Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos

• URL: http://arxiv.org/abs/2307.04760v4
• Date: Mon, 6 May 2024 03:58:51 GMT
• Title: Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos
• Authors: Sagnik Majumder, Ziad Al-Halah, Kristen Grauman,
• Abstract summary: We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked (multi-channel) audio through the synergy of audio and vision.
• Score: 69.79632907349489
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a self-supervised method for learning representations based on spatial audio-visual correspondences in egocentric videos. Our method uses a masked auto-encoding framework to synthesize masked binaural (multi-channel) audio through the synergy of audio and vision, thereby learning useful spatial relationships between the two modalities. We use our pretrained features to tackle two downstream video tasks requiring spatial understanding in social scenarios: active speaker detection and spatial audio denoising. Through extensive experiments, we show that our features are generic enough to improve over multiple state-of-the-art baselines on both tasks on two challenging egocentric video datasets that offer binaural audio, EgoCom and EasyCom. Project: http://vision.cs.utexas.edu/projects/ego_av_corr.

Related papers

• SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos [77.55518265996312]
  We propose a novel self-supervised embedding to learn how actions sound from narrated in-the-wild egocentric videos. Our multimodal contrastive-consensus coding (MC3) embedding reinforces the associations between audio, language, and vision when all modality pairs agree.
  arXiv  Detail & Related papers  (2024-04-08T05:19:28Z)
• Egocentric Audio-Visual Object Localization [51.434212424829525]
  We propose a geometry-aware temporal aggregation module to handle the egomotion explicitly. The effect of egomotion is mitigated by estimating the temporal geometry transformation and exploiting it to update visual representations. It improves cross-modal localization robustness by disentangling visually-indicated audio representation.
  arXiv  Detail & Related papers  (2023-03-23T17:43:11Z)
• Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video [94.42811508809994]
  We propose an audio spatialization method that draws on visual information in videos to convert their monaural (single-channel) audio to audio. Whereas existing approaches leverage visual features extracted directly from video frames, our approach explicitly disentangles the geometric cues present in the visual stream to guide the learning process.
  arXiv  Detail & Related papers  (2021-11-21T19:26:45Z)
• Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation [45.526051369551915]
  We propose an audio spatialization framework to convert a monaural video into a one exploiting the relationship across audio and visual components. Experiments on benchmark datasets confirm the effectiveness of our proposed framework in both semi-supervised and fully supervised scenarios.
  arXiv  Detail & Related papers  (2021-05-03T09:34:11Z)
• Learning Representations from Audio-Visual Spatial Alignment [76.29670751012198]
  We introduce a novel self-supervised pretext task for learning representations from audio-visual content. The advantages of the proposed pretext task are demonstrated on a variety of audio and visual downstream tasks.
  arXiv  Detail & Related papers  (2020-11-03T16:20:04Z)
• Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision [63.564385139097624]
  We propose a method to learn self-supervised speech representations from the raw audio waveform. We train a raw audio encoder by combining audio-only self-supervision (by predicting informative audio attributes) with visual self-supervision (by generating talking faces from audio) Our results demonstrate the potential of multimodal self-supervision in audiovisual speech for learning good audio representations.
  arXiv  Detail & Related papers  (2020-07-08T14:07:06Z)
• Telling Left from Right: Learning Spatial Correspondence of Sight and Sound [16.99266133458188]
  We propose a novel self-supervised task to leverage a principle: matching spatial information in the audio stream to the positions of sound sources in the visual stream. We train a model to determine whether the left and right audio channels have been flipped, forcing it to reason about spatial localization across the visual and audio streams. We demonstrate that understanding spatial correspondence enables models to perform better on three audio-visual tasks, achieving quantitative gains over supervised and self-supervised baselines.
  arXiv  Detail & Related papers  (2020-06-11T04:00:24Z)

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.