Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning

• URL: http://arxiv.org/abs/2505.22045v1
• Date: Wed, 28 May 2025 07:08:17 GMT
• Title: Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
• Authors: Le Xu, Chenxing Li, Yong Ren, Yujie Chen, Yu Gu, Ruibo Fu, Shan Yang, Dong Yu,
• Abstract summary: Current vision-guided audio captioning systems fail to address audiovisual misalignment in real-world scenarios.<n>We present an entropy-aware gated fusion framework that dynamically modulates visual information flow through cross-modal uncertainty quantification.<n>We also develop a batch-wise audiovisual shuffling technique that generates synthetic mismatched training pairs.
• Score: 37.17910848101769
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current vision-guided audio captioning systems frequently fail to address audiovisual misalignment in real-world scenarios, such as dubbed content or off-screen sounds. To bridge this critical gap, we present an entropy-aware gated fusion framework that dynamically modulates visual information flow through cross-modal uncertainty quantification. Our novel approach employs attention entropy analysis in cross-attention layers to automatically identify and suppress misleading visual cues during modal fusion. Complementing this architecture, we develop a batch-wise audiovisual shuffling technique that generates synthetic mismatched training pairs, greatly enhancing model resilience against alignment noise. Evaluations on the AudioCaps benchmark demonstrate our system's superior performance over existing baselines, especially in mismatched modality scenarios. Furthermore, our solution demonstrates an approximately 6x improvement in inference speed compared to the baseline.

Related papers

• Spatial and Semantic Embedding Integration for Stereo Sound Event Localization and Detection in Regular Videos [3.2472293599354596]
  This report presents our systems submitted to the audio-only and audio-visual tracks of the DCASE2025 Task 3 Challenge: Stereo Sound Event localization and Detection in Regular Video Content.<n>SELD is a complex task that combines temporal event classification with spatial localization, requiring reasoning across spatial, temporal, and semantic dimensions.<n>To address this, we enhance standard SELD architectures with semantic information by integrating pre-trained, contrastive language-aligned models: CLAP for audio and OWL-ViT for visual inputs.
  arXiv  Detail & Related papers  (2025-07-07T10:08:57Z)
• CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment [76.32508013503653]
  We propose CAV-MAE Sync as a simple yet effective extension of the original CAV-MAE framework for self-supervised audio-visual learning.<n>We tackle the mismatch between modalities by treating audio as a temporal sequence aligned with video frames, rather than using global representations.<n>We improve spatial localization by introducing learnable register tokens that reduce semantic load on patch tokens.
  arXiv  Detail & Related papers  (2025-05-02T12:59:58Z)
• AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection [57.649223695021114]
  We present a novel weakly supervised framework that leverages audio-visual collaboration for robust video anomaly detection.<n>Our framework demonstrates superior performance across multiple benchmarks, with audio integration significantly boosting anomaly detection accuracy.
  arXiv  Detail & Related papers  (2025-04-06T13:59:16Z)
• Parameter Efficient Audio Captioning With Faithful Guidance Using Audio-text Shared Latent Representation [0.9285295512807729]
  We propose a data augmentation technique for generating hallucinated audio captions and show that similarity based on an audio-text shared latent space is suitable for detecting hallucination. We then propose a parameter efficient inference time faithful decoding algorithm that enables smaller audio captioning models with performance equivalent to larger models trained with more data.
  arXiv  Detail & Related papers  (2023-09-06T19:42:52Z)
• Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder [58.523884148942166]
  We propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework. First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes. Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers.
  arXiv  Detail & Related papers  (2023-08-14T08:19:24Z)
• Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead [88.17413955380262]
  We introduce a novel architecture for early exiting based on the vision transformer architecture. We show that our method works for both classification and regression problems. We also introduce a novel method for integrating audio and visual modalities within early exits in audiovisual data analysis.
  arXiv  Detail & Related papers  (2021-05-19T13:30:34Z)
• Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation [73.1652905564163]
  We address the problem of separating individual speech signals from videos using audio-visual neural processing. Most conventional approaches utilize frame-wise matching criteria to extract shared information between co-occurring audio and video. We propose a cross-modal affinity network (CaffNet) that learns global correspondence as well as locally-varying affinities between audio and visual streams.
  arXiv  Detail & Related papers  (2021-03-25T15:39:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.