Grounded Question-Answering in Long Egocentric Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Di, Shangzhe, Xie, Weidi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913293408403456
author Di, Shangzhe
Xie, Weidi
author_facet Di, Shangzhe
Xie, Weidi
contents Existing approaches to video understanding, mainly designed for short videos from a third-person perspective, are limited in their applicability in certain fields, such as robotics. In this paper, we delve into open-ended question-answering (QA) in long, egocentric videos, which allows individuals or robots to inquire about their own past visual experiences. This task presents unique challenges, including the complexity of temporally grounding queries within extensive video content, the high resource demands for precise data annotation, and the inherent difficulty of evaluating open-ended answers due to their ambiguous nature. Our proposed approach tackles these challenges by (i) integrating query grounding and answering within a unified model to reduce error propagation; (ii) employing large language models for efficient and scalable data synthesis; and (iii) introducing a close-ended QA task for evaluation, to manage answer ambiguity. Extensive experiments demonstrate the effectiveness of our method, which also achieves state-of-the-art performance on the QaEgo4D and Ego4D-NLQ benchmarks. Code, data, and models are available at https://github.com/Becomebright/GroundVQA.
format Preprint
id arxiv_https___arxiv_org_abs_2312_06505
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Grounded Question-Answering in Long Egocentric Videos
Di, Shangzhe
Xie, Weidi
Computer Vision and Pattern Recognition
Existing approaches to video understanding, mainly designed for short videos from a third-person perspective, are limited in their applicability in certain fields, such as robotics. In this paper, we delve into open-ended question-answering (QA) in long, egocentric videos, which allows individuals or robots to inquire about their own past visual experiences. This task presents unique challenges, including the complexity of temporally grounding queries within extensive video content, the high resource demands for precise data annotation, and the inherent difficulty of evaluating open-ended answers due to their ambiguous nature. Our proposed approach tackles these challenges by (i) integrating query grounding and answering within a unified model to reduce error propagation; (ii) employing large language models for efficient and scalable data synthesis; and (iii) introducing a close-ended QA task for evaluation, to manage answer ambiguity. Extensive experiments demonstrate the effectiveness of our method, which also achieves state-of-the-art performance on the QaEgo4D and Ego4D-NLQ benchmarks. Code, data, and models are available at https://github.com/Becomebright/GroundVQA.
title Grounded Question-Answering in Long Egocentric Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.06505