Tianxiang Lu, Qinglin |
| contents | With the growing demand for short videos and personalized content, automated Video Log (Vlog) generation has become a key direction in multimodal content creation. Existing methods mostly rely on predefined scripts, lacking dynamism and personal expression. Therefore, there is an urgent need for an automated Vlog generation approach that enables effective multimodal collaboration and high personalization. To this end, we propose PersonaVlog, an automated multimodal stylized Vlog generation framework that can produce personalized Vlogs featuring videos, background music, and inner monologue speech based on a given theme and reference image. Specifically, we propose a multi-agent collaboration framework based on Multimodal Large Language Models (MLLMs). This framework efficiently generates high-quality prompts for multimodal content creation based on user input, thereby improving the efficiency and creativity of the process. In addition, we incorporate a feedback and rollback mechanism that leverages MLLMs to evaluate and provide feedback on generated results, thereby enabling iterative self-correction of multimodal content. We also propose ThemeVlogEval, a theme-based automated benchmarking framework that provides standardized metrics and datasets for fair evaluation. Comprehensive experiments demonstrate the significant advantages and potential of our framework over several baselines, highlighting its effectiveness and great potential for generating automated Vlogs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction Hou, Xiaolu Ma, Bing Cheng, Jiaxiang Ren, Xuhua Yu, Kai Li, Wenyue Zheng, Tianxiang Lu, Qinglin Computer Vision and Pattern Recognition With the growing demand for short videos and personalized content, automated Video Log (Vlog) generation has become a key direction in multimodal content creation. Existing methods mostly rely on predefined scripts, lacking dynamism and personal expression. Therefore, there is an urgent need for an automated Vlog generation approach that enables effective multimodal collaboration and high personalization. To this end, we propose PersonaVlog, an automated multimodal stylized Vlog generation framework that can produce personalized Vlogs featuring videos, background music, and inner monologue speech based on a given theme and reference image. Specifically, we propose a multi-agent collaboration framework based on Multimodal Large Language Models (MLLMs). This framework efficiently generates high-quality prompts for multimodal content creation based on user input, thereby improving the efficiency and creativity of the process. In addition, we incorporate a feedback and rollback mechanism that leverages MLLMs to evaluate and provide feedback on generated results, thereby enabling iterative self-correction of multimodal content. We also propose ThemeVlogEval, a theme-based automated benchmarking framework that provides standardized metrics and datasets for fair evaluation. Comprehensive experiments demonstrate the significant advantages and potential of our framework over several baselines, highlighting its effectiveness and great potential for generating automated Vlogs. |
| title | PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.13602 |