3 accepted papers
This paper explores the detection of frame-wise instances of violence in both audio and visual modalities, where only clip-level labels are available. Previous works selected fixed value of frames for objective optimization to model frame-level features, and applied straightforward fusion strategy t…
Most audio tagging models are trained with one-hot labels as supervised information. However, one-hot labels treat all sound events equally, ignoring the semantic hierarchy and proximity relationships between sound events. In contrast, the event descriptions contains richer information, describing t…
Mixup proves to be an efficient data augmentation method on audio classification tasks. Original mixup scheme directly mixes the waveform of two random samples, which not only ignores the temporal distribution of the sound events but may also interfere with the original sound events in another sampl…