Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

EgoAVU: Egocentric Audio-Visual Understanding

About

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.

Ashish Seth, Xinhao Mei, Changsheng Zhao, Varun Nagaraja, Ernie Chang, Gregory P. Meyer, Gael Le Lan, Yunyang Xiong, Vikas Chandra, Yangyang Shi, Dinesh Manocha, Zhipeng Cai• 2026

Related benchmarks

TaskDatasetResultRank
Video Question AnsweringEgoSchema
Accuracy67.34
88
Video Question AnsweringVideo-MME Short Duration 1.0--
18
Audio-Visual Question AnsweringAVQA
Accuracy89.7
14
Audio-Visual Dense NarrationEgoAVU-Bench
S Score2.66
9
Audio-Visual HallucinationEgoAVU-Bench
Accuracy61.69
9
Audio-Visual Segment NarrationEgoAVU-Bench
S Score2.63
9
Source-Sound AssociationEgoAVU-Bench
S Score3.2
9
Temporal ReasoningEgoAVU-Bench
Accuracy67.84
9
Video Question AnsweringEgoTempo
Accuracy20.83
3
Video Question AnsweringEgoIllusion
Accuracy60.36
3
Showing 10 of 10 rows

Other info

Follow for update