MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ye, Hanrong, Zhang, Haotian, Daxberger, Erik, Chen, Lin, Lin, Zongyu, Li, Yanghao, Zhang, Bowen, You, Haoxuan, Xu, Dan, Gan, Zhe, Lu, Jiasen, Yang, Yinfei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908316069789696
author Ye, Hanrong
Zhang, Haotian
Daxberger, Erik
Chen, Lin
Lin, Zongyu
Li, Yanghao
Zhang, Bowen
You, Haoxuan
Xu, Dan
Gan, Zhe
Lu, Jiasen
Yang, Yinfei
author_facet Ye, Hanrong
Zhang, Haotian
Daxberger, Erik
Chen, Lin
Lin, Zongyu
Li, Yanghao
Zhang, Bowen
You, Haoxuan
Xu, Dan
Gan, Zhe
Lu, Jiasen
Yang, Yinfei
contents This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths. We introduce a new de-biasing evaluation method to help mitigate the unavoidable language bias present in the models being evaluated. Third, we propose a specialized multimodal architecture featuring a novel "Memory Pointer Prompting" mechanism. This design includes a \textit{global glimpse} step to gain an overarching understanding of the entire video and identify key visual information, followed by a fallback step that utilizes the key visual information to generate responses. This enables the model to more effectively comprehend extended video content. With the data, benchmark, and model, we build MM-Ego, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding.
format Preprint
id arxiv_https___arxiv_org_abs_2410_07177
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA
Ye, Hanrong
Zhang, Haotian
Daxberger, Erik
Chen, Lin
Lin, Zongyu
Li, Yanghao
Zhang, Bowen
You, Haoxuan
Xu, Dan
Gan, Zhe
Lu, Jiasen
Yang, Yinfei
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
This research aims to comprehensively explore building a multimodal foundation model for egocentric video understanding. To achieve this goal, we work on three fronts. First, as there is a lack of QA data for egocentric video understanding, we automatically generate 7M high-quality QA samples for egocentric videos ranging from 30 seconds to one hour long in Ego4D based on human-annotated data. This is one of the largest egocentric QA datasets. Second, we contribute a challenging egocentric QA benchmark with 629 videos and 7,026 questions to evaluate the models' ability in recognizing and memorizing visual details across videos of varying lengths. We introduce a new de-biasing evaluation method to help mitigate the unavoidable language bias present in the models being evaluated. Third, we propose a specialized multimodal architecture featuring a novel "Memory Pointer Prompting" mechanism. This design includes a \textit{global glimpse} step to gain an overarching understanding of the entire video and identify key visual information, followed by a fallback step that utilizes the key visual information to generate responses. This enables the model to more effectively comprehend extended video content. With the data, benchmark, and model, we build MM-Ego, an egocentric multimodal LLM that shows powerful performance on egocentric video understanding.
title MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.07177