LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Ying, Yang, Yanlai, Ren, Mengye
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910686167171072
author Wang, Ying
Yang, Yanlai
Ren, Mengye
author_facet Wang, Ying
Yang, Yanlai
Ren, Mengye
contents In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity descriptions of the camera wearer and leverages the zero-shot capabilities of pretrained large language models to perform reasoning over long-form video context. Furthermore, LifelongMemory uses a confidence and explanation module to produce confident, high-quality, and interpretable answers. Our approach achieves state-of-the-art performance on the EgoSchema benchmark for question answering and is highly competitive on the natural language query (NLQ) challenge of Ego4D. Code is available at https://github.com/agentic-learning-ai-lab/lifelong-memory.
format Preprint
id arxiv_https___arxiv_org_abs_2312_05269
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos
Wang, Ying
Yang, Yanlai
Ren, Mengye
Computer Vision and Pattern Recognition
Machine Learning
In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity descriptions of the camera wearer and leverages the zero-shot capabilities of pretrained large language models to perform reasoning over long-form video context. Furthermore, LifelongMemory uses a confidence and explanation module to produce confident, high-quality, and interpretable answers. Our approach achieves state-of-the-art performance on the EgoSchema benchmark for question answering and is highly competitive on the natural language query (NLQ) challenge of Ego4D. Code is available at https://github.com/agentic-learning-ai-lab/lifelong-memory.
title LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2312.05269