English
Related papers

Related papers: EquiAV: Leveraging Equivariance for Audio-Visual C…

200 papers

Self-supervised learning aims to learn a embedding space where semantically similar samples are close. Contrastive learning methods pull views of samples together and push different samples away, which utilizes semantic invariance of…

Machine Learning · Computer Science 2023-02-17 Lu Han , Han-Jia Ye , De-Chuan Zhan

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

Sound · Computer Science 2020-11-17 Eduardo Fonseca , Diego Ortego , Kevin McGuinness , Noel E. O'Connor , Xavier Serra

Recent advances suggest the advantage of multi-modal training in comparison with single-modal methods. In contrast to this view, in our work we find that similar gain can be obtained from training with different formats of a single…

Sound · Computer Science 2021-03-25 Luyu Wang , Aaron van den Oord

Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Victor Sechaud , Jérémy Scanvic , Quentin Barthélemy , Patrice Abry , Julián Tachella

Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous work proposed…

Machine Learning · Computer Science 2019-12-20 Da Tang , Dawen Liang , Nicholas Ruozzi , Tony Jebara

Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Yinshuang Xu , Dian Chen , Katherine Liu , Sergey Zakharov , Rares Ambrus , Kostas Daniilidis , Vitor Guizilini

Multimodal large models have been recognized for their advantages in various performance and downstream tasks. The development of these models is crucial towards achieving general artificial intelligence in the future. In this paper, we…

Sound · Computer Science 2023-09-12 Sen Fang , Bowen Gao , Yangjian Wu , Teik Toe Teoh

Recent advances in video-audio (V-A) understanding and generation have increasingly relied on joint V-A embeddings, which serve as the foundation for tasks such as cross-modal retrieval and generation. While prior methods like CAVP…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Shentong Mo , Zehua Chen , Jun Zhu

Learning from audio-visual data offers many possibilities to express correspondence between the audio and visual content, similar to the human perception that relates aural and visual information. In this work, we present a method for…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-23 Shanshan Wang , Archontis Politis , Annamaria Mesaros , Tuomas Virtanen

When watching videos, the occurrence of a visual event is often accompanied by an audio event, e.g., the voice of lip motion, the music of playing instruments. There is an underlying correlation between audio and visual events, which can be…

Multimedia · Computer Science 2020-08-19 Ying Cheng , Ruize Wang , Zhihao Pan , Rui Feng , Yuejie Zhang

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…

Computer Vision and Pattern Recognition · Computer Science 2020-04-10 Yude Wang , Jie Zhang , Meina Kan , Shiguang Shan , Xilin Chen

Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target…

Machine Learning · Computer Science 2019-02-14 Abubakar Abid , James Zou

Audiovisual representation learning typically relies on the correspondence between sight and sound. However, there are often multiple audio tracks that can correspond with a visual scene. Consider, for example, different conversations on…

Sound · Computer Science 2024-06-11 Nikhil Singh , Chih-Wei Wu , Iroro Orife , Mahdi Kalayeh

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Sound · Computer Science 2022-03-29 Xichen Pan , Peiyu Chen , Yichen Gong , Helong Zhou , Xinbing Wang , Zhouhan Lin

Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…

Computer Vision and Pattern Recognition · Computer Science 2021-10-13 Yuwen Xiong , Mengye Ren , Wenyuan Zeng , Raquel Urtasun

Equivariance is a nice property to have as it produces much more parameter efficient neural architectures and preserves the structure of the input through the feature mapping. Even though some combinations of transformations might never…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 David W. Romero , Mark Hoogendoorn

Given a collection of images, humans are able to discover landmarks by modeling the shared geometric structure across instances. This idea of geometric equivariance has been widely used for the unsupervised discovery of object landmark…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Zezhou Cheng , Jong-Chyi Su , Subhransu Maji

The widespread application of AIGC contents has brought not only unprecedented opportunities, but also potential security concerns, e.g., audio-visual deepfakes. Therefore, it is of great importance to develop an effective and generalizable…

Multimedia · Computer Science 2025-11-25 Fan Nie , Jiangqun Ni , Jian Zhang , Bin Zhang , Weizhe Zhang , Bin Li

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Jonathan Kahana , Yedid Hoshen

Creating representations of shapes that are invari-ant to isometric or almost-isometric transforma-tions has long been an area of interest in shape anal-ysis, since enforcing invariance allows the learningof more effective and robust shape…

Computer Vision and Pattern Recognition · Computer Science 2021-07-09 Jeffrey Gu , Serena Yeung