EgoAVU: Egocentric Audio-Visual Understanding

TL;DR

EgoAVU introduces a scalable method for automatically generating egocentric audio-visual data, enabling large-scale training and revealing limitations of current models in understanding both modalities jointly.

Contribution

The paper presents EgoAVU, a novel data engine and dataset for egocentric audio-visual understanding, improving multi-modal model performance and exposing existing biases.

Findings

Finetuning on EgoAVU-Instruct improves performance by up to 113% on EgoAVU-Bench.

Models biased towards visual signals, neglecting audio cues.

Transfer gains observed on EgoTempo and EgoIllusion benchmarks.

Abstract

Understanding egocentric videos plays a vital role for embodied intelligence. Recent multi-modal large language models (MLLMs) can accept both visual and audio inputs. However, due to the challenge of obtaining text labels with coherent joint-modality information, whether MLLMs can jointly understand both modalities in egocentric videos remains under-explored. To address this problem, we introduce EgoAVU, a scalable data engine to automatically generate egocentric audio-visual narrations, questions, and answers. EgoAVU enriches human narrations with multimodal context and generates audio-visual narrations through cross-modal correlation modeling. Token-based video filtering and modular, graph-based curation ensure both data diversity and quality. Leveraging EgoAVU, we construct EgoAVU-Instruct, a large-scale training dataset of 3M samples, and EgoAVU-Bench, a manually verified evaluation split covering diverse tasks. EgoAVU-Bench clearly reveals the limitations of existing MLLMs: they bias heavily toward visual signals, often neglecting audio cues or failing to correspond audio with the visual source. Finetuning MLLMs on EgoAVU-Instruct effectively addresses this issue, enabling up to 113% performance improvement on EgoAVU-Bench. Such benefits also transfer to other benchmarks such as EgoTempo and EgoIllusion, achieving up to 28% relative performance gain. Code will be released to the community.