Asd-Transformer: Efficient Active Speaker Detection Using Self And Multimodal Transformers.
Gourav DattaTyler EtchartVivek YadavVarsha HedauPradeep NatarajanShih-Fu ChangPublished in: ICASSP (2022)
Keyphrases
- detection method
- detection algorithm
- multi modal
- automatic detection
- false positives
- fuzzy logic
- cost effective
- visual perception
- detection accuracy
- false alarms
- computationally expensive
- lightweight
- object detection
- multimedia
- artificial intelligence
- computationally efficient
- face detection
- feature selection
- computer vision
- neural network