English
Related papers

Related papers: Echoes Over Time: Unlocking Length Generalization …

200 papers

Existing works have made strides in video generation, but the lack of sound effects (SFX) and background music (BGM) hinders a complete and immersive viewer experience. We introduce a novel semantically consistent v ideo-to-audio generation…

Multimedia · Computer Science 2024-04-29 Gehui Chen , Guan'an Wang , Xiaowen Huang , Jitao Sang

Large-scale multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio…

Diffusion models have revolutionized image and video generation, achieving unprecedented visual quality. However, their reliance on transformer architectures incurs prohibitively high computational costs, particularly when extending…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Justin Cui , Jie Wu , Ming Li , Tao Yang , Xiaojie Li , Rui Wang , Andrew Bai , Yuanhao Ban , Cho-Jui Hsieh

We introduce MMAudioSep, a generative model for video/text-queried sound separation that is founded on a pretrained video-to-audio model. By leveraging knowledge about the relationship between video/text and audio learned through a…

Sound · Computer Science 2026-04-20 Akira Takahashi , Shusuke Takahashi , Yuki Mitsufuji

Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with generating long videos that involve multiple scenes, coherent…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Weijia Wu , Mingyu Liu , Zeyu Zhu , Xi Xia , Haoen Feng , Wen Wang , Kevin Qinghong Lin , Chunhua Shen , Mike Zheng Shou

The rise of deep learning technologies has quickly advanced many fields, including that of generative music systems. There exist a number of systems that allow for the generation of good sounding short snippets, yet, these generated…

Sound · Computer Science 2021-04-27 Zixun Guo , Makris Dimos , Herremans Dorien

Due to the variability in characteristics of audio scenes, some scenes can naturally be recognized earlier than others. In this work, rather than using equal-length snippets for all scene categories, as is common in the literature, we study…

Sound · Computer Science 2019-05-10 Huy Phan , Oliver Y. Chén , Philipp Koch , Lam Pham , Ian McLoughlin , Alfred Mertins , Maarten De Vos

A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow matching based models rely on modeling instantaneous velocity,…

Sound · Computer Science 2025-09-09 Xiaoran Yang , Jianxuan Yang , Xinyue Guo , Haoyu Wang , Ningning Pan , Gongping Huang

Composing music for video is essential yet challenging, leading to a growing interest in automating music generation for video applications. Existing approaches often struggle to achieve robust music-video correspondence and generative…

Sound · Computer Science 2025-04-21 Heda Zuo , Weitao You , Junxian Wu , Shihong Ren , Pei Chen , Mingxu Zhou , Yujia Lu , Lingyun Sun

The increasing amount of online videos brings several opportunities for training self-supervised neural networks. The creation of large scale datasets of videos such as the YouTube-8M allows us to deal with this large amount of data in…

Information Retrieval · Computer Science 2018-01-09 Didac Surís , Amanda Duarte , Amaia Salvador , Jordi Torres , Xavier Giró-i-Nieto

Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free approaches fall into two categories: extensions of bidirectional models, which are tightly…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Jangho Park , Geon Yeong Park , Gihyun Kwon , Jong Chul Ye

Video-to-audio (V2A) generation aims to synthesize realistic and semantically aligned audio from silent videos, with potential applications in video editing, Foley sound design, and assistive multimedia. Although the excellent results,…

Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild videos, given the cross-modal semantic correspondence that is…

Sound · Computer Science 2025-01-10 Darius Petermann , Mahdi M. Kalayeh

Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in…

Computer Vision and Pattern Recognition · Computer Science 2024-11-14 Jianing Zhou , Han Li , Shuai Zhang , Ning Xie , Ruijie Wang , Xiaohan Nie , Sheng Liu , Lingyun Wang

Sounding Video Generation (SVG) is an audio-video joint generation task challenged by high-dimensional signal spaces, distinct data formats, and different patterns of content information. To address these issues, we introduce a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Mingzhen Sun , Weining Wang , Yanyuan Qiao , Jiahui Sun , Zihan Qin , Longteng Guo , Xinxin Zhu , Jing Liu

Most existing text-to-audio (TTA) generation methods produce mono outputs, neglecting essential spatial information for immersive auditory experiences. To address this issue, we propose a cascaded method for text-to-multisource binaural…

Sound · Computer Science 2025-11-06 Yuxuan He , Xiaoran Yang , Ningning Pan , Gongping Huang

This paper presents InfiniteAudio, a simple yet effective strategy for generating infinite-length audio using diffusion-based text-to-audio methods. Current approaches face memory constraints because the output size increases with input…

Audio and Speech Processing · Electrical Eng. & Systems 2025-06-04 Chaeyoung Jung , Hojoon Ki , Ji-Hoon Kim , Junmo Kim , Joon Son Chung

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Hongchen Wei , Zhenzhong Chen

Video generation has witnessed great success recently, but their application in generating long videos still remains challenging due to the difficulty in maintaining the temporal consistency of generated videos and the high memory cost…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Wei Feng , Xin Wang , Hong Chen , Zeyang Zhang , Wenwu Zhu

Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural…

Sound · Computer Science 2024-07-16 Santiago Pascual , Chunghsin Yeh , Ioannis Tsiamas , Joan Serrà