Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation

• URL: http://arxiv.org/abs/2608.04902v1
• Date: Wed, 05 Aug 2026 14:28:05 GMT
• Title: Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation
• Abstract summary: Video-to-audio (V2A) generation extends image-to-audio generation (I2A)<n>We introduce TD-V2A, which leverages temporal differences (TD) as the key representation that distinguishes V2A from I2A.<n>We show that effectively exploiting TD through our proposed framework significantly improves end-to-end V2A generation quality.
• Score: 53.47090840868696
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video-to-audio (V2A) generation extends image-to-audio generation (I2A) by introducing consecutive frames that provide essential temporal cues for audio synthesis. However, existing conditional diffusion-based V2A methods typically enhance visual conditioning with additional audio-visual supervision, acoustic structure prediction, or reasoning from large multimodal models, requiring extra networks or strong inductive biases. Inspired by recent advances in visual representation learning, we introduce TD-V2A, which leverages temporal differences (TD) as the key representation that distinguishes V2A from I2A, enriching visual conditioning with minimal architectural modification. We first investigate TD at both the frame and feature levels to identify the most effective representation level at which TD complements visual representations. Based on these findings, we develop a hierarchically continual learning strategy and an annealed temporal differences guidance method to progressively learn and exploit TD information during diffusion training and sampling process, respectively. Extensive experiments on benchmark datasets demonstrate that effectively exploiting TD through our proposed framework significantly improves end-to-end V2A generation quality, even outperforming dedicated V2A representations such as contrastive audio-visual pretraining.

Related papers

• VIBE: Video Instruction-aligned Background music gEneration [58.326977744404566]
  Current video-to-music (V2M) models lack semantic control and fail to penalize instruction violations.<n>We introduce VIBE, a novel text-and-video-to-music (T+V2M) generation model that leverages Conditioning Connection.
  arXiv  Detail & Related papers  (2026-08-31T01:19:55Z)
• GMS-CAVP: Improving Audio-Video Correspondence with Multi-Scale Contrastive and Generative Pretraining [64.72014392166625]
  GMS-CAVP is a novel framework that combines Multi-Scale Video-Audio Alignment and Multi-Scale Spatial-Temporal Diffusion-based pretraining objectives.<n>First, GMS-CAVP introduces a multi-scale contrastive learning strategy that captures semantic and temporal relations across varying granularities.<n>Second, we go beyond traditional contrastive learning by incorporating a diffusion-based generative objective, enabling modality translation and synthesis between video and audio.
  arXiv  Detail & Related papers  (2026-01-27T13:43:32Z)
• MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings [75.0617088717528]
  MoCa is a framework for transforming pre-trained VLM backbones into effective bidirectional embedding models.<n>MoCa consistently improves performance across MMEB and ViDoRe-v2 benchmarks, achieving new state-of-the-art results.
  arXiv  Detail & Related papers  (2025-06-29T06:41:00Z)
• PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling [95.2927277964409]
  We introduce Online Audio-Visual Event Parsing (On-AVEP), a novel paradigm for parsing audio, visual, and audio-visual events by sequentially analyzing incoming video streams.<n>We propose the Predictive Future Modeling framework featured by (a) predictive multimodal future modeling to infer and integrate beneficial future audio-visual cues.<n>Experiments show PreFM significantly outperforms state-of-the-art methods by a large margin with significantly fewer parameters.
  arXiv  Detail & Related papers  (2025-05-29T06:46:19Z)
• Sequential Contrastive Audio-Visual Learning [12.848371604063168]
  We propose sequential contrastive audiovisual learning (SCAV), which contrasts examples based on their non-aggregated representation space.<n>Experiments with the VGGSound and Music datasets demonstrate the effectiveness of SCAV.<n>We also show that models trained with SCAV exhibit a significant degree of flexibility regarding the metric employed for retrieval.
  arXiv  Detail & Related papers  (2024-07-08T09:45:20Z)
• Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation [72.90144343056227]
  We explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed T2V model. Our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-18T17:59:58Z)
• CMMD: Contrastive Multi-Modal Diffusion for Video-Audio Conditional Modeling [21.380988939240844]
  We introduce a multi-modal diffusion model tailored for the bi-directional conditional generation of video and audio. We propose a joint contrastive training loss to improve the synchronization between visual and auditory occurrences.
  arXiv  Detail & Related papers  (2023-12-08T23:55:19Z)
• A multimodal dynamical variational autoencoder for audiovisual speech representation learning [23.748108659645844]
  multimodal and dynamical VAE (MDVAE) applied to unsupervised audio-visual speech representation learning. Experiments include manipulating audiovisual speech, audiovisual facial image denoising, and audiovisual speech emotion recognition.
  arXiv  Detail & Related papers  (2023-05-05T14:37:26Z)
• Multiresolution and Multimodal Speech Recognition with Transformers [22.995102995029576]
  This paper presents an audio visual automatic speech recognition (AV-ASR) system using a Transformer-based architecture. We focus on the scene context provided by the visual information, to ground the ASR. Our results are comparable to state-of-the-art Listen, Attend and Spell-based architectures.
  arXiv  Detail & Related papers  (2020-04-29T09:32:11Z)
• How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition [10.74796391075403]
  This study investigates the inner workings of AV Align and visualises the audio-visual alignment patterns. We find that AV Align learns to align acoustic and visual representations of speech at the frame level on TCD-TIMIT in a generally monotonic pattern. We propose a regularisation method which involves predicting lip-related Action Units from visual representations.
  arXiv  Detail & Related papers  (2020-04-17T13:59:19Z)

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.