paper-with-me

홈 › Papers

What's Making That Sound Right Now? Video-centric Audio-Visual Localization

2025-07-07 · Hahyeon Choi, Junhoo Lee, Nojun Kwak arxiv

Audio-Visual Localization (AVL) aims to identify sound-emitting sources within a visual scene. However, existing studies focus on image-level audio-visual associations, failing to capture temporal dynamics. Moreover, they assume simplified scenarios where sound sources are always visible and involve only a single object. To address these limitations, we propose AVATAR, a video-centric AVL benchmark that incorporates high-resolution temporal information. AVATAR introduces four distinct scenarios -- Single-sound, Mixed-sound, Multi-entity, and Off-screen -- enabling a more comprehensive evaluation of AVL models. Additionally, we present TAVLO, a novel video-centric AVL model that explicitly integrates temporal information. Experimental results show that conventional methods struggle to track temporal variations due to their reliance on global audio features and frame-level mappings. In contrast, TAVLO achieves robust and precise audio-visual alignment by leveraging high-resolution temporal modeling. Our work empirically demonstrates the importance of temporal dynamics in AVL and establishes a new standard for video-centric audio-visual localization.

📄 PDF Abstract BibTeX arXiv:2507.04667

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Localization

Similar Papers 제목 키워드 기반

A SOUND APPROACH: Using Large Language Models to generate audio descriptions for egocentric text-audio retrieval

2024-02-29 · Andreea-Maria Oncescu, João F. Henriques, Andrew Zisserman, Samuel Albanie 외

Video databases from the internet are a valuable source of text-audio retrieval datasets. However, given that sound and vision streams represent different "views" of the data, treating visual descriptions as audio descri…

Retrieval

EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation

2025-12-31 · Bingxuan Li, Yiming Cui, Yicheng He, Yiwei Wang 외 arxiv

Sound effects build an essential layer of multimodal storytelling, shaping the emotional atmosphere and the narrative semantics of videos. Despite recent advancement in video-text-to-audio (VT2A), the current formulation…

EgoSampling: Fast-Forward and Stereo for Egocentric Videos

2014-12-11 · CVPR 2015 6 · Yair Poleg, Tavi Halperin, Chetan Arora, Shmuel Peleg

While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video b…

Sound Bridge: Associating Egocentric and Exocentric Videos via Audio Cues

2025-01-01 · CVPR 2025 1 · Sihong Huang, Jiaxin Wu, XiaoYong Wei, Yi Cai 외

Understanding human behavior and the environmental information in the egocentric video is very challenging due to the invisibility of some actions (e.g., laughing and sneezing) and the local nature of the first-perso…

Action RecognitionScene RecognitionVideo Alignment

SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos

2024-04-08 · CVPR 2024 1 · Changan Chen, Kumar Ashutosh, Rohit Girdhar, David Harwath 외

We propose a novel self-supervised embedding to learn how actions sound from narrated in-the-wild egocentric videos. Whereas existing methods rely on curated data with known audio-visual correspondence, our multimodal co…