ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction

• URL: http://arxiv.org/abs/2012.06170v2
• Date: Thu, 18 Mar 2021 06:00:20 GMT
• Title: ViNet: Pushing the limits of Visual Modality for Audio-Visual Saliency Prediction
• Abstract summary: ViNet is a fully convolutional encoder-decoder architecture. ViNet does not use audio as input and still outperforms state-of-the-art audio-visual saliency prediction models.
• Score: 7.632076006056503
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose the ViNet architecture for audio-visual saliency prediction. ViNet is a fully convolutional encoder-decoder architecture. The encoder uses visual features from a network trained for action recognition, and the decoder infers a saliency map via trilinear interpolation and 3D convolutions, combining features from multiple hierarchies. The overall architecture of ViNet is conceptually simple; it is causal and runs in real-time (60 fps). ViNet does not use audio as input and still outperforms the state-of-the-art audio-visual saliency prediction models on nine different datasets (three visual-only and six audio-visual datasets). ViNet also surpasses human performance on the CC, SIM and AUC metrics for the AVE dataset, and to our knowledge, it is the first network to do so. We also explore a variation of ViNet architecture by augmenting audio features into the decoder. To our surprise, upon sufficient training, the network becomes agnostic to the input audio and provides the same output irrespective of the input. Interestingly, we also observe similar behaviour in the previous state-of-the-art models \cite{tsiami2020stavis} for audio-visual saliency prediction. Our findings contrast with previous works on deep learning-based audio-visual saliency prediction, suggesting a clear avenue for future explorations incorporating audio in a more effective manner. The code and pre-trained models are available at https://github.com/samyak0210/ViNet.

Related papers

• Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language [77.33458847943528]
  We present DenseAV, a novel dual encoder grounding architecture that learns high-resolution, semantically meaningful, and audio-visually aligned features solely through watching videos. We show that DenseAV can discover the meaning'' of words and the location'' of sounds without explicit localization supervision.
  arXiv  Detail & Related papers  (2024-06-09T03:38:21Z)
• Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding [57.08832099075793]
  Visually-guided sound source separation consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. This paper presents audio-visual predictive coding (AVPC) to tackle this task in parameter harmonizing and more effective manner. In addition, we develop a valid self-supervised learning strategy for AVPC via co-predicting two audio-visual representations of the same sound source.
  arXiv  Detail & Related papers  (2023-06-19T03:10:57Z)
• CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective [30.995357472421404]
  Video Saliency Prediction (VSP) imitates the selective attention mechanism of human brain. Most VSP methods exploit semantic correlation between vision and audio modalities but ignore the negative effects due to the temporal inconsistency of audio-visual intrinsics. Inspired by the biological inconsistency-correction within multi-sensory information, a consistency-aware audio-visual saliency prediction network (CASP-Net) is proposed.
  arXiv  Detail & Related papers  (2023-03-11T09:29:57Z)
• Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos [101.83513408195692]
  We propose a multitask learning method for visual-audio saliency prediction and sound source localization on multi-face video. The proposed method outperforms 12 state-of-the-art saliency prediction methods, and achieves competitive results in sound source localization.
  arXiv  Detail & Related papers  (2021-11-05T14:35:08Z)
• TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation [35.93516937521393]
  We introduce TriBERT -- a transformer-based architecture inspired by ViLBERT. TriBERT enables contextual feature learning across three modalities: vision, pose, and audio. We show that the learned TriBERT representations are generic and significantly improve performance on other audio-visual tasks.
  arXiv  Detail & Related papers  (2021-10-26T04:50:42Z)
• SVSNet: An End-to-end Speaker Voice Similarity Assessment Model [61.3813595968834]
  We propose SVSNet, the first end-to-end neural network model to assess the speaker voice similarity between natural speech and synthesized speech. The experimental results on the Voice Conversion Challenge 2018 and 2020 show that SVSNet notably outperforms well-known baseline systems.
  arXiv  Detail & Related papers  (2021-07-20T10:19:46Z)
• Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model [96.24038430433885]
  We propose a novel multi-modal video saliency model consisting of three branches: visual, audio and face. Experimental results show that the proposed method outperforms 11 state-of-the-art saliency prediction works.
  arXiv  Detail & Related papers  (2021-03-29T09:09:39Z)
• VGGSound: A Large-scale Audio-Visual Dataset [160.1604237188594]
  We propose a scalable pipeline to create an audio dataset from open-source media. We use this pipeline to curate the VGGSound dataset consisting of more than 210k videos for 310 audio classes. The resulting dataset can be used for training and evaluating audio recognition models.
  arXiv  Detail & Related papers  (2020-04-29T17:46:54Z)
• CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition [24.706843543488763]
  Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. Traditional deep learning methods require storing all previous class samples in the system and training the model again from scratch. In this work, we demonstrate a lifelong 3D convolutional framework -- c(C)la(a)ss increment(t)al net(Net)work (CatNet) We propose a two-stream CatNet, which deploys RGB and depth modalities to train two separate networks.
  arXiv  Detail & Related papers  (2020-04-20T11:36:02Z)
• STAViS: Spatio-Temporal AudioVisual Saliency Network [45.04894808904767]
  STAViS is a network that combines visual saliency and auditory features. It learns to appropriately localize sound sources and to fuse the two saliencies in order to obtain a final saliency map. We compare our method against 8 different state-of-the-art visual saliency models.
  arXiv  Detail & Related papers  (2020-01-09T15:34:04Z)

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.