Saved in:
Bibliographic Details
Main Authors: Nguyen, Khanh Binh, Park, Chae Jung
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.22732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917359311126528
author Nguyen, Khanh Binh
Park, Chae Jung
author_facet Nguyen, Khanh Binh
Park, Chae Jung
contents Large-scale pre-trained image-text models exhibit robust multimodal representations, yet applying the Contrastive Language-Image Pre-training (CLIP) model to audio-visual localization remains challenging. Replacing the classification token ([CLS]) with an audio-embedded token ([V_A]) struggles to capture semantic cues, and the prompt "a photo of a [V_A]" fails to establish meaningful connections between audio embeddings and context tokens. To address these issues, we propose Sound-aware Prompt Learning (SOUPLE), which replaces fixed prompts with learnable context tokens. These tokens incorporate visual features to generate conditional context for a mask decoder, effectively bridging semantic correspondence between audio and visual inputs. Experiments on VGGSound, SoundNet, and AVSBench demonstrate that SOUPLE improves localization and segmentation performance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_22732
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts
Nguyen, Khanh Binh
Park, Chae Jung
Computer Vision and Pattern Recognition
Large-scale pre-trained image-text models exhibit robust multimodal representations, yet applying the Contrastive Language-Image Pre-training (CLIP) model to audio-visual localization remains challenging. Replacing the classification token ([CLS]) with an audio-embedded token ([V_A]) struggles to capture semantic cues, and the prompt "a photo of a [V_A]" fails to establish meaningful connections between audio embeddings and context tokens. To address these issues, we propose Sound-aware Prompt Learning (SOUPLE), which replaces fixed prompts with learnable context tokens. These tokens incorporate visual features to generate conditional context for a mask decoder, effectively bridging semantic correspondence between audio and visual inputs. Experiments on VGGSound, SoundNet, and AVSBench demonstrate that SOUPLE improves localization and segmentation performance.
title SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.22732