paper-with-me

홈 › Papers

Aligning Audio-Visual Joint Representations with an Agentic Workflow

2024-10-30 · Shentong Mo, Yibing Song

Visual content and accompanied audio signals naturally formulate a joint representation to improve audio-visual (AV) related applications. While studies develop various AV representation learning frameworks, the importance of AV data alignment is usually undermined for achieving high-quality representation. We observe that an audio signal may contain background noise interference. Also, non-synchronization may appear between audio and video streams. These non-strict data alignment limits representation quality and downgrade application performance. In this paper, we propose to improve AV joint representations from a data-centric perspective by aligning audio signals to visual data. Our alignment is conducted in an agentic workflow controlled by an LLM-based assistant named AVAgent. For each input AV data pair, our AVAgent uses a multi-modal LLM to convert audio and visual data into language descriptions separately (i.e., tool use). Then, AVAgent reasons whether this paired data is aligned well and plans to edit the audio signal if needed (i.e., planning). The audio editing is executed by predefined actions that filter noise or augment data. Moreover, we use a VLM to evaluate how modified audio signals match the visual content and provide feedback to AVAgent (i.e., reflection). The tool use, planning, and reflection steps operate cyclically to become an agentic workflow where audio signals are gradually aligned to visual content. To this end, existing methods can directly leverage the aligned AV data via our agentic workflow to improve AV joint representations. The experimental results comprehensively demonstrate the state-of-the-art performance of the proposed approach against previous baselines in diverse downstream tasks.

📄 PDF Abstract BibTeX arXiv:2410.23230

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers

2024-06-07 · Tanvir Mahmud, Shentong Mo, Yapeng Tian, Diana Marculescu

Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimo…

audio-visual learningContrastive Learning

A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition

2023-05-30 · Shentong Mo, Pedro Morgado

The ability to accurately recognize, localize and separate sound sources is fundamental to any audio-visual perception task. Historically, these abilities were tackled separately, with several methods developed independe…

audio-visual learning

AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding

2025-12-18 · Sanjoy Chowdhury, Karren D. Yang, Xudong Liu, Fartash Faghri 외 arxiv

Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in multi-speaker, dialogue-centric settings that demand agentic reasoning tracking who speaks, maintaining…

JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation

2026-06-02 · Yinan Chen, Chuming Lin, Zhennan Chen, Yuxiang Zeng 외 arxiv

While instruction-based video editing has seen significant progress, joint audio-visual editing remains constrained by the absence of dedicated datasets and benchmarks. To bridge this gap, we present JAVEdit-100k, the fi…

Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention

2020-08-14 · Bin Duan, Hao Tang, Wei Wang, Ziliang Zong 외

The major challenge in audio-visual event localization task lies in how to fuse information from multiple modalities effectively. Recent works have shown that attention mechanism is beneficial to the fusion process. In t…

audio-visual event localizationvalid