Related papers: Learning from Silence and Noise for Visual Sound S…

To decide whether a digital video has been captured by a given device, multimedia forensic tools usually exploit characteristic noise traces left by the camera sensor on the acquired frames. This analysis requires that the noise pattern…

Label noise is ubiquitous in various machine learning scenarios such as self-labeling with model predictions and erroneous data annotation. Many existing approaches are based on heuristics such as sample losses, which might not be flexible…

Learning to segment images purely by relying on the image-text alignment from web data can lead to sub-optimal performance due to noise in the data. The noise comes from the samples where the associated text does not correlate with the…

We learn rich natural sound representations by capitalizing on large amounts of unlabeled sound data collected in the wild. We leverage the natural synchronization between vision and sound to learn an acoustic representation using…

This work examines a semi-blind single-channel source separation problem. Our specific aim is to separate one source whose local structure is approximately known, from another a priori unspecified background source, given only a single…

Audio-visual automatic speech recognition is a promising approach to robust ASR under noisy conditions. However, up until recently it had been traditionally studied in isolation assuming the video of a single speaking face matches the…

Audio-visual automatic speech recognition (AV-ASR) models are very effective at reducing word error rates on noisy speech, but require large amounts of transcribed AV training data. Recently, audio-visual self-supervised learning (SSL)…

Video saliency detection (VSD) aims at fast locating the most attractive objects/things/patterns in a given video clip. Existing VSD-related works have mainly relied on the visual system but paid less attention to the audio aspect, while,…

Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations obtained from…

A microphone array can provide a mobile robot with the capability of localizing, tracking and separating distant sound sources in 2D, i.e., estimating their relative elevation and azimuth. To combine acoustic data with visual information in…

Video text spotting (VTS) aims to simultaneously localize, recognize and track text instances in videos. To address the limited recognition capability of end-to-end methods, recent methods track the zero-shot results of state-of-the-art…

Recently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the…

This paper presents a novel metric learning approach to address the performance gap between normal and silent speech in visual speech recognition (VSR). The difference in lip movements between the two poses a challenge for existing VSR…

We present SELDVisualSynth, a tool for generating synthetic videos for audio-visual sound event localization and detection (SELD). Our approach incorporates real-world background images to improve realism in synthetic audio-visual SELD data…

Learning visual representations through self-supervision is an extremely challenging task as the network needs to sieve relevant patterns from spurious distractors without the active guidance provided by supervision. This is achieved…

Different self-supervised tasks (SSL) reveal different features from the data. The learned feature representations can exhibit different performance for each downstream task. In this light, this work aims to combine Multiple SSL tasks…

Recently, self-supervised learning (SSL) has demonstrated strong performance in speaker recognition, even if the pre-training objective is designed for speech recognition. In this paper, we study which factor leads to the success of…

We present a unique comparative analysis, and evaluation of vision, radio, and audio based localization algorithms. We create the first baseline for the aforementioned sensors using the recently published Lund University Vision, Radio, and…

Underwater acoustic localization has traditionally been challenging due to the presence of unknown environmental structure and dynamic conditions. The problem is richer still when such structure includes occlusion, which causes the loss of…

Designing robust algorithms capable of training accurate neural networks on uncurated datasets from the web has been the subject of much research as it reduces the need for time consuming human labor. The focus of many previous research…