| Virual Oral Presentation Slide by Slide |
IEEE/ICACT20230179 Slide.07
[Big Slide]
[YouTube] |
Oral Presentation |
|
|
- Secondly, the latent message vector is further compressed by average pooling on BERT embedding. The timestamp $\tau_n^k$ is embedd into latent vectors $\boldsymbol{E}_n^k(\tau)$ based on the time2vec. We also explore the effect of relative position of historical actions. The index embedding $\boldsymbol{P}^k$ is constructed by performing periodic trigonometric transformation of the positional variables $k$ | |
| [Go to Next Slide] |