Seeing through Sounds: Predicting Visual Semantic Segmentation Results from Multichannel Audio Signals.
Go IrieMirela OstrekHaochen WangHirokazu KameokaAkisato KimuraTakahito KawanishiKunio KashinoPublished in: ICASSP (2019)
Keyphrases
- audio signals
- semantic segmentation
- audio signal
- conditional random fields
- superpixels
- hidden markov models
- visual information
- weakly supervised
- scene classification
- object categories
- object classes
- visual features
- speaker identification
- machine learning
- object detection
- music information retrieval
- image registration
- image sequences
- information retrieval