Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.06272 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913784361123840 |
|---|---|
| author | Rosa, Kevin Dela |
| author_facet | Rosa, Kevin Dela |
| contents | We present RAVEN an adaptive AI agent framework designed for multimodal entity discovery and retrieval in large-scale video collections. Synthesizing information across visual, audio, and textual modalities, RAVEN autonomously processes video data to produce structured, actionable representations for downstream tasks. Key contributions include (1) a category understanding step to infer video themes and general-purpose entities, (2) a schema generation mechanism that dynamically defines domain-specific entities and attributes, and (3) a rich entity extraction process that leverages semantic retrieval and schema-guided prompting. RAVEN is designed to be model-agnostic, allowing the integration of different vision-language models (VLMs) and large language models (LLMs) based on application-specific requirements. This flexibility supports diverse applications in personalized search, content discovery, and scalable information retrieval, enabling practical applications across vast datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06272 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RAVEN: An Agentic Framework for Multimodal Entity Discovery from Large-Scale Video Collections Rosa, Kevin Dela Information Retrieval Artificial Intelligence We present RAVEN an adaptive AI agent framework designed for multimodal entity discovery and retrieval in large-scale video collections. Synthesizing information across visual, audio, and textual modalities, RAVEN autonomously processes video data to produce structured, actionable representations for downstream tasks. Key contributions include (1) a category understanding step to infer video themes and general-purpose entities, (2) a schema generation mechanism that dynamically defines domain-specific entities and attributes, and (3) a rich entity extraction process that leverages semantic retrieval and schema-guided prompting. RAVEN is designed to be model-agnostic, allowing the integration of different vision-language models (VLMs) and large language models (LLMs) based on application-specific requirements. This flexibility supports diverse applications in personalized search, content discovery, and scalable information retrieval, enabling practical applications across vast datasets. |
| title | RAVEN: An Agentic Framework for Multimodal Entity Discovery from Large-Scale Video Collections |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2504.06272 |