Virual Oral Presentation Slide by Slide

IEEE/ICACT20240342 Slide.06        [Big Slide]	Oral Presentation
	For the unimodal feature extractions, we employ a pre-trained BERT-base model to encode the input textual tokens into word embedding, and take advantage of Long Short-Term Memory(LSTM) to extract audio and vision features. Next for the alignment part, we deploy a 1-dimensional convolution layer and a scale layer to align the dimension of feature vectors space. And for the Utterance-Level Feature Representations, we employ utterance-level attention(ULA) to learn the distinctive properties of unimodal modality, as for the detailed information, refer to the next page.

[Go to Next Slide]

Select Voice: Virtual Oral Presentation!!